JP2019076290A - Rehabilitation assistance system, rehabilitation assistance method, and rehabilitation assistance program - Google Patents

Abstract

To reduce deviation of a target distance set as rehabilitation from an exercise distance over which a user actually exercises.SOLUTION: A target object recognizability enhancing system comprises: an action detection unit to detect a first rehabilitation action of a user; a display control unit to control to display an avatar image that moves according to the detected first rehabilitation action, a target image that indicates a target of the first rehabilitation action, and at least one legibility assistance image for improving legibility of the target image; an evaluation unit to compare the first rehabilitation action with a target position represented by the target image to evaluate the rehabilitation ability of the user; and an update unit to update the target position according to the evaluation result from the evaluation unit.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a target recognition system, a method of improving target recognition, and a program for improving target recognition.

  In the above technical field, Patent Document 1 discloses a system for supporting rehabilitation performed for hemiplegic patients due to stroke and the like.

JP, 2015-228957, A

  However, in the technique described in the above document, there is a problem that when a large target is presented to a patient with low cognitive function from the viewpoint of visibility, the divergence between the exercise distance and the target distance becomes large.

  An object of the present invention is to provide a technique for solving the above-mentioned problems.

In order to achieve the above object, a system for improving target object recognition according to the present invention is:
Motion detection means for detecting a first rehabilitation motion of the user;
Display control for displaying an avatar image moving according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid for improving the visibility of the target image Means,
An evaluation unit that evaluates the user's rehabilitation ability by comparing the first rehabilitation operation with the target position represented by the target image;
Updating means for updating the target position according to the evaluation result by the evaluation means;
Equipped.

In order to achieve the above object, the method for improving target object recognition according to the present invention is:
A motion detection step of detecting a first rehabilitation motion of the user;
Display control for displaying an avatar image moving according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid for improving the visibility of the target image Step and
An evaluation step of evaluating the rehabilitation ability of the user by comparing the first rehabilitation operation with a target position represented by the target image;
An updating step of updating the target position according to the evaluation result in the evaluation step;
including.

In order to achieve the above object, a target recognition improvement program according to the present invention is:
A motion detection step of detecting a first rehabilitation motion of the user;
Display control for displaying an avatar image moving according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid for improving the visibility of the target image Step and
An evaluation step of evaluating the rehabilitation ability of the user by comparing the first rehabilitation operation with a target position represented by the target image;
An updating step of updating the target position according to the evaluation result in the evaluation step;
On a computer.

  According to the present invention, it is possible to suppress the deviation between the target distance set as rehabilitation and the exercise distance which the user actually exercises.

BRIEF DESCRIPTION OF THE DRAWINGS It is a block diagram which shows the structure of the target object recognition efficiency improvement system which concerns on 1st Embodiment of this invention. It is a block diagram which shows the structure of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a flowchart which shows the flow of a process of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure which shows the other structure of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure which shows the structure of the database of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure explaining the outline of operation | movement of the target object recognition efficiency improvement system which concerns on a base technology. It is a figure explaining the outline of operation | movement of the target object recognition efficiency improvement system which concerns on a base technology. It is a figure explaining an outline of operation of a target object recognition efficiency improvement system concerning a 3rd embodiment of the present invention. It is a figure explaining the arrangement position of the visual recognition auxiliary image in the target object recognition efficiency improvement system concerning a 3rd embodiment of the present invention. It is a figure explaining the other example of the visual recognition auxiliary | assistant image in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention. It is a figure explaining the further another example of the visual recognition assistance image in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention. It is a figure explaining the further another example of the visual recognition auxiliary | assistant image in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention. It is a figure explaining the further another example of the visual recognition assistance image in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention. It is a figure explaining the further another example of the visual recognition assistance image in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention. It is a figure explaining the further another example of the visual recognition assistance image in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention. It is a block diagram explaining the composition of the target object recognition efficiency improvement system concerning a 3rd embodiment of the present invention. It is a figure explaining an example of the patient table which the object recognition performance improvement server contained in the object recognition efficiency improvement system concerning a 3rd embodiment of the present invention has. It is a figure explaining an example of a display parameter table which a target object recognition efficiency improvement server contained in a target object recognition efficiency improvement system concerning a 3rd embodiment of the present invention has. It is a figure explaining an example of the image table which the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention has. It is a block diagram explaining the hardware constitutions of the target object recognition improvement server contained in the target object recognition improvement system concerning a 3rd embodiment of the present invention. It is a flowchart explaining the process sequence of the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention. It is a flowchart explaining the process sequence of the visual recognition assistance image display of the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention. It is a block diagram explaining the composition of the target object recognition efficiency improvement system concerning a 4th embodiment of the present invention. It is a figure explaining an example of the sound table which the target object recognition performance improvement server contained in the target object recognition performance improvement system concerning a 4th embodiment of the present invention has. It is a figure explaining the hardware constitutions of the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system concerning a 4th embodiment of the present invention. It is a flowchart explaining the process sequence of the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system which concerns on 4th Embodiment of this invention. It is a flowchart explaining the process procedure of the sound output control of the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system which concerns on 4th Embodiment of this invention.

  Hereinafter, exemplary embodiments of the present invention will be exemplarily described in detail with reference to the drawings. However, the configuration, the numerical values, the flow of processing, the functional elements, and the like described in the following embodiments are merely examples, and modifications and changes are free, and the technical scope of the present invention is described in the following description. It is not for the purpose of limiting.

First Embodiment
A target object recognition performance improvement system 100 according to a first embodiment of the present invention will be described with reference to FIG. The information processing system 100 is a system that supports the rehabilitation performed for the user 110.

  As shown in FIG. 1, the target object recognition performance improvement system 100 includes an operation detection unit 101, a display control unit 102, an evaluation unit 103, and an update unit 104.

  The motion detection unit 101 detects a first rehabilitation motion of the user 110. The display control unit 102 displays an avatar image that moves according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid image that improves the visibility of the target image. Let The evaluation unit 103 evaluates the rehabilitation ability of the user 110 by comparing the first rehabilitation operation with the target position represented by the target image. The update unit 104 updates the target position according to the evaluation result by the evaluation unit.

  According to the present embodiment, it is possible to suppress the deviation between the target distance set as rehabilitation and the exercise distance at which the user actually exercises.

Second Embodiment
Next, a rehabilitation support system 200 according to a second embodiment of the present invention will be described with reference to FIG. FIG. 2 is a diagram for explaining the configuration of the rehabilitation support system according to the present embodiment.

  As shown in FIG. 2, the rehabilitation support system 200 includes a rehabilitation support server 210, two base stations 231 and 232, a head mounted display 233, and two controllers 234 and 235. The head mounted display 233 may be a non-transmissive type, a video see-through type, or an optical see-through type.

  The rehabilitation support server 210 also includes a motion detection unit 211, a display control unit 212, an evaluation unit 213, an update unit 214, a voice input / output unit 215, a target database 216, and a background image + question / answer database 217.

  The motion detection unit 211 acquires the position of the controller 234 or 235 held by the user 220 and the position of the head mounted display 233 via the base station 231 or 232, and detects the rehabilitation motion of the user 220 based on the change in the position. .

  The display control unit 212 causes the head mount display 233 to display an avatar image that moves according to the detected rehabilitation operation and a target image that indicates the target of the rehabilitation operation. FIG. 3 is a view showing an example of avatars 311 and 312 on the screen 301 displayed on the head mounted display 233. As shown in FIG. The avatars 311 and 312 are superimposed on the background image 313 and displayed. In this example, the avatars 311 and 312 have the same shape as the controllers 234 and 235, and move in the screen 301 in accordance with the movements of the controllers 234 and 235. In addition, the background image 313 changes in accordance with the position and orientation of the head mounted display 233. As displayed in the avatars 311 and 312, buttons are prepared in the controllers 234 and 235 so that various setting operations can be performed. Here, as the background image 313, a landscape image (for example, a moving image obtained by shooting a town in New York) obtained by imaging an actual landscape is displayed. As a landscape image, an image of a road around a rehabilitation facility may be used, and it is possible to make it feel as if you are taking a walk in a foreign country, or to feel as you are taking a walk in a familiar place. By superimposing the landscape image, it is possible to realize training in a large amount of information while entertaining the patient.

  Further, for example, as shown in FIG. 4, the display control unit 212 superimposes the background image 313 on the screens 401 to 403 of the head mounted display 233, and displays the object 411. The object 411 gradually changes the display position and size so as to be lowered from the overhead direction of the user 220 downward. The user 220 moves the controllers 234 and 235 to bring the avatar image 311 on the screen closer to the object 411. When the avatar image 311 hits the object 411, the object 411 disappears.

  The evaluation unit 213 evaluates the user's rehabilitation ability by comparing the rehabilitation operation detected by the operation detection unit 211 with the target position represented by the target image displayed by the display control unit 212. Specifically, it is determined by comparison of the position in the three-dimensional virtual space whether or not the avatar image 311 moved according to the rehabilitation operation detected by the operation detection unit 211 and the object 411 as a target image overlap. . As a result, if they overlap, it is evaluated that one rehabilitation operation has been cleared, and points are added. The positions in the depth direction of the object 411 are prepared in various stages (for example, three stages), and different points (high points for distant objects, low points for near objects) are set respectively.

  The updating unit 214 updates the target task according to the accumulated points. For example, the target task may be updated using the task achievement rate (the number of goals achieved / the number of tasks) or the like.

  FIG. 5 is a flowchart showing the flow of processing in the rehabilitation support server 210. In step S501, as a calibration process, the target of the rehabilitation operation is initialized to the user. Specifically, each patient is first required to work in the actionable range as a calibration, and after setting it to an initial value, the target is initialized according to the user.

  Also, with reference to the target database 216, a target is set according to the user's attribute information (for example, whether it is an athlete or Parkinson's disease). For example, in the case of an injured sports player, an initial value that does not aggravate the injury is set, and in the case of a user who suffers from Parkinson's disease, an exercise that causes the progression of a medical condition is set as an initial value. Do. Furthermore, each patient is first required to work in the action range, and after setting it to the initial value, the target is initialized to the user.

  Next, in step S503, avatar images 311 and 312 are displayed according to the positions of the controllers 234 and 235 detected by the operation detection unit 211. Further, in step S505, the object 411 is displayed at the position and speed according to the set task.

  In step S507, the motion of the avatars 311 and 312 is compared with the motion of the object 411 to determine whether the task has been cleared. If the task has not been cleared, the process returns to step S505, and the next object is displayed without changing the difficulty level of the task.

  If the task has been cleared, the process proceeds to step S509, and the cumulative point, the task achievement probability, and the like are calculated. Further, the process proceeds to step S511 to compare the accumulated points and the task achievement probability with the threshold T, and when the accumulated points and the task achievement probability etc exceed the predetermined threshold T, the process proceeds to step S513 to update the exercise intensity of the task. . If the cumulative points, the task achievement probability, and the like do not reach the threshold T, the process returns to step S505, and the next object is displayed without changing the degree of difficulty of the task.

  For example, when the achievement level of the short distance exceeds 80% (or may be 10 times, etc.), the display frequency of the medium distance object is increased. If the achievement of the medium distance object exceeds 80% (or even 10 times or so), the display frequency of the long distance object is increased.

  The update of the task here is also changed in accordance with the user's attributes (such as an injured athlete or a patient with Parkinson's disease, etc.). As a method of updating the task, a method of switching the background image may be considered.

  After updating the task, the process proceeds to step S515, where the degree of fatigue of the user is calculated and compared with the threshold N. If the degree of fatigue exceeds a predetermined threshold, the processing is terminated as "stop condition". For example, it can be calculated as (degree of fatigue = 1−recovery of the most proximal object). Alternatively, it may be calculated as (degree of fatigue = 1 / eye movement). If you are not clearly focused (not looking for an object at all, don't shake your head, etc.), it will be meaningless to continue rehabilitation further, so you will take a break. Furthermore, the degree of fatigue may be calculated by detecting (accelerating) a decrease in speed when extending the arm.

  Also, for example, if the accumulated point exceeds a predetermined threshold, as shown in the character image 601 of FIG. 6, which of the two controllers 234 and 235 should be used to touch the object 411 with the left or right controller (here, right) To indicate. This makes it necessary to have a cognitive function that recognizes characters, increases the difficulty of movement, and requires a higher motor function. In other words, dual tasks of cognitive function and motor function are required.

  In FIG. 6, the instruction is given by characters, but the present invention is not limited to this, and the instruction may be given by an arrow, a color or a voice. Thus, in the present embodiment, the load is updated according to the evaluation of the rehabilitation operation.

(About dual task)
Healthy people are doing two or more things at the same time, such as "walk while talking" in normal daily life. Such "the ability to do two things simultaneously" declines with age. For example, "if you talk while walking, you will stop your leg" and so on. It is thought that the cause of the fall of the elderly is not only "the decrease in motor function" but also "the decrease in ability to do two things at the same time". In fact, there are many elderly people who fall after returning home even though it is judged that rehabilitation sufficiently restores their motor function. One of the factors is that rehabilitation is being performed with the environment and conditions in which it is possible to concentrate on the rehabilitation operation. That is, in the living environment, it is often the operation under the condition that factors that can not concentrate on the operation such as poor visibility, the presence of an obstacle, and the conversational awareness.

  Therefore, it is considered important to carry out rehabilitation that disperses attention, and it is desirable to train specifically by giving dual tasks. Such dual task training is an effective program not only for the fall of elderly people but also for the prevention of dementia.

  Dual task training includes training that combines two types of exercise tasks, as well as training that combines cognitive tasks and exercise tasks.

  The cognitive task + exercise task includes training such as walking while subtracting one by one from 100, and the exercise task + exercise task includes training such as walking so as not to spill the water in the cup.

  The evaluation unit 213 evaluates that the fall risk is high if the walking speed is delayed by about 20% in the dual task walking test as compared to simple walking, and notifies the display control unit 212 to repeat the dual task. .

  The person with relatively high mobility is more likely to have dual tasks. For example, if you are an elderly person who can not release the cane even if you move indoors, strengthening the balance ability (such as muscle strength and sense of balance) has higher priority than the dual task ability. As a rough judgment, it can be said that the person in need of support needs dual task ability, and the person in need of care needs balance ability other than dual task ability. Display the time series of calibration and visually show the improvement of one's movement range.

(Setting change by user attribute)
For patients who can expect normal improvement (subject to orthopedic disease such as bone fracture and complete improvement assumed), set the hardest rehabilitation operation and accelerate improvement.

  For patients with different degrees of improvement depending on the individual (patients who have different forms of paralysis depending on the lesion site in cerebral infarction etc.), the load of the task is improved to a certain extent. Stop.

  In patients with Parkinson's disease, etc., whose function is basically reduced, it is useful to constantly evaluate the current assessment of their ability to move.

(Another dual task training example)
FIG. 7 is a view showing another exemplary image for dual task training. By placing a loss on the object (bomb), the cognitive function is required. Alternatively, as shown in FIG. 8, a question image (here, multiplication as an example) may be superimposed and displayed on the background screen, and only the acquisition of the object for which the answer is displayed may be evaluated. The background screen may display one of Goo, Choi, and Pa, and may request collection of an object with a win mark.

  Furthermore, the object may simply be displayed with numbers, and only the acquisition of objects with large numbers may be evaluated. In addition, when a signal is displayed in the background image 313 and an object is picked up in the case of a red signal, the evaluation unit 213 may make the point negative.

  According to the present embodiment, since the task is updated according to the degree of achievement (such as the achievement probability) of the rehabilitation operation, it is possible to give the user a load according to the progress of the rehabilitation. In addition, displaying the background image 313 makes it possible not only to enjoy the patient but also to perform rehabilitation in a situation in which the user is conscious about the surroundings, and a safer life can be realized when returning to the real world.

  FIG. 9 is a diagram showing another dual task training example. The voice input / output unit 215 outputs the question voice regarding the background image to the headphone 901 as shown in FIG. 9, and acquires the answer to the question via the microphone 902 provided on the head mounted display 233. The evaluation unit 213 performs voice recognition processing on the response acquired as voice information, compares it with the response prepared in advance, and evaluates the user's rehabilitation ability according to the comparison result.

  FIG. 10 is a diagram showing an example of the contents of the background image / question / answer database 217. As shown in FIG. The question voice, the answer and the point are stored in association with the background moving image.

  As the user's reaction, it is expected that the dual task results in a decrease in the object recovery rate. We expect the result that the recovery achievement rate of objects does not differ even if dual task is displayed as a goal. The recovery rate of objects or the reach rate to objects is compared at single task time and dual task time, and training is repeated until it falls within a certain range.

  The above is dual task training that simultaneously requires motor function and cognitive function, but the present invention is not limited to this, and may be dual task training which requires two motor functions simultaneously.

  For example, as shown in FIG. 11, it may be required to pick up the object 411 while avoiding the flying object 1111. By detecting the position of the sensor provided on the head mounted display 233, it can be determined whether or not the object 1111 has been successfully taken. The evaluation and the update of the task may be performed based on the achievement points (for example, the achievement rate) of both of the two rehabilitation operations.

  For example, as shown in the image 1201 of FIG. 12, as the avatar image which moves according to the operation of the controller 234, 235, the cup images 1211, 1212 containing water are displayed, and these cup images 1211, 121 are moved. The object 411 may be collected. However, as shown in the image 1202, when water is spilled by tilting the cup image 1221, points can not be obtained even if the object 411 is recovered by the cup image 1222. Points are added only when the object 411 is recovered without spilling water in the cup images 1231 and 1232 as in the image 1203.

  In addition, it may be considered that the avatar image on the opposite side to the avatar image on the object recovery side is required to always touch a designated place. The controller 234 or 235 may request that the object be collected while pressing a designated button a predetermined number of times. In addition, when a sensor for acquiring the movement of the user's foot is provided, the specified movement of the foot may be requested.

Third Embodiment
Next, a target object recognition performance improvement system according to a third embodiment of the present invention will be described using FIGS. 13A to 17B. FIG. 13A is a diagram for explaining the outline of the operation of the base technology of the target object recognition efficiency improvement system according to the present embodiment. FIG. 13B is a diagram for describing an outline of the operation of the base technology of the target object recognition efficiency improvement system according to the present embodiment. The target object recognition performance improvement system according to the present embodiment is different from the second embodiment in that a visual recognition auxiliary image for improving the recognition performance (for example, the visibility) of a target image is displayed. The other configurations and operations are similar to those of the second embodiment, and therefore the same configurations and operations are denoted by the same reference numerals and the detailed description thereof is omitted.

  In the base technology, the movement distance of avatar image 1320, that is, the movement distance 1312 of user 220 is measured by the distance between reference 1310 and the sensor of avatar image 1320 (the head portion of avatar image 1320). Then, a target distance 1311 which is a distance that the user 220 has to move an arm or the like is determined based on the distance between the reference 1310 and the reference line 1331 of the object 1330 as a target image. Then, the user 220 moves the avatar image 1320 closer to the object 1330 as a rehabilitation exercise.

  However, as shown in FIG. 13B, when the avatar image 1320 touches the vertex 1332 of the object 1330, the system determines that one of the user 220's rehabilitation operations has ended, and a new object 1330 is taken as the next goal. indicate.

  As a provider of the system, as a rehabilitation exercise, the avatar image 1320 is desired to be in contact with the object 1330 when the user 220 is fully extended. However, if the size of the object 1330 is large (the distance between the apex and the reference line 1331 is large), it is determined that the object 1330 is touched only by touching the avatar image 1320 at the end of the object 1330. Therefore, since the user 220 can not move the arm by the distance initially assumed, it is difficult to obtain the expected rehabilitation effect.

  In addition, since the user 220 can also touch the object 1330 before the arm is extended and cut, a sense of accomplishment and satisfaction due to the rehabilitation exercise can not be sufficiently obtained, and the motivation for rehabilitation may be lowered. .

  In this case, an exercise distance 1312 which is a distance by which the avatar image 1320 has actually moved deviates from a target distance 1311 which is a distance that the user 220 has to move originally. Therefore, the user 220 does not exercise the exercise distance 1312 set before the start of rehabilitation, and the effect obtained by rehabilitation is also smaller than the expected effect.

  For example, the length of one side of the object 1330 is 20.0 cm, and the diameter 1321 of the sensor unit (the head portion of the avatar image 1320) of the avatar image 1320 is 5.0 cm. In this case, when the user 220 brings the avatar 1320 into contact with the apex 1332 instead of the reference line 1331 of the object 1330, an error of about 10.0 cm occurs between the target distance 1311 and the movement distance 1312.

  Therefore, since the user 220 does not move the avatar image 1320 by the exercise distance 1312 assumed before the start of rehabilitation, the effect of the rehabilitation which the user 220 should have been able to enjoy will be reduced.

  If the size of the object 1330 is reduced so that the user 220 touches the object 1330 when the user stretches his or her arm, it becomes difficult for the user 220 to visually recognize the position of the object 1330 in the screen. If the object 1330 can not be viewed, rehabilitation is not established.

  Therefore, the sensor part (reaction part) of avatar image 1320 is made into a field smaller than the head part of avatar image 1320. This makes it possible to further reduce the deviation (error) between the target distance 1311 and the movement distance.

  FIG. 13C is a diagram for describing an outline of the operation of the target object recognition performance improvement system according to the present embodiment. Therefore, in the present embodiment, the central portion of the object 1330 is darkened to be a reaction portion so that a deviation does not occur between the assumed target distance 1311 and the movement distance 1312 by the avatar image 1320. Then, the gradation of the portion around the reaction portion of the object 1330 is lightened. That is, the size of the object 1330 shown in FIGS. 13A and 13B is reduced, and the periphery thereof is surrounded by the visual aid 1133 larger than the object 1330. That is, the object 1330 and the visual recognition auxiliary image 1333 are superimposed and displayed.

  From the viewpoint of the user 220, when the size of the object 1330 is reduced, the object 1330 becomes difficult to see (the visibility decreases), but the visual aid image is displayed around the reduced object 1330 to compensate for the decrease in visibility. Arrange 1333.

  For example, the length of one side of the object 1330 is 5.0 cm, the length of one side of the visual assistant image 1333 is 20.0 cm, and the diameter of the sensor unit 1322 of the avatar image 1320 is 2.0 cm. Then, the error (deviation) between the target distance 1311 and the movement distance 1312 decreases to around 2.0 cm.

  Thereby, the deviation (error) between the target distance 1311 and the movement distance 1312 is reduced while preventing the decrease in the visibility of the object 1330 due to the difference in gradation and the difference in size of the object 1330 and the visual auxiliary image 1333. Can. As a secondary effect, the experience level when the avatar image 1320 is brought into contact with the object 1330 is increased. That is, for the user 220, the sense when touching the object 1330 becomes clear, and the joy of achieving the goal of rehabilitation also rises.

  FIG. 13D is a view for explaining the arrangement position of the visual recognition auxiliary image in the target object recognition efficiency improvement system according to the present embodiment. In FIG. 13C, the object 1330 as the target image is displayed so as to be included in the visual aid auxiliary image 1333 and is disposed near the center of the visual aid auxiliary image 1333.

  However, as shown in FIG. 13D, the object 1330 may be arranged near the lower side of the near side of the visual aid image 1333. That is, the object 1330 may be arranged on the front side as viewed from the user 220. As described above, the object 1330 may be disposed at any position of the visual assistance image 1333 as long as the object 1330 is displayed so as to be included in the visual recognition assistance image 1333. As described above, when the size of the object 1330 is reduced and the deviation between the target distance 1311 and the movement distance 1312 is reduced, the visibility of the object 1330 is reduced. Therefore, in order to improve the visibility of the object 1330, the visibility assistance image 1333 larger than the object 1330 is displayed around the object 1330 to compensate for the decrease in the visibility of the object 1330. Note that the visual aid 1133 for improving the visibility of the object 1330 is not limited to the cube shown in this case where the magnification of the cubic object 1330 is enlarged.

  Next, another shape of the visual identification auxiliary image 1333 will be described with reference to FIGS. 13E to 13I. FIG. 13E is a view for explaining another example of the visual recognition auxiliary image in the target object recognition efficiency improvement system according to the present embodiment. FIG. 13F is a view for explaining still another example of the auxiliary visual recognition image in the target object recognition efficiency improvement system according to the present embodiment. FIG. 13G is a view for explaining still another example of the auxiliary visual recognition image in the target object recognition efficiency improvement system according to the present embodiment. FIG. 13H is a view for explaining still another example of the auxiliary visual recognition image in the target object recognition efficiency improvement system according to the present embodiment. FIG. 13I is a view for explaining still another example of the auxiliary visual recognition image in the target object recognition efficiency improvement system according to the present embodiment.

  As shown in FIG. 13E, the visual recognition auxiliary image 1340 may have, for example, an arrow shape indicating the position where the object 1330 is present. Then, the object 1330 is not included in the arrow-shaped visual aid 1340. In other words, the visual aid image 1340 is disposed outside the object 1330, instead of the object 1330 as the target image and the visual aid image 1340 being displayed in an overlapping manner. As described above, with the aid of the arrow-shaped visual aid 1340, the user 220 can easily recognize that the object 1330 is present at the tip of the tip of the arrow.

  As shown in FIG. 13F, the viewing assistance image 1350 may be shaped to draw the user's 220 attention. The shape that draws the user's 220 attention is not limited to the shape shown in FIG. 13F, and may be, for example, a star shape, a cross shape, a polygon shape, or the like. The vertical line 1351 and the horizontal line 1352 may be displayed together to indicate that the object 1330 is disposed at the center of the vertical line 1351 and the horizontal line 1352.

  As shown in FIG. 13G, the visual aid image 1360 may be an alternate long and short dash line extending from the sensor unit 1322 of the avatar image 1320 toward the object 1330. Note that the visual aid image 1360 is not limited to the one-dot and dash line, and may be, for example, a straight line, a two-dot and dash line, or a dotted line.

  Then, the user 220 can visually recognize the object 1330 and recognize the existing position of the object 1330 by moving the line of sight along the dashed dotted line with the dashed dotted line as a guideline. Furthermore, moving the avatar image 1320 along the alternate long and short dash line allows the object 1330 to touch the avatar image 1320. In addition, when the visual recognition assistance image 1333 is displayed together with the visual recognition assistance image 1370, the visibility of the object 1330 is further improved.

  As shown in FIG. 13H, the visual aid 1130 may have a plurality of arrows arranged on a straight line from the sensor unit 1322 toward the object 1330. Then, the user 220 can visually recognize the object 1330 by recognizing the position of the object 1330 by moving the line of sight along the plurality of arrows with the plurality of arrows as a guideline. Furthermore, moving the avatar image 1320 along the plurality of arrows allows the object 1330 to touch the avatar image 1320. Note that if the cube auxiliary visual image 1333 is displayed together with the visual auxiliary image 1370, the visibility of the object 1330 is further improved.

  As shown in FIG. 13I, a plurality of spherical visual aids 1380 are arranged at the top, bottom, left, and right of the object 1330. That is, in FIG. 13I, a plurality of spherical visual aids 1380 are arranged around the object 1330 such that the object 1330 is arranged at the center of the four visual aids 1380. The shape of the visual aid image 1380 is not limited to a spherical shape, and may be, for example, a triangular shape, a rectangular shape, a polygonal shape, a star shape, or the like.

  FIG. 13J is a view for explaining still another example of the auxiliary visual recognition image in the target object recognition efficiency improvement system according to the present embodiment. For example, the target object recognition performance improvement server may change the size of the visual assistance image 1333 displayed on the display unit 1402 according to the progress of the rehabilitation of the user 220. For example, the target object recognition performance improvement server displays a larger visual aid image 1333 at the initial stage of rehabilitation. Then, in a state where the rehabilitation of the user 220 has progressed, the size of the visual identification auxiliary image 1333 may be reduced according to the progress of the rehabilitation.

  In addition, the target object recognition performance improvement server may change the size of the visual assistance image 1333 in accordance with the visual acuity of the user 220, for example, in accordance with the progress of the rehabilitation of the user 220. That is, the target object recognition performance improvement server displays the larger visual assistance image 1333 if the user 220 has poor vision, and displays the smaller visual assistance image 1333 if the user 220 has relatively good vision. It is also good. Thus, the target object recognition performance improvement server may display a visual aid image of a size according to the visual acuity of the user 220.

  In addition, for example, when the user 220 is a dementia, the target object recognition performance improvement server may display a visual aid 1133 having a size that matches the progress of the dementia or the cognitive function. In addition, even if the target recognition improving server automatically changes the size of the visual recognition auxiliary image 1333, the operator such as a doctor who operates the target recognition improving system manually changes it, and the user 220 changes it. You may

  FIG. 14 is a block diagram for explaining the configuration of the target object recognition performance improvement system according to the present embodiment. The target object recognition performance improvement system 1400 has a target object recognition performance improvement server 1401 and a display unit 1402. In addition, the element contained in the target object recognition efficiency improvement system 1400 is not limited to these. The target object recognition performance improvement server 1401 includes an operation detection unit 1411, a display control unit 1412, an evaluation unit 1413, and an update unit 1414.

  The operation detection unit 1411 acquires the position of the controller held by the user 220 and the position of the head mounted display mounted by the user 220, and the movement of the user 220 based on the acquired change in position ( Detect rehabilitation action).

  The display control unit 1412 displays, on the display unit 1402, an avatar image 1320 that moves according to the detected rehabilitation operation, a target image indicating the target of the rehabilitation operation, and at least one visual aid 1133 for improving the visibility of the target image. Display on etc.

  The display control unit 1412 superimposes and displays the target image and the visual recognition auxiliary image 1333. For example, the size of the target image is made smaller than the size of the visual recognition auxiliary image 1333, and the target image is displayed so as to be included in the visual recognition auxiliary image 1333.

  The display control unit 1412 may cause the target image to be displayed, for example, in the vicinity of the center of the visual recognition auxiliary image 1333. In addition, the display control unit 1412 displays the target image not in the vicinity of the center of the visual recognition auxiliary image 1333 but in the visual recognition auxiliary image 1333 and further near the avatar image 1320, that is, the front side as viewed from the user 220 You may

  The display control unit 1412 may display the object 1330 and the visual recognition auxiliary image 1333 in a distinguishable manner. Specifically, for example, the gradation of the object 1330 is displayed darker than the gradation of the visual identification auxiliary image 1333. As a result, since the object 1330 is displayed dark, the user 220 has a difference in contrast with the lightly displayed auxiliary visual image 1333 and can reliably recognize the object 1330. In addition, how to put the gradation to the object 1330 and the visual recognition auxiliary image 1333 is not limited to the method shown here. For example, even a user 220 with weak vision may use a gradation that can reliably identify the object 1330 and the visual aid 1133.

  In addition, the display control unit 1412 displays the object 1330 and the visual assistance image 1333 in different colors in order to display the object 1330 and the visual recognition assistance image 1133 in a distinguishable manner. For example, the display control unit 1412 colors the object 1330 with a dark color and colors the visual aid image 1333 with a light color, but the combination (pattern) of colors to be colored is not limited to this. For example, even a user 220 with color blindness (color blindness) may be colored in a combination of colors that can reliably identify the object 1330 and the visual aid 1133. In addition, the display control unit 1412 may perform coloring that can correspond to various types of users 220 such as low vision, visual field narrowing, and color vision abnormalities. Note that the user 220 may select the color to be used to color the object 1330 and the visual recognition auxiliary image 1333 or may be selected by an operator such as a doctor.

  Although the gradation and color of the object 1330 and the auxiliary visual image 1333 have been described here, the gradation and color may be similarly changed for the other auxiliary visual images 1340, 1350, 1360, 1370, and 1380. .

  Furthermore, the display control unit 1412 controls the change of the display of the visual recognition auxiliary image 1333 according to at least one of the visual acuity of the user 220 and the evaluation result by the evaluation unit 1413. For example, the display control unit 1412 changes the size of the viewing assistance image 1333 according to the visual acuity of the user 220, the progress of the rehabilitation of the user 220, the progress of the dementia of the user 220, and the like.

  The evaluation unit 1413 evaluates the rehabilitation ability of the user 220 in comparison with the rehabilitation operation detected by the operation detection unit 1411 and the target position represented by the object 1330 as the target image displayed by the display control unit 1412.

  The update unit 1414 updates the target position represented by the object 1330 according to the evaluation result by the evaluation unit 1413.

  The display unit 1402 displays a target image, a visibility auxiliary image, and the like according to the control of the display control unit 1412. The display unit 1402 is a head mounted display, a display, a screen, or the like, but is not limited thereto.

  FIG. 15A is a view for explaining an example of a patient table included in the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. The patient table 1501 stores attribute information 1512, rehabilitation target 1513, current level 1514 and rehabilitation menu 15115 in association with a patient ID (Identifier) 1511. The patient ID 1511 is an identifier for identifying a patient. The attribute information 1512 is information indicating an attribute of a patient such as age and gender. The rehabilitation target 1513 is data indicating which part of the body of the patient is targeted for rehabilitation, and is data representing a part of the body such as an arm or a leg, for example.

  The current level 1514 is data indicating the patient's current level of rehabilitation. That is, it is data indicating the progress of rehabilitation of the patient. The data from the initial stage to the final stage of rehabilitation is divided into a plurality of ranks, such as A rank and B rank. In addition, how to divide the level of rehabilitation is not limited to this. The rehabilitation menu 1515 is information on a menu of rehabilitation that the patient should receive.

  Next, FIG. 15B is a diagram for explaining an example of a display parameter table included in the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. The display parameter table 1502 stores a target image ID 1521, a visual aid image ID 1522, and a display parameter 1523 in association with the rehabilitation menu 1515.

  The target image ID 1521 is an identifier for identifying an object 1330 to be displayed on the display unit 1402. The viewing assistance image ID is an identifier for identifying the viewing assistance image 1333, 1340, 1350, 1360, 1370, 1380 to be displayed on the display unit 1402. The display parameter 1523 is a parameter necessary for causing the display unit 1402 to display the object 1330 and the auxiliary visual image 1333, 1340, 1350, 1360, 1370, and 1380. The display parameter 1523 includes, for example, information such as position and magnification, but the information included in the display parameter 1523 is not limited to these.

  And FIG. 15C is a figure explaining an example of the image table which the target object recognition performance improvement server contained in the target object recognition performance improvement system concerning this embodiment has. The image table 1503 stores image data 1532, a display position 1533 and a magnification 1534 in association with the image type 1531. The items stored in the image table 1503 are not limited to these.

  The image type 1531 is information that distinguishes whether an image to be displayed is a target image or a visual aid image. The image data 1532 is image data of an object 1330 displayed on the display unit 1402, an auxiliary visual image 1333, and the like, and includes image data of various image file formats. The display position 1533 is data indicating which position in the display unit 1402 the display position should be displayed, and is, for example, data of a set of (X coordinate position, Y coordinate position, Z coordinate position). The magnification 1534 is data for determining what size the object 1330, the visual recognition auxiliary image 1333 or the like is to be displayed on the display unit 1402.

  Then, the target object recognition performance improvement server 1401 causes the display unit 1402 to display a visual aid image 1333, 1340, 1350, 1360, 1370, 1380 with reference to the tables 1501, 1502, 1503.

  FIG. 16 is a block diagram for explaining the hardware configuration of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. A central processing unit (CPU) 1610 is a processor for arithmetic control, and implements a functional component of the target object recognition performance improvement server 1401 in FIG. 14 by executing a program. A ROM (Read Only Memory) 1620 stores fixed data such as initial data and programs and other programs. Also, the network interface 1630 communicates with other devices via a network. Note that the CPU 1610 is not limited to one, and may be a plurality of CPUs or may include a GPU (Graphics Processing Unit) for image processing. Further, it is desirable that the network interface 1630 have a CPU independent of the CPU 1610 and write or read transmission / reception data in a region of a random access memory (RAM) 1640. Further, it is desirable to provide a DMAC (Direct Memory Access Controller) for transferring data between the RAM 1640 and the storage 1650 (not shown). Furthermore, it is desirable that the input / output interface 1660 have a CPU independent of the CPU 1610 and write or read out input / output data in the area of the RAM 1640. Therefore, the CPU 1610 recognizes that data has been received or transferred to the RAM 1640 and processes the data. Further, the CPU 1610 prepares the processing result in the RAM 640, and leaves the subsequent transmission or transfer to the network interface 1630, the DMAC, or the input / output interface 1660.

  The RAM 1640 is a random access memory used by the CPU 1610 as a temporary storage work area. In the RAM 1640, an area for storing data necessary for realizing the present embodiment is secured. The patient data 1641 is data on a patient who is to be rehabilitated using the target recognition system. The image data 1642 is data such as an object 1330 as a target image displayed on the display unit 1402 and a visual aid image 1333. The display position 1643 is data indicating at which position of the display unit 1402 the object 1330 or the visual recognition auxiliary image 1333 is to be displayed. The magnification 1644 is data indicating how large the image such as the object 1330 or the visual recognition auxiliary image 1333 is to be displayed on the display unit 1402. Then, these data are read from, for example, a patient table 1501, a display parameter table 1502 and an image table 1503.

  The input / output data 1645 is data input / output via the input / output interface 1660. Transmission / reception data 1646 is data transmitted / received via the network interface 1630. The RAM 1640 also has an application execution area 1647 for executing various application modules.

  The storage 1650 stores a database, various parameters, or the following data or program necessary for realizing the present embodiment. The storage 1650 stores a patient table 1501, a display parameter table 1502 and an image table 1503. The patient table 1501 is a table for managing the relationship between the patient ID 1511 and the attribute information 1512 shown in FIG. 15A. The display parameter table 1502 is a table for managing the relationship between the rehabilitation menu 1515 and the display parameter 1523 shown in FIG. 15B. The image table 1503 is a table for managing the relationship between the image type 1531 and the image data 1532 as shown in FIG. 15C.

  The storage 1650 further stores an operation detection module 1651, a display control module 1652, an evaluation module 1653 and an update module 1654.

  The motion detection module 1651 is a module that detects a rehabilitation motion of the user 220. The display control module 1652 is a module that causes the display unit 1402 to display an avatar image 1320, an object 1330 as a target image, and a visual aid image 1333 for improving the visibility of the object 1330. The evaluation module 1653 is a module for evaluating the rehabilitation ability of the user 220. The update module 1654 is a module that updates the target position represented by the target image according to the evaluation result. These modules 1651 to 1654 are read by the CPU 1610 to the application execution area 1647 of the RAM 1640 and executed. The control program 1655 is a program for controlling the entire target object recognition performance improvement server 1401.

  The input / output interface 1660 interfaces input / output data with input / output devices. A display unit 1661 and an operation unit 1662 are connected to the input / output interface 1660. Further, a storage medium 1664 may be connected to the input / output interface 1660. Furthermore, a speaker 1663 which is an audio output unit, a microphone which is an audio input unit, or a GPS (Global Positioning System) position determination unit may be connected. Note that, in the RAM 1640 and the storage 1650 shown in FIG. 16, programs and data regarding general-purpose functions and other realizable functions that the target object recognition performance improvement server 1401 has are not illustrated.

  FIG. 17A is a flowchart for describing the processing procedure of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. FIG. 17B is a flowchart for describing a processing procedure of visual aid image display of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. These flowcharts are executed by the CPU 1610 using the RAM 1640, and implement the functional components of the target object recognition performance improvement server 1401 of FIG.

  In step S1701, the target object recognition performance improvement server 1401 causes the display unit 1402 or the like to display a visual aid.

  In step S1721, the target object recognition performance improvement server 1401 acquires patient information such as an attribute of a patient to be rehabilitated and what kind of rehabilitation menu is to be received using the target object recognition performance improvement system 1400.

  In step S 1723, the target object recognition performance improvement server 1401 acquires display parameters necessary for displaying the visual recognition auxiliary image 1333 or the like to be displayed on the display unit 1402 on the display unit 1402. The display parameters to be acquired are, for example, parameters related to the position of the visual recognition auxiliary image 1333 or the like, the magnification and the like.

  In step S1725, the target object recognition performance improvement server 1401 acquires the image data of the visual recognition auxiliary image 1333. In step S1727, the target object recognition performance improvement server 1401 causes the display unit 1402 to display the visual recognition auxiliary image 1333 or the like.

  In step S1729, the target object recognition performance improvement server 1401 determines whether it is necessary to change the display of the visual recognition auxiliary image 1333 or the like. When the display change is not necessary (NO in step S1729), the target object recognition efficiency improvement server 1401 ends the processing. When the display change is necessary (YES in step S1729), the target object recognition efficiency improvement server 1401 proceeds to the next step.

  In step S1731, the target object recognition performance improvement server 1401 changes the size of the visual assistance image 1333 according to the evaluation result of the visual acuity of the user 220 and the rehabilitation ability of the user 220.

  According to the present embodiment, even if the size of the target image is reduced to reduce the deviation between the target distance and the movement distance, the target distance and the movement distance are brought close while maintaining the visibility of the target image. Can increase the effects of rehabilitation. In addition, since the user feels clear when touching the target image, the user can experience satisfaction with the goal achievement.

Fourth Embodiment
Next, a target object recognition performance improvement system according to a fourth embodiment of the present invention will be described using FIG. 18 to FIG. FIG. 18 is a block diagram for explaining the configuration of the target object recognition performance improvement system according to the present embodiment. The target object recognition performance improvement system according to the present embodiment differs from the second and third embodiments in that it has a sound output unit. The other configurations and operations are similar to those of the second and third embodiments, and therefore, the same configurations and operations are denoted by the same reference numerals and the detailed description thereof will be omitted.

  The target recognition performance improvement system 1800 includes a target recognition performance improvement server 1801 and a sound output unit 1802. The target object recognition performance improvement server 1801 has a sound output control unit 1811. The sound output control unit 1811 controls the sound output according to the positional relationship between the object 1330 as a target image and the avatar image 1320. The sound whose output is controlled by the sound output control unit 1811 is output from the sound output unit 1802.

  The sound output control unit 1811 outputs a sound based on, for example, the distance between the object 1330 and the avatar image 1320, that is, the positional relationship, when the object 1330 is lowered from the upper side to the lower side, for example.

  As the distance between the object 1330 and the avatar image 1320 decreases, that is, as the object 1330 approaches the avatar image 1320, the output sound may be a high frequency sound. Similarly, as the distance between the object 1330 and the avatar image 1320 increases, that is, as the object 1330 moves away from the avatar image 1320, the output sound may be a low frequency sound. That is, as in the Doppler effect, it represents an acoustic effect in which the frequency of the sound (wave) is observed differently according to the distance between the object 1330 (sound source) and the avatar image 1320 (user 220 (observer)) You may Note that instead of changing the frequency of the sound to be output, the volume of the sound to be output may be increased or decreased according to the distance between the object 1330 and the avatar image 1320.

  Also, the position of the object 1330 may be taught to the user 220 by outputting a sound from the sound output control unit 1811. That is, the user's 220 hearing is used to teach the position of the object 1330.

  For example, consider a case where the user 220 wears headphones when using the target object recognition efficiency improvement system 1800. When the object 1330 as the target image is on the right side of the avatar image 1320 (user 220), the target object recognition efficiency improvement server 1801 makes a sound from the headphones on the right ear side. Similarly, when the object 1330 is on the left side of the avatar image 1320 (user 220), sound is emitted from the headphones on the left ear side. Thus, the user 220 can determine whether the object 1330 is on the right side or on the left side of the user 220 from the direction of the sound. In addition, if the object 1330 is in front of the avatar image 1320 (user 220), sound is emitted from both headphones.

  Also, in the above description, the position of the object 1330 is taught using the visual and auditory sense of the user 220, but the object 220 is an object using the other five senses, taste, touch, smell and the like other than visual sense and auditory sense The position of 1330 may be taught.

  For example, the sensor may be placed on the tongue of the user 220, and the user 220 may feel a taste according to the position of the object 1330. Alternatively, a controller held by the user 220, headphones worn by the user 220, a head mounted display, or the like may be vibrated. That is, the position of the object 1330 may be taught using the sense of touch of the user 220.

  FIG. 19 is a diagram for explaining an example of a sound table of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. The sound table 1901 stores sound data 1911 in association with the image type 1531. Then, the target object recognition performance improvement server 1801 controls the sound to be output with reference to the sound table 1901.

  FIG. 20 is a diagram for describing a hardware configuration of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. A RAM 2040 is a random access memory used by the CPU 1610 as a temporary storage work area. In the RAM 2040, an area for storing data necessary for realizing the present embodiment is secured. The sound data 2041 is data relating to the sound to be output. Then, this data is read from, for example, the sound table 1901.

  The storage 2050 stores a database, various parameters, or the following data or program necessary for realizing the present embodiment. The storage 2050 stores a sound table 1901. The sound table 1901 is a table for managing the relationship between the image type 1531 and the sound data 1911 shown in FIG.

  The storage 2050 further stores a sound output control module 2051. The sound output control module 2051 is a module that controls the output of sound according to the positional relationship between the object 1330 as a target image and the avatar image 1320. The module 2051 is read by the CPU 1610 into the application execution area 1647 of the RAM 2040 and executed. In the RAM 2040 and the storage 2050 shown in FIG. 20, programs and data regarding general-purpose functions and other realizable functions possessed by the target object recognition performance improvement server 1801 are not shown.

  FIG. 21A is a flowchart for describing the processing procedure of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. FIG. 21B is a flowchart for describing the process procedure of the sound output control of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. These flowcharts are executed by the CPU 1610 using the RAM 2040, and implement the functional components of the target object recognition performance improvement server 1801 of FIG.

  In step S 2101, the target object recognition performance improvement server 1801 controls the output of sound. In step S <b> 2121, the target recognition performance improvement target recognition performance improvement server 1801 acquires the position of the avatar image 1320. In step S2123, the target object recognition performance improvement server 1801 acquires the position of the object 1330. In step S 2125, the target object recognition performance improvement server 1801 determines the positional relationship between the avatar image 1320 and the object 1330. In step S2127, the target object recognition performance improvement server 1801 controls the output of sound according to the determined positional relationship.

  According to the present embodiment, since rehabilitation is performed using hearing in addition to the user's vision, the user can more easily view the object, and the effect obtained by the rehabilitation can be further enhanced. Also, the user can grasp the position of the object not only by sight but also by hearing. Moreover, since the sound is output, even a user with weak vision can receive the rehabilitation according to the present embodiment.

[Other embodiments]
Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. The configurations and details of the present invention can be modified in various ways that can be understood by those skilled in the art within the scope of the present invention. Also included within the scope of the present invention are systems or devices that combine the different features included in each embodiment.

  Furthermore, the present invention may be applied to a system configured of a plurality of devices or to a single device. Furthermore, the present invention is also applicable to the case where an information processing program for realizing the functions of the embodiments is supplied to a system or apparatus directly or remotely. Therefore, in order to realize the functions of the present invention on a computer, a program installed on the computer, a medium storing the program, and a WWW (World Wide Web) server for downloading the program are also included in the scope of the present invention. . In particular, a non-transitory computer readable medium storing a program that causes a computer to execute at least the processing steps included in the above-described embodiment is included in the scope of the present invention.

  The present invention relates to a target recognition system, a method of improving target recognition, and a program for improving target recognition.

  In the above technical field, Patent Document 1 discloses a system for supporting rehabilitation performed for hemiplegic patients due to stroke and the like.

JP, 2015-228957, A

  However, in the technique described in the above document, there is a problem that when a large target is presented to a patient with low cognitive function from the viewpoint of visibility, the divergence between the exercise distance and the target distance becomes large.

  An object of the present invention is to provide a technique for solving the above-mentioned problems.

In order to achieve the above object, a system for improving target object recognition according to the present invention is:
Motion detection means for detecting a first rehabilitation motion of the user;
Display control for displaying an avatar image moving according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid for improving the visibility of the target image Means,
An evaluation unit that evaluates the user's rehabilitation ability by comparing the first rehabilitation operation with the target position represented by the target image;
Updating means for updating the target position according to the evaluation result by the evaluation means;
Equipped.

In order to achieve the above object, the method for improving target object recognition according to the present invention is:
A motion detection step of detecting a first rehabilitation motion of the user;
Display control for displaying an avatar image moving according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid for improving the visibility of the target image Step and
An evaluation step of evaluating the rehabilitation ability of the user by comparing the first rehabilitation operation with a target position represented by the target image;
An updating step of updating the target position according to the evaluation result in the evaluation step;
including.

In order to achieve the above object, a target recognition improvement program according to the present invention is:
A motion detection step of detecting a first rehabilitation motion of the user;
Display control for displaying an avatar image moving according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid for improving the visibility of the target image Step and
An evaluation step of evaluating the rehabilitation ability of the user by comparing the first rehabilitation operation with a target position represented by the target image;
An updating step of updating the target position according to the evaluation result in the evaluation step;
On a computer.

  According to the present invention, it is possible to suppress the deviation between the target distance set as rehabilitation and the exercise distance which the user actually exercises.

BRIEF DESCRIPTION OF THE DRAWINGS It is a block diagram which shows the structure of the target object recognition efficiency improvement system which concerns on 1st Embodiment of this invention. FIG. 1 is a block diagram showing a configuration of a target object recognition efficiency improvement system according to a base technology 1 ; It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on the premise technique 1. FIG. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on the premise technique 1. FIG. It is a flowchart which shows the flow of a process of the target object recognition efficiency improvement system which concerns on the premise technique 1. FIG. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on the premise technique 1. FIG. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on the premise technique 1. FIG. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on the premise technique 1. FIG. It is a figure which shows the other structure of the target object recognition efficiency improvement system which concerns on the prior art 1. FIG. It is a figure which shows the structure of the database of the target object recognition efficiency improvement system which concerns on the prior art 1. FIG. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on the premise technique 1. FIG. It is a figure which shows the example of a display screen of the target object recognition efficiency improvement system which concerns on the premise technique 1. FIG. FIG. 8 is a diagram for explaining an outline of the operation of the target object recognition efficiency improvement system according to the base technology 2 ; FIG. 8 is a diagram for explaining an outline of the operation of the target object recognition efficiency improvement system according to the base technology 2 ; It is a figure explaining an outline of operation of a target object recognition efficiency improvement system concerning a 2nd embodiment of the present invention. It is a figure explaining the arrangement position of the visual recognition auxiliary image in the target object recognition efficiency improvement system concerning a 2nd embodiment of the present invention. It is a figure explaining the other example of the visual recognition auxiliary | assistant image in the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure explaining the further another example of the visual recognition auxiliary | assistant image in the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure explaining the further another example of the visual recognition auxiliary | assistant image in the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure explaining the further another example of the visual recognition auxiliary | assistant image in the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure explaining the further another example of the visual recognition auxiliary | assistant image in the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a figure explaining the further another example of the visual recognition auxiliary | assistant image in the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a block diagram explaining the composition of the target object recognition efficiency improvement system concerning a 2nd embodiment of the present invention. It is a figure explaining an example of the patient table which the object recognition performance improvement server contained in the object recognition efficiency improvement system concerning a 2nd embodiment of the present invention has. It is a figure explaining an example of the display parameter table which the target object recognition performance improvement server contained in the target object recognition performance improvement system concerning a 2nd embodiment of the present invention has. It is a figure explaining an example of the image table which the target object recognition performance improvement server contained in the target object recognition performance improvement system which concerns on 2nd Embodiment of this invention has. It is a block diagram explaining the hardware constitutions of the object recognition efficiency improvement server contained in the object recognition efficiency improvement system concerning a 2nd embodiment of the present invention. It is a flowchart explaining the process sequence of the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a flowchart explaining the process sequence of a visual recognition auxiliary | assistant image display of the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system which concerns on 2nd Embodiment of this invention. It is a block diagram explaining the composition of the target object recognition efficiency improvement system concerning a 3rd embodiment of the present invention. It is a figure explaining an example of the sound table which the target object recognition performance improvement server contained in the target object recognition performance improvement system which concerns on 3rd Embodiment of this invention has. It is a figure explaining the hardware constitutions of the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system concerning a 3rd embodiment of the present invention. It is a flowchart explaining the process sequence of the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention. It is a flowchart explaining the process procedure of the sound output control of the target object recognition efficiency improvement server contained in the target object recognition efficiency improvement system which concerns on 3rd Embodiment of this invention.

  Hereinafter, exemplary embodiments of the present invention will be exemplarily described in detail with reference to the drawings. However, the configuration, the numerical values, the flow of processing, the functional elements, and the like described in the following embodiments are merely examples, and modifications and changes are free, and the technical scope of the present invention is described in the following description. It is not for the purpose of limiting.

First Embodiment
A target object recognition performance improvement system 100 according to a first embodiment of the present invention will be described with reference to FIG. The information processing system 100 is a system that supports the rehabilitation performed for the user 110.

  As shown in FIG. 1, the target object recognition performance improvement system 100 includes an operation detection unit 101, a display control unit 102, an evaluation unit 103, and an update unit 104.

  The motion detection unit 101 detects a first rehabilitation motion of the user 110. The display control unit 102 displays an avatar image that moves according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid image that improves the visibility of the target image. Let The evaluation unit 103 evaluates the rehabilitation ability of the user 110 by comparing the first rehabilitation operation with the target position represented by the target image. The update unit 104 updates the target position according to the evaluation result by the evaluation unit.

  According to the present embodiment, it is possible to suppress the deviation between the target distance set as rehabilitation and the exercise distance at which the user actually exercises.

[ Prerequisite technology 1 ]
Next, the rehabilitation support system 200 according to the base technique 1 will be described with reference to FIG. FIG. 2 is a diagram for explaining the configuration of the rehabilitation support system according to the present embodiment.

  As shown in FIG. 2, the rehabilitation support system 200 includes a rehabilitation support server 210, two base stations 231 and 232, a head mounted display 233, and two controllers 234 and 235. The head mounted display 233 may be a non-transmissive type, a video see-through type, or an optical see-through type.

  The rehabilitation support server 210 also includes a motion detection unit 211, a display control unit 212, an evaluation unit 213, an update unit 214, a voice input / output unit 215, a target database 216, and a background image + question / answer database 217.

  The motion detection unit 211 acquires the position of the controller 234 or 235 held by the user 220 and the position of the head mounted display 233 via the base station 231 or 232, and detects the rehabilitation motion of the user 220 based on the change in the position. .

  The display control unit 212 causes the head mount display 233 to display an avatar image that moves according to the detected rehabilitation operation and a target image that indicates the target of the rehabilitation operation. FIG. 3 is a view showing an example of avatars 311 and 312 on the screen 301 displayed on the head mounted display 233. As shown in FIG. The avatars 311 and 312 are superimposed on the background image 313 and displayed. In this example, the avatars 311 and 312 have the same shape as the controllers 234 and 235, and move in the screen 301 in accordance with the movements of the controllers 234 and 235. In addition, the background image 313 changes in accordance with the position and orientation of the head mounted display 233. As displayed in the avatars 311 and 312, buttons are prepared in the controllers 234 and 235 so that various setting operations can be performed. Here, as the background image 313, a landscape image (for example, a moving image obtained by shooting a town in New York) obtained by imaging an actual landscape is displayed. As a landscape image, an image of a road around a rehabilitation facility may be used, and it is possible to make it feel as if you are taking a walk in a foreign country, or to feel as you are taking a walk in a familiar place. By superimposing the landscape image, it is possible to realize training in a large amount of information while entertaining the patient.

  Further, for example, as shown in FIG. 4, the display control unit 212 superimposes the background image 313 on the screens 401 to 403 of the head mounted display 233, and displays the object 411. The object 411 gradually changes the display position and size so as to be lowered from the overhead direction of the user 220 downward. The user 220 moves the controllers 234 and 235 to bring the avatar image 311 on the screen closer to the object 411. When the avatar image 311 hits the object 411, the object 411 disappears.

  The evaluation unit 213 evaluates the user's rehabilitation ability by comparing the rehabilitation operation detected by the operation detection unit 211 with the target position represented by the target image displayed by the display control unit 212. Specifically, it is determined by comparison of the position in the three-dimensional virtual space whether or not the avatar image 311 moved according to the rehabilitation operation detected by the operation detection unit 211 and the object 411 as a target image overlap. . As a result, if they overlap, it is evaluated that one rehabilitation operation has been cleared, and points are added. The positions in the depth direction of the object 411 are prepared in various stages (for example, three stages), and different points (high points for distant objects, low points for near objects) are set respectively.

  The updating unit 214 updates the target task according to the accumulated points. For example, the target task may be updated using the task achievement rate (the number of goals achieved / the number of tasks) or the like.

  FIG. 5 is a flowchart showing the flow of processing in the rehabilitation support server 210. In step S501, as a calibration process, the target of the rehabilitation operation is initialized to the user. Specifically, each patient is first required to work in the actionable range as a calibration, and after setting it to an initial value, the target is initialized according to the user.

  Also, with reference to the target database 216, a target is set according to the user's attribute information (for example, whether it is an athlete or Parkinson's disease). For example, in the case of an injured sports player, an initial value that does not aggravate the injury is set, and in the case of a user who suffers from Parkinson's disease, an exercise that causes the progression of a medical condition is set as an initial value. Do. Furthermore, each patient is first required to work in the action range, and after setting it to the initial value, the target is initialized to the user.

  Next, in step S503, avatar images 311 and 312 are displayed according to the positions of the controllers 234 and 235 detected by the operation detection unit 211. Further, in step S505, the object 411 is displayed at the position and speed according to the set task.

  In step S507, the motion of the avatars 311 and 312 is compared with the motion of the object 411 to determine whether the task has been cleared. If the task has not been cleared, the process returns to step S505, and the next object is displayed without changing the difficulty level of the task.

  If the task has been cleared, the process proceeds to step S509, and the cumulative point, the task achievement probability, and the like are calculated. Further, the process proceeds to step S511 to compare the accumulated points and the task achievement probability with the threshold T, and when the accumulated points and the task achievement probability etc exceed the predetermined threshold T, the process proceeds to step S513 to update the exercise intensity of the task. . If the cumulative points, the task achievement probability, and the like do not reach the threshold T, the process returns to step S505, and the next object is displayed without changing the degree of difficulty of the task.

  For example, when the achievement level of the short distance exceeds 80% (or may be 10 times, etc.), the display frequency of the medium distance object is increased. If the achievement of the medium distance object exceeds 80% (or even 10 times or so), the display frequency of the long distance object is increased.

  The update of the task here is also changed in accordance with the user's attributes (such as an injured athlete or a patient with Parkinson's disease, etc.). As a method of updating the task, a method of switching the background image may be considered.

  After updating the task, the process proceeds to step S515, where the degree of fatigue of the user is calculated and compared with the threshold N. If the degree of fatigue exceeds a predetermined threshold, the processing is terminated as "stop condition". For example, it can be calculated as (degree of fatigue = 1−recovery of the most proximal object). Alternatively, it may be calculated as (degree of fatigue = 1 / eye movement). If you are not clearly focused (not looking for an object at all, don't shake your head, etc.), it will be meaningless to continue rehabilitation further, so you will take a break. Furthermore, the degree of fatigue may be calculated by detecting (accelerating) a decrease in speed when extending the arm.

  Also, for example, if the accumulated point exceeds a predetermined threshold, as shown in the character image 601 of FIG. 6, which of the two controllers 234 and 235 should be used to touch the object 411 with the left or right controller (here, right) To indicate. This makes it necessary to have a cognitive function that recognizes characters, increases the difficulty of movement, and requires a higher motor function. In other words, dual tasks of cognitive function and motor function are required.

  In FIG. 6, the instruction is given by characters, but the present invention is not limited to this, and the instruction may be given by an arrow, a color or a voice. Thus, in the present embodiment, the load is updated according to the evaluation of the rehabilitation operation.

(About dual task)
Healthy people are doing two or more things at the same time, such as "walk while talking" in normal daily life. Such "the ability to do two things simultaneously" declines with age. For example, "if you talk while walking, you will stop your leg" and so on. It is thought that the cause of the fall of the elderly is not only "the decrease in motor function" but also "the decrease in ability to do two things at the same time". In fact, there are many elderly people who fall after returning home even though it is judged that rehabilitation sufficiently restores their motor function. One of the factors is that rehabilitation is being performed with the environment and conditions in which it is possible to concentrate on the rehabilitation operation. That is, in the living environment, it is often the operation under the condition that factors that can not concentrate on the operation such as poor visibility, the presence of an obstacle, and the conversational awareness.

  Therefore, it is considered important to carry out rehabilitation that disperses attention, and it is desirable to train specifically by giving dual tasks. Such dual task training is an effective program not only for the fall of elderly people but also for the prevention of dementia.

  Dual task training includes training that combines two types of exercise tasks, as well as training that combines cognitive tasks and exercise tasks.

  The cognitive task + exercise task includes training such as walking while subtracting one by one from 100, and the exercise task + exercise task includes training such as walking so as not to spill the water in the cup.

  The evaluation unit 213 evaluates that the fall risk is high if the walking speed is delayed by about 20% in the dual task walking test as compared to simple walking, and notifies the display control unit 212 to repeat the dual task. .

  The person with relatively high mobility is more likely to have dual tasks. For example, if you are an elderly person who can not release the cane even if you move indoors, strengthening the balance ability (such as muscle strength and sense of balance) has higher priority than the dual task ability. As a rough judgment, it can be said that the person in need of support needs dual task ability, and the person in need of care needs balance ability other than dual task ability. Display the time series of calibration and visually show the improvement of one's movement range.

(Setting change by user attribute)
For patients who can expect normal improvement (subject to orthopedic disease such as bone fracture and complete improvement assumed), set the hardest rehabilitation operation and accelerate improvement.

  For patients with different degrees of improvement depending on the individual (patients who have different forms of paralysis depending on the lesion site in cerebral infarction etc.), the load of the task is improved to a certain extent. Stop.

  In patients with Parkinson's disease, etc., whose function is basically reduced, it is useful to constantly evaluate the current assessment of their ability to move.

(Another dual task training example)
FIG. 7 is a view showing another exemplary image for dual task training. By placing a loss on the object (bomb), the cognitive function is required. Alternatively, as shown in FIG. 8, a question image (here, multiplication as an example) may be superimposed and displayed on the background screen, and only the acquisition of the object for which the answer is displayed may be evaluated. The background screen may display one of Goo, Choi, and Pa, and may request collection of an object with a win mark.

  Furthermore, the object may simply be displayed with numbers, and only the acquisition of objects with large numbers may be evaluated. In addition, when a signal is displayed in the background image 313 and an object is picked up in the case of a red signal, the evaluation unit 213 may make the point negative.

  According to the present embodiment, since the task is updated according to the degree of achievement (such as the achievement probability) of the rehabilitation operation, it is possible to give the user a load according to the progress of the rehabilitation. In addition, displaying the background image 313 makes it possible not only to enjoy the patient but also to perform rehabilitation in a situation in which the user is conscious about the surroundings, and a safer life can be realized when returning to the real world.

  FIG. 9 is a diagram showing another dual task training example. The voice input / output unit 215 outputs the question voice regarding the background image to the headphone 901 as shown in FIG. 9, and acquires the answer to the question via the microphone 902 provided on the head mounted display 233. The evaluation unit 213 performs voice recognition processing on the response acquired as voice information, compares it with the response prepared in advance, and evaluates the user's rehabilitation ability according to the comparison result.

  FIG. 10 is a diagram showing an example of the contents of the background image / question / answer database 217. As shown in FIG. The question voice, the answer and the point are stored in association with the background moving image.

  As the user's reaction, it is expected that the dual task results in a decrease in the object recovery rate. We expect the result that the recovery achievement rate of objects does not differ even if dual task is displayed as a goal. The recovery rate of objects or the reach rate to objects is compared at single task time and dual task time, and training is repeated until it falls within a certain range.

  The above is dual task training that simultaneously requires motor function and cognitive function, but the present invention is not limited to this, and may be dual task training which requires two motor functions simultaneously.

  For example, as shown in FIG. 11, it may be required to pick up the object 411 while avoiding the flying object 1111. By detecting the position of the sensor provided on the head mounted display 233, it can be determined whether or not the object 1111 has been successfully taken. The evaluation and the update of the task may be performed based on the achievement points (for example, the achievement rate) of both of the two rehabilitation operations.

  For example, as shown in the image 1201 of FIG. 12, as the avatar image which moves according to the operation of the controller 234, 235, the cup images 1211, 1212 containing water are displayed, and these cup images 1211, 121 are moved. The object 411 may be collected. However, as shown in the image 1202, when water is spilled by tilting the cup image 1221, points can not be obtained even if the object 411 is recovered by the cup image 1222. Points are added only when the object 411 is recovered without spilling water in the cup images 1231 and 1232 as in the image 1203.

  In addition, it may be considered that the avatar image on the opposite side to the avatar image on the object recovery side is required to always touch a designated place. The controller 234 or 235 may request that the object be collected while pressing a designated button a predetermined number of times. In addition, when a sensor for acquiring the movement of the user's foot is provided, the specified movement of the foot may be requested.

Second Embodiment
Next, a target object recognition performance improvement system according to a second embodiment of the present invention will be described using FIGS. 13A to 17B. FIG. 13A is a diagram for explaining an outline of the operation of the base technology 2 of the target object recognition efficiency improvement system according to the present embodiment. FIG. 13B is a diagram for describing an outline of the operation of the base technology 2 of the target object recognition efficiency improvement system according to the present embodiment. The target object recognition performance improvement system according to the present embodiment is different from the above base technology 1 in that it displays a visual aid image for improving the target image recognition performance (for example, the visibility). The other configurations and operations are similar to those of the base technology 1, and therefore the same configurations and operations are denoted by the same reference numerals and the detailed description thereof is omitted.

In the base technology 2 , the movement distance of the avatar image 1320, that is, the movement distance 1312 of the user 220 is measured by the distance between the reference 1310 and the sensor of the avatar image 1320 (the head portion of the avatar image 1320). Then, a target distance 1311 which is a distance that the user 220 has to move an arm or the like is determined based on the distance between the reference 1310 and the reference line 1331 of the object 1330 as a target image. Then, the user 220 moves the avatar image 1320 closer to the object 1330 as a rehabilitation exercise.

  However, as shown in FIG. 13B, when the avatar image 1320 touches the vertex 1332 of the object 1330, the system determines that one of the user 220's rehabilitation operations has ended, and a new object 1330 is taken as the next goal. indicate.

  As a provider of the system, as a rehabilitation exercise, the avatar image 1320 is desired to be in contact with the object 1330 when the user 220 is fully extended. However, if the size of the object 1330 is large (the distance between the apex and the reference line 1331 is large), it is determined that the object 1330 is touched only by touching the avatar image 1320 at the end of the object 1330. Therefore, since the user 220 can not move the arm by the distance initially assumed, it is difficult to obtain the expected rehabilitation effect.

  In addition, since the user 220 can also touch the object 1330 before the arm is extended and cut, a sense of accomplishment and satisfaction due to the rehabilitation exercise can not be sufficiently obtained, and the motivation for rehabilitation may be lowered. .

  In this case, an exercise distance 1312 which is a distance by which the avatar image 1320 has actually moved deviates from a target distance 1311 which is a distance that the user 220 has to move originally. Therefore, the user 220 does not exercise the exercise distance 1312 set before the start of rehabilitation, and the effect obtained by rehabilitation is also smaller than the expected effect.

  For example, the length of one side of the object 1330 is 20.0 cm, and the diameter 1321 of the sensor unit (the head portion of the avatar image 1320) of the avatar image 1320 is 5.0 cm. In this case, when the user 220 brings the avatar 1320 into contact with the apex 1332 instead of the reference line 1331 of the object 1330, an error of about 10.0 cm occurs between the target distance 1311 and the movement distance 1312.

  Therefore, since the user 220 does not move the avatar image 1320 by the exercise distance 1312 assumed before the start of rehabilitation, the effect of the rehabilitation which the user 220 should have been able to enjoy will be reduced.

  If the size of the object 1330 is reduced so that the user 220 touches the object 1330 when the user stretches his or her arm, it becomes difficult for the user 220 to visually recognize the position of the object 1330 in the screen. If the object 1330 can not be viewed, rehabilitation is not established.

  Therefore, the sensor part (reaction part) of avatar image 1320 is made into a field smaller than the head part of avatar image 1320. This makes it possible to further reduce the deviation (error) between the target distance 1311 and the movement distance.

  FIG. 13C is a diagram for describing an outline of the operation of the target object recognition performance improvement system according to the present embodiment. Therefore, in the present embodiment, the central portion of the object 1330 is darkened to be a reaction portion so that a deviation does not occur between the assumed target distance 1311 and the movement distance 1312 by the avatar image 1320. Then, the gradation of the portion around the reaction portion of the object 1330 is lightened. That is, the size of the object 1330 shown in FIGS. 13A and 13B is reduced, and the periphery thereof is surrounded by the visual aid 1133 larger than the object 1330. That is, the object 1330 and the visual recognition auxiliary image 1333 are superimposed and displayed.

  From the viewpoint of the user 220, when the size of the object 1330 is reduced, the object 1330 becomes difficult to see (the visibility decreases), but the visual aid image is displayed around the reduced object 1330 to compensate for the decrease in visibility. Arrange 1333.

  For example, the length of one side of the object 1330 is 5.0 cm, the length of one side of the visual assistant image 1333 is 20.0 cm, and the diameter of the sensor unit 1322 of the avatar image 1320 is 2.0 cm. Then, the error (deviation) between the target distance 1311 and the movement distance 1312 decreases to around 2.0 cm.

  Thereby, the deviation (error) between the target distance 1311 and the movement distance 1312 is reduced while preventing the decrease in the visibility of the object 1330 due to the difference in gradation and the difference in size of the object 1330 and the visual auxiliary image 1333. Can. As a secondary effect, the experience level when the avatar image 1320 is brought into contact with the object 1330 is increased. That is, for the user 220, the sense when touching the object 1330 becomes clear, and the joy of achieving the goal of rehabilitation also rises.

  FIG. 13D is a view for explaining the arrangement position of the visual recognition auxiliary image in the target object recognition efficiency improvement system according to the present embodiment. In FIG. 13C, the object 1330 as the target image is displayed so as to be included in the visual aid auxiliary image 1333 and is disposed near the center of the visual aid auxiliary image 1333.

  However, as shown in FIG. 13D, the object 1330 may be arranged near the lower side of the near side of the visual aid image 1333. That is, the object 1330 may be arranged on the front side as viewed from the user 220. As described above, the object 1330 may be disposed at any position of the visual assistance image 1333 as long as the object 1330 is displayed so as to be included in the visual recognition assistance image 1333. As described above, when the size of the object 1330 is reduced and the deviation between the target distance 1311 and the movement distance 1312 is reduced, the visibility of the object 1330 is reduced. Therefore, in order to improve the visibility of the object 1330, the visibility assistance image 1333 larger than the object 1330 is displayed around the object 1330 to compensate for the decrease in the visibility of the object 1330. Note that the visual aid 1133 for improving the visibility of the object 1330 is not limited to the cube shown in this case where the magnification of the cubic object 1330 is enlarged.

  Next, another shape of the visual identification auxiliary image 1333 will be described with reference to FIGS. 13E to 13I. FIG. 13E is a view for explaining another example of the visual recognition auxiliary image in the target object recognition efficiency improvement system according to the present embodiment. FIG. 13F is a view for explaining still another example of the auxiliary visual recognition image in the target object recognition efficiency improvement system according to the present embodiment. FIG. 13G is a view for explaining still another example of the auxiliary visual recognition image in the target object recognition efficiency improvement system according to the present embodiment. FIG. 13H is a view for explaining still another example of the auxiliary visual recognition image in the target object recognition efficiency improvement system according to the present embodiment. FIG. 13I is a view for explaining still another example of the auxiliary visual recognition image in the target object recognition efficiency improvement system according to the present embodiment.

  As shown in FIG. 13E, the visual recognition auxiliary image 1340 may have, for example, an arrow shape indicating the position where the object 1330 is present. Then, the object 1330 is not included in the arrow-shaped visual aid 1340. In other words, the visual aid image 1340 is disposed outside the object 1330, instead of the object 1330 as the target image and the visual aid image 1340 being displayed in an overlapping manner. As described above, with the aid of the arrow-shaped visual aid 1340, the user 220 can easily recognize that the object 1330 is present at the tip of the tip of the arrow.

  As shown in FIG. 13F, the viewing assistance image 1350 may be shaped to draw the user's 220 attention. The shape that draws the user's 220 attention is not limited to the shape shown in FIG. 13F, and may be, for example, a star shape, a cross shape, a polygon shape, or the like. The vertical line 1351 and the horizontal line 1352 may be displayed together to indicate that the object 1330 is disposed at the center of the vertical line 1351 and the horizontal line 1352.

  As shown in FIG. 13G, the visual aid image 1360 may be an alternate long and short dash line extending from the sensor unit 1322 of the avatar image 1320 toward the object 1330. Note that the visual aid image 1360 is not limited to the one-dot and dash line, and may be, for example, a straight line, a two-dot and dash line, or a dotted line.

  Then, the user 220 can visually recognize the object 1330 and recognize the existing position of the object 1330 by moving the line of sight along the dashed dotted line with the dashed dotted line as a guideline. Furthermore, moving the avatar image 1320 along the alternate long and short dash line allows the object 1330 to touch the avatar image 1320. In addition, when the visual recognition assistance image 1333 is displayed together with the visual recognition assistance image 1370, the visibility of the object 1330 is further improved.

  As shown in FIG. 13H, the visual aid 1130 may have a plurality of arrows arranged on a straight line from the sensor unit 1322 toward the object 1330. Then, the user 220 can visually recognize the object 1330 by recognizing the position of the object 1330 by moving the line of sight along the plurality of arrows with the plurality of arrows as a guideline. Furthermore, moving the avatar image 1320 along the plurality of arrows allows the object 1330 to touch the avatar image 1320. Note that if the cube auxiliary visual image 1333 is displayed together with the visual auxiliary image 1370, the visibility of the object 1330 is further improved.

  As shown in FIG. 13I, a plurality of spherical visual aids 1380 are arranged at the top, bottom, left, and right of the object 1330. That is, in FIG. 13I, a plurality of spherical visual aids 1380 are arranged around the object 1330 such that the object 1330 is arranged at the center of the four visual aids 1380. The shape of the visual aid image 1380 is not limited to a spherical shape, and may be, for example, a triangular shape, a rectangular shape, a polygonal shape, a star shape, or the like.

  FIG. 13J is a view for explaining still another example of the auxiliary visual recognition image in the target object recognition efficiency improvement system according to the present embodiment. For example, the target object recognition performance improvement server may change the size of the visual assistance image 1333 displayed on the display unit 1402 according to the progress of the rehabilitation of the user 220. For example, the target object recognition performance improvement server displays a larger visual aid image 1333 at the initial stage of rehabilitation. Then, in a state where the rehabilitation of the user 220 has progressed, the size of the visual identification auxiliary image 1333 may be reduced according to the progress of the rehabilitation.

  In addition, the target object recognition performance improvement server may change the size of the visual assistance image 1333 in accordance with the visual acuity of the user 220, for example, in accordance with the progress of the rehabilitation of the user 220. That is, the target object recognition performance improvement server displays the larger visual assistance image 1333 if the user 220 has poor vision, and displays the smaller visual assistance image 1333 if the user 220 has relatively good vision. It is also good. Thus, the target object recognition performance improvement server may display a visual aid image of a size according to the visual acuity of the user 220.

  In addition, for example, when the user 220 is a dementia, the target object recognition performance improvement server may display a visual aid 1133 having a size that matches the progress of the dementia or the cognitive function. In addition, even if the target recognition improving server automatically changes the size of the visual recognition auxiliary image 1333, the operator such as a doctor who operates the target recognition improving system manually changes it, and the user 220 changes it. You may

  FIG. 14 is a block diagram for explaining the configuration of the target object recognition performance improvement system according to the present embodiment. The target object recognition performance improvement system 1400 has a target object recognition performance improvement server 1401 and a display unit 1402. In addition, the element contained in the target object recognition efficiency improvement system 1400 is not limited to these. The target object recognition performance improvement server 1401 includes an operation detection unit 1411, a display control unit 1412, an evaluation unit 1413, and an update unit 1414.

  The operation detection unit 1411 acquires the position of the controller held by the user 220 and the position of the head mounted display mounted by the user 220, and the movement of the user 220 based on the acquired change in position ( Detect rehabilitation action).

  The display control unit 1412 displays, on the display unit 1402, an avatar image 1320 that moves according to the detected rehabilitation operation, a target image indicating the target of the rehabilitation operation, and at least one visual aid 1133 for improving the visibility of the target image. Display on etc.

  The display control unit 1412 superimposes and displays the target image and the visual recognition auxiliary image 1333. For example, the size of the target image is made smaller than the size of the visual recognition auxiliary image 1333, and the target image is displayed so as to be included in the visual recognition auxiliary image 1333.

  The display control unit 1412 may cause the target image to be displayed, for example, in the vicinity of the center of the visual recognition auxiliary image 1333. In addition, the display control unit 1412 displays the target image not in the vicinity of the center of the visual recognition auxiliary image 1333 but in the visual recognition auxiliary image 1333 and further near the avatar image 1320, that is, the front side as viewed from the user 220 You may

  The display control unit 1412 may display the object 1330 and the visual recognition auxiliary image 1333 in a distinguishable manner. Specifically, for example, the gradation of the object 1330 is displayed darker than the gradation of the visual identification auxiliary image 1333. As a result, since the object 1330 is displayed dark, the user 220 has a difference in contrast with the lightly displayed auxiliary visual image 1333 and can reliably recognize the object 1330. In addition, how to put the gradation to the object 1330 and the visual recognition auxiliary image 1333 is not limited to the method shown here. For example, even a user 220 with weak vision may use a gradation that can reliably identify the object 1330 and the visual aid 1133.

  In addition, the display control unit 1412 displays the object 1330 and the visual assistance image 1333 in different colors in order to display the object 1330 and the visual recognition assistance image 1133 in a distinguishable manner. For example, the display control unit 1412 colors the object 1330 with a dark color and colors the visual aid image 1333 with a light color, but the combination (pattern) of colors to be colored is not limited to this. For example, even a user 220 with color blindness (color blindness) may be colored in a combination of colors that can reliably identify the object 1330 and the visual aid 1133. In addition, the display control unit 1412 may perform coloring that can correspond to various types of users 220 such as low vision, visual field narrowing, and color vision abnormalities. Note that the user 220 may select the color to be used to color the object 1330 and the visual recognition auxiliary image 1333 or may be selected by an operator such as a doctor.

  Although the gradation and color of the object 1330 and the auxiliary visual image 1333 have been described here, the gradation and color may be similarly changed for the other auxiliary visual images 1340, 1350, 1360, 1370, and 1380. .

  Furthermore, the display control unit 1412 controls the change of the display of the visual recognition auxiliary image 1333 according to at least one of the visual acuity of the user 220 and the evaluation result by the evaluation unit 1413. For example, the display control unit 1412 changes the size of the viewing assistance image 1333 according to the visual acuity of the user 220, the progress of the rehabilitation of the user 220, the progress of the dementia of the user 220, and the like.

  The evaluation unit 1413 evaluates the rehabilitation ability of the user 220 in comparison with the rehabilitation operation detected by the operation detection unit 1411 and the target position represented by the object 1330 as the target image displayed by the display control unit 1412.

  The update unit 1414 updates the target position represented by the object 1330 according to the evaluation result by the evaluation unit 1413.

  The display unit 1402 displays a target image, a visibility auxiliary image, and the like according to the control of the display control unit 1412. The display unit 1402 is a head mounted display, a display, a screen, or the like, but is not limited thereto.

  FIG. 15A is a view for explaining an example of a patient table included in the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. The patient table 1501 stores attribute information 1512, rehabilitation target 1513, current level 1514 and rehabilitation menu 15115 in association with a patient ID (Identifier) 1511. The patient ID 1511 is an identifier for identifying a patient. The attribute information 1512 is information indicating an attribute of a patient such as age and gender. The rehabilitation target 1513 is data indicating which part of the body of the patient is targeted for rehabilitation, and is data representing a part of the body such as an arm or a leg, for example.

  The current level 1514 is data indicating the patient's current level of rehabilitation. That is, it is data indicating the progress of rehabilitation of the patient. The data from the initial stage to the final stage of rehabilitation is divided into a plurality of ranks, such as A rank and B rank. In addition, how to divide the level of rehabilitation is not limited to this. The rehabilitation menu 1515 is information on a menu of rehabilitation that the patient should receive.

  Next, FIG. 15B is a diagram for explaining an example of a display parameter table included in the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. The display parameter table 1502 stores a target image ID 1521, a visual aid image ID 1522, and a display parameter 1523 in association with the rehabilitation menu 1515.

  The target image ID 1521 is an identifier for identifying an object 1330 to be displayed on the display unit 1402. The viewing assistance image ID is an identifier for identifying the viewing assistance image 1333, 1340, 1350, 1360, 1370, 1380 to be displayed on the display unit 1402. The display parameter 1523 is a parameter necessary for causing the display unit 1402 to display the object 1330 and the auxiliary visual image 1333, 1340, 1350, 1360, 1370, and 1380. The display parameter 1523 includes, for example, information such as position and magnification, but the information included in the display parameter 1523 is not limited to these.

  And FIG. 15C is a figure explaining an example of the image table which the target object recognition performance improvement server contained in the target object recognition performance improvement system concerning this embodiment has. The image table 1503 stores image data 1532, a display position 1533 and a magnification 1534 in association with the image type 1531. The items stored in the image table 1503 are not limited to these.

  The image type 1531 is information that distinguishes whether an image to be displayed is a target image or a visual aid image. The image data 1532 is image data of an object 1330 displayed on the display unit 1402, an auxiliary visual image 1333, and the like, and includes image data of various image file formats. The display position 1533 is data indicating which position in the display unit 1402 the display position should be displayed, and is, for example, data of a set of (X coordinate position, Y coordinate position, Z coordinate position). The magnification 1534 is data for determining what size the object 1330, the visual recognition auxiliary image 1333 or the like is to be displayed on the display unit 1402.

  Then, the target object recognition performance improvement server 1401 causes the display unit 1402 to display a visual aid image 1333, 1340, 1350, 1360, 1370, 1380 with reference to the tables 1501, 1502, 1503.

  FIG. 16 is a block diagram for explaining the hardware configuration of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. A central processing unit (CPU) 1610 is a processor for arithmetic control, and implements a functional component of the target object recognition performance improvement server 1401 in FIG. 14 by executing a program. A ROM (Read Only Memory) 1620 stores fixed data such as initial data and programs and other programs. Also, the network interface 1630 communicates with other devices via a network. Note that the CPU 1610 is not limited to one, and may be a plurality of CPUs or may include a GPU (Graphics Processing Unit) for image processing. Further, it is desirable that the network interface 1630 have a CPU independent of the CPU 1610 and write or read transmission / reception data in a region of a random access memory (RAM) 1640. Further, it is desirable to provide a DMAC (Direct Memory Access Controller) for transferring data between the RAM 1640 and the storage 1650 (not shown). Furthermore, it is desirable that the input / output interface 1660 have a CPU independent of the CPU 1610 and write or read out input / output data in the area of the RAM 1640. Therefore, the CPU 1610 recognizes that data has been received or transferred to the RAM 1640 and processes the data. Further, the CPU 1610 prepares the processing result in the RAM 640, and leaves the subsequent transmission or transfer to the network interface 1630, the DMAC, or the input / output interface 1660.

  The RAM 1640 is a random access memory used by the CPU 1610 as a temporary storage work area. In the RAM 1640, an area for storing data necessary for realizing the present embodiment is secured. The patient data 1641 is data on a patient who is to be rehabilitated using the target recognition system. The image data 1642 is data such as an object 1330 as a target image displayed on the display unit 1402 and a visual aid image 1333. The display position 1643 is data indicating at which position of the display unit 1402 the object 1330 or the visual recognition auxiliary image 1333 is to be displayed. The magnification 1644 is data indicating how large the image such as the object 1330 or the visual recognition auxiliary image 1333 is to be displayed on the display unit 1402. Then, these data are read from, for example, a patient table 1501, a display parameter table 1502 and an image table 1503.

  The input / output data 1645 is data input / output via the input / output interface 1660. Transmission / reception data 1646 is data transmitted / received via the network interface 1630. The RAM 1640 also has an application execution area 1647 for executing various application modules.

  The storage 1650 stores a database, various parameters, or the following data or program necessary for realizing the present embodiment. The storage 1650 stores a patient table 1501, a display parameter table 1502 and an image table 1503. The patient table 1501 is a table for managing the relationship between the patient ID 1511 and the attribute information 1512 shown in FIG. 15A. The display parameter table 1502 is a table for managing the relationship between the rehabilitation menu 1515 and the display parameter 1523 shown in FIG. 15B. The image table 1503 is a table for managing the relationship between the image type 1531 and the image data 1532 as shown in FIG. 15C.

  The storage 1650 further stores an operation detection module 1651, a display control module 1652, an evaluation module 1653 and an update module 1654.

  The motion detection module 1651 is a module that detects a rehabilitation motion of the user 220. The display control module 1652 is a module that causes the display unit 1402 to display an avatar image 1320, an object 1330 as a target image, and a visual aid image 1333 for improving the visibility of the object 1330. The evaluation module 1653 is a module for evaluating the rehabilitation ability of the user 220. The update module 1654 is a module that updates the target position represented by the target image according to the evaluation result. These modules 1651 to 1654 are read by the CPU 1610 to the application execution area 1647 of the RAM 1640 and executed. The control program 1655 is a program for controlling the entire target object recognition performance improvement server 1401.

  The input / output interface 1660 interfaces input / output data with input / output devices. A display unit 1661 and an operation unit 1662 are connected to the input / output interface 1660. Further, a storage medium 1664 may be connected to the input / output interface 1660. Furthermore, a speaker 1663 which is an audio output unit, a microphone which is an audio input unit, or a GPS (Global Positioning System) position determination unit may be connected. Note that, in the RAM 1640 and the storage 1650 shown in FIG. 16, programs and data regarding general-purpose functions and other realizable functions that the target object recognition performance improvement server 1401 has are not illustrated.

  FIG. 17A is a flowchart for describing the processing procedure of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. FIG. 17B is a flowchart for describing a processing procedure of visual aid image display of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. These flowcharts are executed by the CPU 1610 using the RAM 1640, and implement the functional components of the target object recognition performance improvement server 1401 of FIG.

  In step S1701, the target object recognition performance improvement server 1401 causes the display unit 1402 or the like to display a visual aid.

  In step S1721, the target object recognition performance improvement server 1401 acquires patient information such as an attribute of a patient to be rehabilitated and what kind of rehabilitation menu is to be received using the target object recognition performance improvement system 1400.

  In step S 1723, the target object recognition performance improvement server 1401 acquires display parameters necessary for displaying the visual recognition auxiliary image 1333 or the like to be displayed on the display unit 1402 on the display unit 1402. The display parameters to be acquired are, for example, parameters related to the position of the visual recognition auxiliary image 1333 or the like, the magnification and the like.

  In step S1725, the target object recognition performance improvement server 1401 acquires the image data of the visual recognition auxiliary image 1333. In step S1727, the target object recognition performance improvement server 1401 causes the display unit 1402 to display the visual recognition auxiliary image 1333 or the like.

  In step S1729, the target object recognition performance improvement server 1401 determines whether it is necessary to change the display of the visual recognition auxiliary image 1333 or the like. When the display change is not necessary (NO in step S1729), the target object recognition efficiency improvement server 1401 ends the processing. When the display change is necessary (YES in step S1729), the target object recognition efficiency improvement server 1401 proceeds to the next step.

  In step S1731, the target object recognition performance improvement server 1401 changes the size of the visual assistance image 1333 according to the evaluation result of the visual acuity of the user 220 and the rehabilitation ability of the user 220.

  According to the present embodiment, even if the size of the target image is reduced to reduce the deviation between the target distance and the movement distance, the target distance and the movement distance are brought close while maintaining the visibility of the target image. Can increase the effects of rehabilitation. In addition, since the user feels clear when touching the target image, the user can experience satisfaction with the goal achievement.

Third Embodiment
Next, a target object recognition performance improvement system according to a third embodiment of the present invention will be described using FIGS. 18 to 21. FIG. FIG. 18 is a block diagram for explaining the configuration of the target object recognition performance improvement system according to the present embodiment. The target object recognition performance improvement system according to the present embodiment is different in that it has a sound output unit as compared with the above-described base technology 1 and the second embodiment. The other configurations and operations are similar to those of the base technology 1 and the second embodiment, and therefore the same configurations and operations are denoted by the same reference numerals and the detailed description thereof is omitted.

  The target recognition performance improvement system 1800 includes a target recognition performance improvement server 1801 and a sound output unit 1802. The target object recognition performance improvement server 1801 has a sound output control unit 1811. The sound output control unit 1811 controls the sound output according to the positional relationship between the object 1330 as a target image and the avatar image 1320. The sound whose output is controlled by the sound output control unit 1811 is output from the sound output unit 1802.

  The sound output control unit 1811 outputs a sound based on, for example, the distance between the object 1330 and the avatar image 1320, that is, the positional relationship, when the object 1330 is lowered from the upper side to the lower side, for example.

  As the distance between the object 1330 and the avatar image 1320 decreases, that is, as the object 1330 approaches the avatar image 1320, the output sound may be a high frequency sound. Similarly, as the distance between the object 1330 and the avatar image 1320 increases, that is, as the object 1330 moves away from the avatar image 1320, the output sound may be a low frequency sound. That is, as in the Doppler effect, it represents an acoustic effect in which the frequency of the sound (wave) is observed differently according to the distance between the object 1330 (sound source) and the avatar image 1320 (user 220 (observer)) You may Note that instead of changing the frequency of the sound to be output, the volume of the sound to be output may be increased or decreased according to the distance between the object 1330 and the avatar image 1320.

  Also, the position of the object 1330 may be taught to the user 220 by outputting a sound from the sound output control unit 1811. That is, the user's 220 hearing is used to teach the position of the object 1330.

  For example, consider a case where the user 220 wears headphones when using the target object recognition efficiency improvement system 1800. When the object 1330 as the target image is on the right side of the avatar image 1320 (user 220), the target object recognition efficiency improvement server 1801 makes a sound from the headphones on the right ear side. Similarly, when the object 1330 is on the left side of the avatar image 1320 (user 220), sound is emitted from the headphones on the left ear side. Thus, the user 220 can determine whether the object 1330 is on the right side or on the left side of the user 220 from the direction of the sound. In addition, if the object 1330 is in front of the avatar image 1320 (user 220), sound is emitted from both headphones.

  Also, in the above description, the position of the object 1330 is taught using the visual and auditory sense of the user 220, but the object 220 is an object using the other five senses, taste, touch, smell and the like other than visual sense and auditory sense The position of 1330 may be taught.

  For example, the sensor may be placed on the tongue of the user 220, and the user 220 may feel a taste according to the position of the object 1330. Alternatively, a controller held by the user 220, headphones worn by the user 220, a head mounted display, or the like may be vibrated. That is, the position of the object 1330 may be taught using the sense of touch of the user 220.

  FIG. 19 is a diagram for explaining an example of a sound table of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. The sound table 1901 stores sound data 1911 in association with the image type 1531. Then, the target object recognition performance improvement server 1801 controls the sound to be output with reference to the sound table 1901.

  FIG. 20 is a diagram for describing a hardware configuration of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. A RAM 2040 is a random access memory used by the CPU 1610 as a temporary storage work area. In the RAM 2040, an area for storing data necessary for realizing the present embodiment is secured. The sound data 2041 is data relating to the sound to be output. Then, this data is read from, for example, the sound table 1901.

  The storage 2050 stores a database, various parameters, or the following data or program necessary for realizing the present embodiment. The storage 2050 stores a sound table 1901. The sound table 1901 is a table for managing the relationship between the image type 1531 and the sound data 1911 shown in FIG.

  The storage 2050 further stores a sound output control module 2051. The sound output control module 2051 is a module that controls the output of sound according to the positional relationship between the object 1330 as a target image and the avatar image 1320. The module 2051 is read by the CPU 1610 into the application execution area 1647 of the RAM 2040 and executed. In the RAM 2040 and the storage 2050 shown in FIG. 20, programs and data regarding general-purpose functions and other realizable functions possessed by the target object recognition performance improvement server 1801 are not shown.

  FIG. 21A is a flowchart for describing the processing procedure of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. FIG. 21B is a flowchart for describing the process procedure of the sound output control of the target object recognition performance improvement server included in the target object recognition performance improvement system according to the present embodiment. These flowcharts are executed by the CPU 1610 using the RAM 2040, and implement the functional components of the target object recognition performance improvement server 1801 of FIG.

  In step S 2101, the target object recognition performance improvement server 1801 controls the output of sound. In step S <b> 2121, the target recognition performance improvement target recognition performance improvement server 1801 acquires the position of the avatar image 1320. In step S2123, the target object recognition performance improvement server 1801 acquires the position of the object 1330. In step S 2125, the target object recognition performance improvement server 1801 determines the positional relationship between the avatar image 1320 and the object 1330. In step S2127, the target object recognition performance improvement server 1801 controls the output of sound according to the determined positional relationship.

  According to the present embodiment, since rehabilitation is performed using hearing in addition to the user's vision, the user can more easily view the object, and the effect obtained by the rehabilitation can be further enhanced. Also, the user can grasp the position of the object not only by sight but also by hearing. Moreover, since the sound is output, even a user with weak vision can receive the rehabilitation according to the present embodiment.

[Other embodiments]
Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above embodiments. The configurations and details of the present invention can be modified in various ways that can be understood by those skilled in the art within the scope of the present invention. Also included within the scope of the present invention are systems or devices that combine the different features included in each embodiment.

  Furthermore, the present invention may be applied to a system configured of a plurality of devices or to a single device. Furthermore, the present invention is also applicable to the case where an information processing program for realizing the functions of the embodiments is supplied to a system or apparatus directly or remotely. Therefore, in order to realize the functions of the present invention on a computer, a program installed on the computer, a medium storing the program, and a WWW (World Wide Web) server for downloading the program are also included in the scope of the present invention. . In particular, a non-transitory computer readable medium storing a program that causes a computer to execute at least the processing steps included in the above-described embodiment is included in the scope of the present invention.

The present invention relates to a rehabilitation support system, a rehabilitation support method, and a rehabilitation support program.

In order to achieve the above object, the rehabilitation support system according to the present invention is
Motion detection means for detecting a first rehabilitation motion of the user;
Avatar image moves in response to the detected first rehabilitation operation, the contour of the target image indicating the target of the first rehabilitation operation, the contour of the at least one visual recognition assistance image to improve the visibility of the target image, the Display control means for displaying and not displaying a trajectory which the user should follow in the rehabilitation operation up to the target image ;
Evaluation means for evaluating the user's rehabilitation ability by comparing the position of the avatar image with the target position represented by the target image;
Updating means for updating the target position according to the evaluation result by the evaluation means;
Equipped.

In order to achieve the above object, a rehabilitation support method according to the present invention is:
A motion detection step of detecting a first rehabilitation motion of the user;
Avatar image moves in response to the detected first rehabilitation operation, the contour of the target image indicating the target of the first rehabilitation operation, the contour of the at least one visual recognition assistance image to improve the visibility of the target image, the A display control step of displaying and not displaying a trajectory that the user should follow in the rehabilitation operation up to the target image ;
Evaluating the rehabilitation ability of the user by comparing the position of the avatar image with the target position represented by the target image;
An updating step of updating the target position according to the evaluation result in the evaluation step;
including.

In order to achieve the above object, a rehabilitation support program according to the present invention is:
A motion detection step of detecting a first rehabilitation motion of the user;
Avatar image moves in response to the detected first rehabilitation operation, the contour of the target image indicating the target of the first rehabilitation operation, the contour of the at least one visual recognition assistance image to improve the visibility of the target image, the A display control step of displaying and not displaying a trajectory that the user should follow in the rehabilitation operation up to the target image ;
Evaluating the rehabilitation ability of the user by comparing the position of the avatar image with the target position represented by the target image;
An updating step of updating the target position according to the evaluation result in the evaluation step;
On a computer.

In order to achieve the above object, the rehabilitation support system according to the present invention is
Motion detection means for detecting a first rehabilitation motion of the user;
Display and avatar image moves in response to the detected first rehabilitation operation, the target image showing the target of the first rehabilitation operation, and a large viewing auxiliary image than the target image to improve the visibility of the target image Display control means for causing
Evaluation means for evaluating the user's rehabilitation ability by comparing the position of the avatar image with the target position represented by the target image;
Updating means for updating the target position according to the evaluation result by the evaluation means;
Equipped with
The display control means superimposes and displays the visual recognition auxiliary image so as to include the target image .

In order to achieve the above object, a rehabilitation support method according to the present invention is:
A motion detection step of detecting a first rehabilitation motion of the user by the motion detection unit of the rehabilitation support system;
The display control unit of the rehabilitation support system, the avatar image moving according to the detected first rehabilitation operation, the target image indicating the target of the first rehabilitation operation, and the target image for improving the visibility of the target image a display control step of displaying a large viewing auxiliary image, a than,
An evaluation step of evaluating the rehabilitation ability of the user by comparing the position of the avatar image with the target position represented by the target image by the evaluation unit of the rehabilitation support system;
An updating step of updating the target position according to the evaluation result in the evaluation step, the updating unit of the rehabilitation support system;
Only including,
The display control step superimposes and displays the visual recognition auxiliary image so as to include the target image .

In order to achieve the above object, a rehabilitation support program according to the present invention is:
A motion detection step of detecting a first rehabilitation motion of the user;
The display control unit of the rehabilitation support system, the avatar image moving according to the detected first rehabilitation operation, the target image indicating the target of the first rehabilitation operation, and the target image for improving the visibility of the target image a display control step of displaying a large viewing auxiliary image, a than,
Evaluating the rehabilitation ability of the user by comparing the position of the avatar image with the target position represented by the target image;
An updating step of updating the target position according to the evaluation result in the evaluation step;
On your computer ,
The display control step superimposes and displays the visual recognition auxiliary image so as to include the target image .

Claims (21)

Motion detection means for detecting a first rehabilitation motion of the user;
Display control for displaying an avatar image moving according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid for improving the visibility of the target image Means,
An evaluation unit that evaluates the user's rehabilitation ability by comparing the first rehabilitation operation with the target position represented by the target image;
Updating means for updating the target position according to the evaluation result by the evaluation means;
Target recognition improvement system equipped with.   The system according to claim 1, wherein the display control unit superimposes and displays the target image and the visual recognition auxiliary image.   The system according to claim 2, wherein the display control means displays the target image near the center of the visual recognition auxiliary image.   3. The target object recognition efficiency improvement system according to claim 2, wherein the display control means displays the target image at a position other than the vicinity of the center of the visual recognition auxiliary image.   The target recognition performance improvement system according to any one of claims 1 to 4, wherein the display control means displays a visual recognition auxiliary image indicating a position where the target image is present.   The target recognition performance improvement system according to any one of claims 1 to 5, wherein the display control means displays the target image and the visual recognition auxiliary image in a distinguishable manner.   7. The target object recognition efficiency improvement system according to claim 6, wherein the display control means displays the target image darker than the visual recognition auxiliary image.   8. The target object recognition efficiency improvement system according to claim 6, wherein the display control means displays the target image and the visual recognition auxiliary image in different colors.   The target according to any one of claims 1 to 8, wherein the display control means controls a change in display of the visual aid image according to at least one of the visual acuity of the user and the evaluation result by the evaluation means. Object recognition improvement system.   10. The target object recognition efficiency improvement system according to claim 9, wherein the display control means controls a change in size of the visual recognition auxiliary image.   The target object recognition efficiency improvement system according to any one of claims 1 to 10, further comprising sound output control means for controlling an output of sound according to a positional relationship between the target image and the avatar image. The display control means superimposes and displays a background image on the avatar image, the target image, and the visual recognition auxiliary image.
The apparatus further comprises audio output means for outputting the question concerning the background image by voice.
12. The target object recognition efficiency improvement system according to any one of claims 1 to 11, wherein the evaluation means further evaluates the rehabilitation ability of the user according to an answer to the question.   The target object recognition efficiency improvement system according to claim 12, further comprising voice recognition means for obtaining an answer to the question by voice recognition.   The target object recognition performance improvement system according to claim 12 or 13, wherein the voice output means outputs the question concerning the background image by voice when the evaluation means evaluates the first rehabilitation operation more than a predetermined level. . The display control means superimposes and displays a question image on the avatar image, the target image, and the visual recognition auxiliary image.
The target recognition performance improvement system according to any one of claims 1 to 14, wherein the evaluation means further evaluates the rehabilitation ability of the user according to an answer to the question image.   The target object recognition efficiency improvement system according to claim 15, further comprising voice recognition means for obtaining an answer to the question image by voice recognition.   17. The target object recognition efficiency improvement system according to claim 15, wherein the display control means superimposes and displays the question image when the evaluation means evaluates the first rehabilitation operation at a predetermined level or more. The motion detection means
Furthermore, a second rehabilitation operation of the user is detected during the first rehabilitation operation,
The target object recognition efficiency improvement system according to any one of claims 1 to 17, wherein the evaluation means evaluates the rehabilitation ability based on both of the first rehabilitation action and the second rehabilitation action.   The evaluation means according to claim 18, wherein the evaluation means evaluates the rehabilitation ability based on both the first rehabilitation action and the second rehabilitation action when evaluating only the first rehabilitation action or more. Target recognition improvement system. A motion detection step of detecting a first rehabilitation motion of the user;
Display control for displaying an avatar image moving according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid for improving the visibility of the target image Step and
An evaluation step of evaluating the rehabilitation ability of the user by comparing the first rehabilitation operation with a target position represented by the target image;
An updating step of updating the target position according to the evaluation result in the evaluation step;
Target object recognition improvement method including. A motion detection step of detecting a first rehabilitation motion of the user;
Display control for displaying an avatar image moving according to the detected first rehabilitation operation, a target image indicating a target of the first rehabilitation operation, and at least one visual aid for improving the visibility of the target image Step and
An evaluation step of evaluating the rehabilitation ability of the user by comparing the first rehabilitation operation with a target position represented by the target image;
An updating step of updating the target position according to the evaluation result in the evaluation step;
Target recognition improvement program to make a computer execute.

Images