JP2017211884A - Motion detection system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a motion detection system that is disposed in a vehicle interior, and recognizes motions of crew members performed with respect to an operation screen for giving on-vehicle devices instructions.SOLUTION: The present motion detection system 1 is the motion detection system that detects motions of crew members to be performed to an operation screen 2 for giving an on-vehicle device 9 instructions. The motion detection system comprises: a position detection unit 4 that shoots space upward in a vertical direction of the operation screen, and detects a position of a body portion 8 of a crew member in a three-dimensional coordinate with the operation screen set as a reference; a motion detection unit 5 that creates motion information including a position of a prescribed portion of the crew member, shape thereof and movement direction thereof from information on the position obtained by the position detection unit; and a judgement unit 6 that judges an instruction of the crew member on the basis of the motion information. The judgement unit is configured to detect a motion in which the prescribed portion of the crew member stays still for a prescribed time as a start motion; and after the start motion is detected, determine the instruction of the crew member on the basis of the motion of the portion.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a motion detection system. More specifically, the present invention relates to a motion detection system that recognizes the motion of an occupant that is disposed in an interior of a vehicle and is operated on an operation screen for giving an instruction to an in-vehicle device.

  Various devices such as an air conditioner and a video / audio device are provided for passengers in a vehicle room of an automobile or the like. In addition, an input device such as an operation panel may be provided so that the occupant can operate these in-vehicle devices with one operation unit. For example, an operation panel is provided on the back of the front seat of the vehicle, etc., and an occupant in the rear seat touches the operation panel to adjust the temperature of the air conditioner, raise / store / tilt the display, and select AV content. And channel switching and volume adjustment. As such an operation panel, one provided with an operation switch or the like, one provided with a touch panel, or the like is used. However, in such an operation panel, it is necessary to directly touch the operation panel surface to give any instruction to the in-vehicle device, which is inconvenient for a seated user to operate in a comfortable posture. .

  In order to enable various on-vehicle devices to be operated in a non-contact manner, a non-contact information input device capable of inputting information indicated by the shape of a user's hand or the like by image processing is known. For example, Patent Document 1 discloses a non-contact type in which the shape and distance of a user's hand is detected by an imaging unit, an operation mode is selected from the shape of the hand, and parameter values are adjusted according to the distance to the hand. An information input device is disclosed.

Japanese Patent Laid-Open No. 2005-50177

It would be convenient if the vehicle occupant could operate the air conditioner, the AV device, etc. without touching the operation panel while keeping the comfortable sitting posture. For example, according to the non-contact type information input device described in Patent Document 1, by processing an image photographed by a camera, the shape and distance of the hand is detected, and various on-vehicle devices are operated. Can do. Recently, a motion sensor that uses an infrared LED and a camera and can recognize a palm or a finger from a photographed image to detect a user's movement is also used. In such a motion sensor, the object is recognized by image processing and the distortion of the shape is measured, or the time until the radiated infrared ray is reflected by the object and received is measured. The distance information is obtained. In addition, there are some that obtain distance information of an object from an image taken by a stereo camera. By using such a motion sensor, it is possible to detect an occupant's instruction operation performed in a non-contact manner with respect to the operation panel of the in-vehicle device from three-dimensional position information including the distance of the user's hand or the like.
However, the space in the automobile is narrow, and the occupant normally performs an operation that does not intend to give instructions to the in-vehicle device, such as changing the sitting posture, moving the body, handling food and drinks and baggage. In addition, vehicle vibrations and vibrations are also applied to the occupant's body. For this reason, there is a problem that it is difficult to recognize the intentional movement of the occupant for giving instructions to various in-vehicle devices separately from the unintended movement.

  The present invention has been made in view of the above situation, and provides a motion detection system that recognizes the movement of an occupant that is disposed in a vehicle interior and that is made on an operation screen for giving instructions to an in-vehicle device. With the goal.

In order to solve the above problem, a motion detection system according to a first aspect of the present invention is a motion detection system that detects a movement of an occupant that is disposed in an interior of a vehicle and that is made on an operation screen for giving an instruction to an in-vehicle device. A position detection unit that captures a space above the operation screen in the vertical direction and detects a position of a body part of an occupant in three-dimensional coordinates with respect to the operation screen; and the position detection unit A motion detection unit that generates motion information including the position, shape, and movement direction of a predetermined part of the occupant from the position information; and a determination unit that determines an occupant instruction based on the motion information, the determination unit comprising: The gist of the present invention is to detect a movement of the predetermined part of the occupant that is stationary for a predetermined time as a start operation, and to determine an instruction of the occupant based on the movement of the part after the start movement is detected.
The second invention is the first invention, wherein the predetermined part of the occupant includes fingers and palms, and the motion detection unit generates the number of photographed fingers, the moving direction and moving amount of the fingertips as movement information, The gist of the moving direction of the fingertip includes left and right, up and down, or a circular direction on a plane substantially parallel to the operation screen, and a vertical direction of the operation screen.
According to a third aspect of the present invention, in the first aspect or the second aspect, the determination unit is configured to perform the operation when the movement of the predetermined portion of the occupant is performed in a predetermined range in a direction parallel to and perpendicular to the operation screen. The gist is to determine the direction of the passenger.
The gist of a fourth invention is that, in any one of the first to third inventions, the determination unit detects the start operation when the occupant's finger or palm is stationary for a predetermined time.
According to a fifth aspect of the present invention, in any one of the first to fourth aspects, the determination unit detects the movement of the occupant's finger in the circular direction when the finger moves approximately one turn. The gist is to detect it as an action.

  According to the motion detection system of the present invention, it is a motion detection system that detects the movement of an occupant made with respect to an operation screen for giving an instruction to an in-vehicle device, and images a space above the operation screen in the vertical direction. A position detection unit that detects the position of the body part of the occupant in three-dimensional coordinates with reference to the operation screen; and the position, shape, and movement of the predetermined part of the occupant from the position information obtained by the position detection unit A motion detection unit that generates motion information including a direction and a determination unit that determines an occupant's instruction based on the motion information, so that the occupant is in an easy sitting posture without touching the operation panel, An AV device or the like can be operated. In addition, the determination unit detects an operation in which the predetermined part of the occupant is stationary for a predetermined time as a start operation, and determines the occupant's instruction based on the movement of the part after the start operation is detected. If a certain start operation is not recognized, the movement is not recognized as an instruction operation for the in-vehicle device, and the recognition rate of the occupant's movement intended for the instruction operation can be increased. Thereby, it is possible to prevent an erroneous operation due to an operation not intended by the passenger.

The predetermined part of the occupant includes a finger and a palm, and the motion detection unit generates the number of photographed fingers, the moving direction and moving amount of the fingertip as movement information, and the moving direction of the fingertip is displayed on the operation screen. In the case of including the right and left, up and down or circular direction on the substantially parallel surface, and the vertical direction of the operation screen, the operation can be distinguished by the number of standing fingers, It is possible to detect a movement in the left / right / up / down direction (swipe operation), a movement to draw a circle (circle operation), a movement to tap on the operation screen (tap operation), and the like. Thereby, the display of the operation screen can be changed corresponding to each operation, or the instruction information can be sent to the in-vehicle device.
The determination unit performs an operation of instructing an unintended occupant movement by determining the occupant's instruction when movement of the predetermined part of the occupant is performed in a predetermined range in a direction parallel to and perpendicular to the operation screen. Can be prevented, and the recognition rate of motion can be increased.
The determination unit clearly determines the intention of the occupant to operate when the occupant's finger or palm is stationary for a predetermined period of time, and correctly determines the operation based on the subsequent movement of the finger or palm. Can be recognized.
When the determination unit detects the movement of the occupant's finger in the circular direction, if the movement is detected as the start operation when the finger moves approximately one turn, the intention of the occupant to operate by the circle operation of the first rotation Since the operation is recognized based on the subsequent circle operation, it is possible to reliably prevent erroneous determination of the circle operation.

The present invention will be further described in the following detailed description with reference to the drawings referred to, with reference to non-limiting examples of exemplary embodiments according to the present invention. Similar parts are shown throughout the several figures.
It is a block diagram which shows the structure of a motion detection system. It is a schematic diagram for demonstrating the predetermined range which detects a predetermined part. It is a flowchart for demonstrating the outline of operation | movement of a motion detection system. It is a schematic diagram for demonstrating (1) start operation | movement and (2) subsequent operation | movement in a swipe operation. It is a schematic diagram for demonstrating fan operation. It is a schematic diagram for demonstrating (1) start operation | movement and (2) subsequent operation | movement in a circle operation. It is a schematic diagram which shows the example of a display of an operation screen. It is a schematic diagram which shows the example of a display of an operation screen.

  The items shown here are for illustrative purposes and exemplary embodiments of the present invention, and are the most effective and easy-to-understand explanations of the principles and conceptual features of the present invention. It is stated for the purpose of providing what seems to be. In this respect, it is not intended to illustrate the structural details of the present invention beyond what is necessary for a fundamental understanding of the present invention. It will be clear to those skilled in the art how it is actually implemented.

The motion detection system (1) according to the present embodiment is arranged in a passenger compartment of a vehicle such as an automobile, and is a user (occupant) made on an operation screen (2) for giving an instruction to the in-vehicle device (9). ) Motion. The installation location of the target operation screen (2) and the occupant do not matter. For example, in a passenger car, an operation screen (2) is provided on the back surface of the front seat and the like, which is suitable for enabling operation by a passenger sitting on the rear seat (see FIG. 2).
In order to detect the movement of the occupant's operation, the motion detection system (1) captures the space above the operation screen (2) in the vertical direction by the imaging means (3) such as a camera, and uses the operation screen (2) as a reference. A position detection unit (4) that detects the position of the body part (8) of the occupant in the three-dimensional coordinates, and the position, shape, and position of the predetermined part of the occupant from the position information obtained by the position detection unit (4) A motion detection unit (5) that generates motion information including a moving direction, and a determination unit (6) that determines an occupant instruction based on the motion information (see FIG. 1).

  The operation screen (2) is a screen of the input device (21) for operating one or more in-vehicle devices (9). The operation screen (2) includes an in-vehicle device (9) to be operated. ) Type, operating state, operation items, and the like are displayed (see FIGS. 7 and 8). The display mode and contents are not particularly limited, and characters, figures, images, and the like can be arbitrarily used. A switch or the like for performing a fixed operation may be provided in the vicinity of the operation screen (2). Further, a touch sensor may be provided on the operation screen (2) in order to reliably detect a touch operation on the operation screen (2).

  The imaging means (3) is arranged so as to photograph the space (7) above the operation screen (2) in the vertical direction. Regardless of the type of the imaging means (3), for example, one or two or more infrared cameras can be used. Moreover, 1 or 2 or more light emitting elements, such as LED which radiate | emits infrared light toward the user's (occupant's) hand etc. who operate, etc. can be provided. The position at which the imaging means (3) is provided is not particularly limited, but it is preferably arranged around the operation screen (2) in order to photograph a passenger's hand or the like facing the operation screen (2). For example, a camera and a light emitting element can be arranged near the outer periphery of the operation screen (2).

The space (7) is a space between the operation screen (2) and the occupant's body, and includes a range in which the occupant moves his / her hand for operation with respect to the operation screen (2). When the imaging means (3) is provided around the operation screen (2) so as to photograph the occupant's body, the space can be accommodated within the field of view.
The position detection unit (4) is configured to recognize a body part such as a passenger's hand by processing an image taken by the imaging means (3). The position (coordinates) of the body part of the occupant in the three-dimensional coordinate system is detected using the operation screen (2) as a reference. The position of the body part to be detected here is not limited to one, and it can be configured to detect the positions of a plurality of places. For example, the position of each fingertip, the boundary position of the palm, the position of the wrist, and the like can be mentioned. The position information is represented by three-dimensional coordinates. As long as the position in the three-dimensional space can be expressed, the type of the coordinate system is not limited, and for example, an orthogonal coordinate system can be used. In the following, the axes perpendicular to the plane parallel to the operation screen (2) are defined as the X axis and the Y axis, and the direction perpendicular to the operation screen (2) is defined as the Z axis. Regardless of the method for detecting the distance in the Z-axis direction between the operation screen (2) and the body part, for example, the distance can be obtained from images taken by two stereo cameras. The position detection unit (4) can be configured to send the detected position information to the motion detection unit (5) as appropriate (for example, at a constant cycle).

  The motion detection unit (5) is configured to generate motion information including the position, shape, and movement direction of a predetermined body part (8) of the occupant from the position information obtained by the position detection unit (4). The Here, the predetermined part is a part of the body that the occupant moves to perform an instruction operation, and may be an arbitrary part such as a finger, palm, wrist, arm, or head. Of these, one or both of a finger and a palm that can be easily moved while an occupant is seated can be cited as a good example. The position of the predetermined part is the position of the occupant's fingertip, palm, wrist, or the like, and the shape can be the number of photographed fingers (stretched fingers), the inclination angle thereof, or the like. Further, the movement direction is a change direction (three-dimensional angle, vector, etc.) from a position a predetermined time before the current position, and the motion detection unit (5) displays the operation screen (2) as the movement direction of the fingertip. Can be included in the plane (XY plane) substantially parallel to the left and right, up and down, or circular direction, and the vertical (Z) direction of the operation screen (2). In addition, the movement amount and speed of the predetermined part can be obtained as the movement information.

  The determination unit (6) is configured to determine an occupant instruction based on the motion information obtained by the motion detection unit (5). Then, the determination unit (6) detects, as a start operation, an operation in which the predetermined part of the occupant is stationary for a predetermined time, and determines an occupant instruction based on the movement of the part after the start operation is detected. Composed. The movement representing the instruction operation can be determined in advance. For example, when the fingertip is moved a certain distance or more from the position of the start operation, the left / right (Y) direction or the up / down direction on a plane substantially parallel to the operation screen (2) It is configured to detect movement in the (X) direction (swipe operation), movement to draw a circle (circle operation), movement that taps in the vertical (Z) direction toward the operation screen (2) (tap operation), and the like. be able to. Further, it can be configured to detect a movement (fan operation) in which the palm reciprocates in the direction perpendicular (Z) to the operation screen (2) at a certain distance from the position of the start operation. Without being limited thereto, the determination unit (6) may be configured to determine an instruction operation based on the combination of movements as described above or a deformed movement (for example, a twisting movement).

Then, when an operation as described above is detected, the determination unit (6) is configured to perform processing based on the detected operation in association with the display content of the operation screen (2) at that time. For example, when a plurality of icons (a, b) are displayed in the left-right direction on the operation screen (2) and a leftward swipe operation is detected, the left side of the icon (b) selected at that time The icon (a) can be moved (see FIG. 7). Further, for example, when the temperature setting of the air conditioner is displayed on the operation screen (2), when it is determined that the circle operation is performed clockwise (left) with the occupant's finger, the determination unit 6 increases the set temperature ( The air conditioner can be controlled to be lowered.
Thus, in order to perform processing based on the operation in association with the display of the operation screen (2), the determination unit (6) is configured to be able to acquire and change the display content of the operation screen (2). The You may comprise so that the display of the operation screen (2) may be controlled by the judgment part (6).

  The determination unit (6) performs the instruction operation of the occupant only when the movement of the occupant's fingers, palms, and the like is performed in a predetermined range (detection space 7) in the direction parallel to and perpendicular to the operation screen (2). Judgment can be made. The position / size of the detection space (7) depends on the size of the operation screen (2), the distance between the operation screen (2) and the occupant's body, image processing means (3), and image processing by the position detection unit (4). What is necessary is just to set suitably according to resolution, speed, etc. Further, the detection space (7) can be set so as not to react to an unintended movement of the occupant, such as a hand placed near the camera. As a result, it is possible to prevent an unintended occupant's movement from being erroneously determined as an instruction operation and to increase the movement recognition rate.

  The determination unit (6) detects an operation in which a predetermined part (8) such as an occupant's finger or palm is stationary for a predetermined time as a “starting operation”, and after detecting the starting operation, the occupant is based on the movement of the part. The instruction is determined. The predetermined time may be a time that can be clearly determined that the occupant is consciously stopping the movement (for example, about 100 milliseconds to 3 seconds). For example, it can be configured to determine that it is stationary when the amount of movement of a predetermined part (8) such as a finger or palm does not exceed a certain range for a predetermined time or longer. Then, when a swipe operation, a tap operation, a fan operation, or the like is detected following the start operation, the operation can be determined to be an operation intended by the occupant. That is, the recognition of the operation is started with the movement (starting operation) of the occupant's fingers, palms, and the like stopped by a predetermined shape such as pointing in the detection space (7).

Further, when the movement of the occupant's fingers in the circular direction is detected, the determination unit (6) can be configured to detect the start operation when the fingers move approximately once. Then, when a circle operation for the second rotation is detected following the start operation, it can be determined that the circle operation is performed intentionally by the occupant.
By determining the start operation as described above, it is possible to clearly determine the intention of the occupant to operate, and to correctly recognize the operation based on the subsequent movement of fingers and palm.

  The determination unit (6) can be configured to control various in-vehicle devices based on the determined operation. The type and number of in-vehicle devices are not particularly limited, and examples include indoor lighting devices, air conditioners, heaters, blower devices, television devices, audio devices, navigation devices, electric windows, electric seats, and the like. The contents to be instructed to these in-vehicle devices can be configured to be selected variously by the in-vehicle devices. For example, on / off of an indoor lighting device, on / off of an air conditioner, heater, blower, etc., setting of temperature / air volume, volume of AV device / channel / music selection, display contents of navigation device, and the like.

The position detection unit 4, the motion detection unit 5, and the determination unit 6 may be realized by any of hardware and software. For example, it can be implemented as software executed on an electronic control unit (ECU). A means for recognizing the occupant's body part 8 by processing an image acquired by the imaging means 3 and detecting its position and movement may be provided as an image processing apparatus connected to the ECU.
The motion detection method performed by the ECU or the like is a motion detection method for detecting the movement of an occupant made with respect to the operation screen 2, and images the space above the operation screen 2 in the vertical direction. A position detection step for detecting the position of the body part of the occupant in the three-dimensional coordinates and generation of motion information including the position, shape and moving direction of the predetermined part 8 of the occupant from the position information obtained by the position detection step. And a determination step of determining an occupant instruction based on the movement information, wherein the determination step detects an operation in which the predetermined portion 8 of the occupant is stationary for a predetermined time as a start operation, and the start operation After the vehicle is detected, the occupant's instruction can be determined based on the movement of the part.
The predetermined part 8 of the occupant includes a finger and a palm, and the motion detection unit step generates the number of photographed fingers, the moving direction and moving amount of the fingertip as movement information, and the moving direction of the fingertip It can include the left, right, up, down, or circular direction on the XY plane substantially parallel to the screen 2 and the vertical Z direction of the operation screen 2.
Further, the determination step can determine the occupant's instruction when the movement of the occupant's predetermined part 8 is performed in a predetermined range in a direction parallel to and perpendicular to the operation screen 2.
Further, the determination step may be detected as the start operation when the occupant's finger or palm is stationary for a predetermined time.
Further, in the determination step, when the movement of the occupant's finger in the circular direction is detected, the movement can be detected as the start operation when the finger moves approximately one rotation.

(Specific configuration and operation of motion detection system)
A more specific configuration and operation of the motion detection system 1 shown in FIG. 1 will be described. The motion detection system 1 is a system that detects the motion of an occupant made on an operation screen 2 for giving an instruction to an in-vehicle device / equipment provided in a vehicle interior. In this example, as shown in FIG. 2, the input device 21 is disposed on the back surface portion of the front seat of the passenger car in which seats are arranged at the front and rear, and the input device 21 is visible so that the passenger in the rear seat can visually recognize. An operation screen 2 is provided on the top. In addition, in order to acquire an image of the body part 8 such as a hand of a rear-seat occupant moved toward the operation screen 2, the input device 21 includes an LED that irradiates infrared light toward the part and the part. Two infrared cameras 3 capable of photographing are provided.

The motion detection system 1 includes a position detection unit 4, a motion detection unit 5, and a determination unit 6. The position detection unit 4 processes an image acquired by the infrared camera 3 in a predetermined range of space (detection space 7) in at least the XY direction parallel to the operation screen 2 and the vertical Z direction (detection space 7). The body part 8 is recognized, and the position on the three-dimensional coordinate is calculated and sent to the motion detector 5. The motion detection unit 5 and the determination unit 6 can detect only the movement of the occupant's body part 8 performed in the detection space 7 and determine the occupant's operation. That is, when a movement deviating from the detection space 7 is detected, it can be determined that the operation is not determined. Further, the motion detection unit 5 and the determination unit 6 define a threshold value, an allowable range (upper and lower limit values) and the like for the amount and direction (angle, vector) of the motion, and the position where the body part 8 is detected in the detection space 7. Can be determined as operations such as a swipe operation and a fan operation when the amount of movement is equal to or greater than a threshold value and within an allowable range.
When determining that the predetermined operation has been performed, the determination unit 6 can change the display of the operation screen 2 and control the target in-vehicle device based on the operation.

FIG. 3 shows an outline of the operation of the motion detection system 1. In this example, the motion detection unit 5 monitors the position of the occupant's body part (finger) detected by the position detection unit, and the shape of the finger (the number of fingers stretched, etc.), the movement direction, and the movement amount Are periodically generated as motion information. Then, the determination unit 6 samples, for example, motion information at a constant period (100 ms), has a shape in which one index finger is stretched, and the position of the fingertip continues for a certain time (300 ms) or more in three-dimensional coordinates. If it is within a certain allowable range (within ± 5 mm for each axis of XYZ), it is determined that the start operation has been performed (step S10).
When determining that the start operation has been performed, the determination unit 6 continues to acquire motion information (step S20) and monitors whether the operation is a predetermined operation (step S22).

For example, with one finger standing, it is stopped for a certain period of time (FIG. 4 (1)) and a starting operation is performed, and within a certain period of time, a certain distance or more is moved in the right (or right, up, down) direction from that position. If it is determined (FIG. 4 (2)), it is determined that the “swipe right (or right, up, down)” operation has been performed. Further, when the distance is moved a certain distance or more in the reverse direction, it can be determined that the “tap” operation has been performed. The “tap” operation may be an operation of bending a finger and then returning it to the original after a start operation of extending and resting one finger.
In addition, for example, when a finger is stopped for a certain period of time with three or more fingers standing up and started for a certain period of time, and is moved a certain distance in the normal vector direction of the palm within a certain period of time (FIG. 5) It is determined that the “fan” operation is performed in the moving direction.
Also, for example, when one finger is raised and the fingertip moves so as to rotate on a plane substantially parallel to the operation screen 2, the rotation angle (progression degree) is sampled and rotated one time (FIG. 6 ( 1) It can be determined that the start operation has been performed. Then, when a movement of one more rotation in the same rotation direction is detected from that position within a certain time (FIG. 6 (2)), it is determined that a “circle” operation has been performed in that rotation direction. In some cases, it is difficult to distinguish between a swipe operation and a circle operation. For this reason, for example, the movement of the finger can be sampled for a certain period of time, and when the total of the three-dimensional angles does not exceed a predetermined value, it can be determined that the operation is a swipe operation.
The reference for determining each operation as described above (three-dimensional movement distance / angle threshold, allowable range, etc.) may be set appropriately for each operation. Further, the type of operation and the determination method of the movement are not limited to the above, and may be a modified movement, or two or more movements may be combined into one operation.

In step S22 shown in FIG. 3, even if it is determined that the operation is a predetermined operation such as a swipe operation, a tap operation, a fan operation, or a circle operation, the determination unit 6 determines whether the operation has been properly completed. A malfunction can be prevented by further determining whether or not (step S30). For example, the determination conditions are appropriately set such that if the fingertip stops for a certain period of time after the swipe operation, it is determined that the proper swipe operation is performed, and even if multiple fan operations are performed, it is determined that the fan operation is performed once. That's fine.
And judgment part 6 performs processing based on judged operation, when predetermined operation is completed appropriately (Step S40).

FIG. 7 shows an example in which a menu is displayed on the operation screen 2. Here, when it is determined that the right swipe operation is performed with the occupant's finger when the icon a is currently selected, the determination unit 6 displays the operation screen in a state where the right icon b (a graphic indicating an air conditioner) is selected. The display of 2 can be changed.
Next, when it is determined that the tap operation has been performed with the occupant's fingers, the determination unit 6 can switch the display to a screen for operating the air conditioner as illustrated in FIG. This figure shows a state in which the temperature setting of the air conditioner is selected. In this state, when it is determined that the right (left) circle operation has been performed with the occupant's fingers, the determination unit 6 outputs a control signal for increasing (decreasing) the set temperature of the air conditioner to the air conditioner and also displays the operation screen 2 A process for changing the displayed temperature can be executed.
In addition, the motion detection system 1 arbitrarily changes each operation performed by the occupant, changes the display on the operation screen 2, switches the target in-vehicle device, selects the setting item, and performs an operation instruction for each item. Can be.

  The present invention is not limited to the embodiments described in detail above, and various modifications or changes can be made within the scope of the claims of the present invention. In this example, a passenger car has been described. However, the present invention is not limited to a passenger car and can be applied not only to a vehicle space.

  DESCRIPTION OF SYMBOLS 1; Motion detection system, 2; Operation screen, 21; Input device, 3; Imaging means, 4; Position detection part, 5: Motion detection part, 6: Judgment part, 7: Detection space, 8; In-vehicle device.

Claims (5)

A motion detection system that detects a movement of an occupant that is disposed in an interior of a vehicle and that is performed on an operation screen for giving an instruction to an in-vehicle device.
A position detection unit that captures a space above the operation screen in the vertical direction and detects the position of the body part of the occupant in three-dimensional coordinates with respect to the operation screen;
A motion detection unit that generates motion information including the position, shape, and movement direction of a predetermined part of the occupant from the position information obtained by the position detection unit;
A determination unit that determines an instruction of an occupant based on the movement information;
With
The determination unit detects an operation in which the predetermined part of the occupant is stationary for a predetermined time as a start operation, and determines an occupant instruction based on the movement of the part after the start operation is detected. Detection system. The predetermined part of the occupant includes fingers and palms,
The motion detection unit generates the number of captured fingers, the moving direction and moving amount of the fingertip as motion information,
The movement detection system according to claim 1, wherein the moving direction of the fingertip includes a left-right, up-down, or circular direction on a plane substantially parallel to the operation screen, and a vertical direction of the operation screen.   3. The motion detection according to claim 1, wherein the determination unit determines an instruction of the occupant when movement of the predetermined portion of the occupant is performed in a predetermined range in a direction parallel to and perpendicular to the operation screen. 4. system.   The motion detection system according to any one of claims 1 to 3, wherein the determination unit detects the start motion when a passenger's finger or palm is stationary for a predetermined time.   5. The motion detection system according to claim 1, wherein when the movement of the occupant's finger in the circular direction is detected, the determination unit detects the start operation when the finger moves approximately one rotation. 6. .

Images