JP2018151834A - Lost child detection apparatus and lost child detection method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To prevent erroneous determination of a lost child when a watcher is watching from a distance a watching target person.SOLUTION: The lost child detection apparatus 3 acquires a captured image including a person from an imaging apparatus 2, detects from the captured image a watching target person who is a target whose action is watched and a watcher who is a person to watch the watching target person and detects a distance between the watcher and the watching target person, calculates a view range of the watcher based on an image of the face of a person included in the captured image, and, when it is determined that the distance is equal to or greater than a predetermined threshold and the watching target person is out of the view range of the watcher, the watching target person is determined to be lost.SELECTED DRAWING: Figure 3

Description

  The present disclosure relates to a lost child detection device and a lost child detection method for detecting a lost child based on a captured image captured by an imaging device.

  In recent years, for example, in a commercial facility such as a shopping mall or a theme park, a lost child is detected based on a captured image obtained by capturing a person with a surveillance camera. As such a technique, while detecting a 1st user (watcher) and a 2nd user (watching object) from a captured image, the present position of a 1st user and a 2nd user is acquired, and 1st use A technique is known in which a second user is determined to be lost after a certain period of time has elapsed between the current position of the user and the current position of the second user (see Patent Document 1).

JP 2007-60528 A

  However, in the prior art disclosed in Patent Document 1, a lost child is determined based on a distance between a watching target person (for example, a child) who watches over the action and a watcher (for example, a parent) watching over the action of the watching target person. For this reason, there is a problem in that when the watcher watches the watch target person from a distance, the watch target person is erroneously determined to be lost.

  The present disclosure has been devised in view of the problems of the prior art, and is a stray child that can prevent misjudgment of a stray child when a watcher watches the person to be watched from a distance. A main object is to provide a detection device and a lost child detection method.

  The lost child detection device of the present disclosure includes a processor and a communication unit that performs communication with the imaging device, and the processor acquires a captured image including a person from the imaging device and observes an action from the captured image. And a watcher who is a person watching the behavior of the watch target person, and detecting a distance between the watch person and the watch target person, and detecting a person included in the captured image Based on the face image, the view range of the watcher is calculated, the distance is determined to be greater than or equal to a predetermined threshold, and the watch target person is determined to be out of the view range of the watcher. In this case, it is determined that the watching target person is lost.

  According to the present disclosure, it is possible to prevent an erroneous determination of a lost child when the watcher watches the watch target person from a distance.

The block diagram which shows the outline | summary of the lost child detection system containing the lost child detection apparatus which concerns on this indication Block diagram showing a schematic configuration of the lost child detection device Flow chart showing the flow of lost child detection processing The figure which shows an example of a parent-child detection process The figure which shows an example of the determination processing of the distance between parents and children The figure which shows an example of the determination process of the direction of a parent's face The figure which shows another example of the determination process of the direction of a parent's face

  A first invention made to solve the above-described problem includes a processor and a communication unit that performs communication with the imaging device, wherein the processor acquires a captured image including a person from the imaging device, and the imaging From the image, while detecting the watching target person who is watching over the action and the watching person who is watching over the behavior of the watching target person, detecting the distance between the watching person and the watching target person, Based on the face image of the person included in the captured image, the view range of the watcher is calculated, the distance is determined to be equal to or greater than a predetermined threshold, and the watch target person is determined from the view range of the watcher. When it is determined that the person is watching, the lost child detection apparatus determines that the person to be watched is a lost child.

  According to the lost child detection device according to the first aspect of the invention, when the watching target person is away from the watcher, it is determined whether or not the watching target person is lost based on the view range of the watcher. This makes it possible to prevent misjudgment of a lost child when watching the subject from a distance.

  The second invention is characterized in that, in the first invention, the field-of-view range is calculated based on a face direction of the watcher.

  According to the stray child detection device according to the second aspect of the present invention, even if the eyes of the watcher cannot be recognized due to lack of resolution of the captured image, the watcher's face direction deviates from the watcher's view range. It is possible to easily determine whether or not it is.

  In a third aspect based on the second aspect, the field-of-view range is a range of a predetermined angle set based on an orientation of the face of the watcher.

  According to the lost child detection apparatus according to the third aspect of the present invention, the view range can be easily calculated.

  In a fourth aspect based on any one of the first aspect to the third aspect, the processor detects an obstacle from the captured image, and the distance is determined to be equal to or greater than a predetermined threshold. And in the case where the obstacle exists between the watching person and the watching target person, it is determined that the watching target person is lost even if the watching target person exists within the field of view. It is characterized by that.

  According to the lost child detection apparatus according to the fourth aspect of the invention, it is possible to appropriately determine whether or not the watching target person is a lost child even when the watching target person is in a place where it is difficult for the watching person to visually recognize directly.

  In a fifth aspect based on any one of the first to fourth aspects, the processor detects a person different from the watcher from the captured image, and the distance is a predetermined threshold. In the case where it is determined as described above and the watcher and a person different from the watcher face each other, even if the watch target person is within the field of view, the watch target person is lost. It is characterized by determining.

  According to the lost child detection apparatus according to the fifth aspect of the invention, for example, even if the watcher's attention is deviated from the watch target person due to circumstances such as the watch person having a conversation with another person, the watch target object It is possible to appropriately determine whether the person is lost.

  According to a sixth invention, in any one of the first to fifth inventions, the processor estimates a year group of persons included in the captured image, and based on the estimated year group, It is characterized in that a person with a high age is determined to be a watcher and a person with a low age is watched and determined to be a target person.

  According to the lost child detecting apparatus according to the sixth aspect of the invention, it is possible to detect in a situation where there is a difference in the age group of the watching person and the watching target person, such as with parents and children.

  According to a seventh aspect, in the sixth aspect, the processor extracts a contour of the person from the captured image, and estimates the age group based on the extracted contour.

  According to the lost child detection apparatus according to the seventh aspect of the present invention, it is possible to easily detect the age group from the captured image.

  In addition, an eighth invention further includes an alarm notification unit that issues an alarm notifying that a lost child has been detected in any one of the first to seventh inventions, wherein the processor includes the processor When it is determined that the person being watched over is a lost child, the alarm notification unit issues the alarm.

  According to the lost child detection apparatus according to the eighth aspect of the present invention, when it is determined that the person being watched over is a lost child, it is possible to issue an alarm notifying that a lost child has been detected.

  According to a ninth aspect of the present invention, there is provided a step of acquiring a captured image of a person from the imaging device, a watching target person who is a target of watching the action from the picked-up image, and a watcher who is a person watching the action of the watching target person. Detecting a distance between the watcher and the watch target person, calculating a view range of the watcher based on a face image of a person included in the captured image, Determining that the person being watched is lost when it is determined that the distance is greater than or equal to a predetermined threshold and that the person being watched is out of the field of view of the watcher; It is a lost child detection method characterized by having.

  According to the lost child detection method according to the ninth aspect of the invention, when the watching target person is away from the watcher, it is determined whether the watching target person is lost based on the view range of the watcher. This makes it possible to prevent misjudgment of a lost child when watching the subject from a distance.

  According to a tenth aspect, in the ninth aspect, the field-of-view range is calculated based on a face direction of the watcher.

  According to the lost child detection method according to the tenth aspect of the present invention, even if the eyes of the watcher cannot be recognized due to lack of resolution of the captured image, the watcher's face direction deviates from the watcher's view range. It is possible to easily determine whether or not it is.

  The eleventh invention is characterized in that, in the tenth invention, the field-of-view range is a range of a predetermined angle set on the basis of the orientation of the face of the watcher.

  According to the lost child detection method according to the eleventh aspect of the present invention, the visibility range can be easily calculated.

  According to a twelfth aspect, in any one of the ninth to eleventh aspects, the step of detecting an obstacle from the captured image, the distance is determined to be equal to or greater than a predetermined threshold, and When the obstacle exists between the watcher and the watch target person, the step of determining that the watch target person is lost even if the watch target person exists within the field of view. Furthermore, it is characterized by having.

  According to the lost child detection method according to the twelfth aspect of the present invention, it is possible to appropriately determine whether or not the watching target person is a lost child even when the watching target person is in a place where it is difficult for the watcher to visually recognize directly.

  Further, in a thirteenth aspect according to any one of the ninth to twelfth aspects, the step of detecting a person different from the watcher from the captured image, and the distance is equal to or greater than a predetermined threshold value. If it is determined and the watcher and a person different from the watcher are facing each other, it is determined that the watch target person is lost even if the watch target person exists within the field of view. And a step.

  According to the lost child detection method according to the thirteenth aspect of the invention, for example, even when the watcher's attention is deviated from the person being watched over due to circumstances such as the watcher having a conversation with another person, etc. It can be appropriately determined whether or not the subject is lost.

  According to a fourteenth aspect of the present invention, in any one of the ninth to thirteenth aspects, the step of estimating the age group of a person included in the captured image, and the age group based on the estimated year group The method further includes the steps of: determining a high person as a watcher and determining a low-age person as a target person.

  According to the lost child detection method according to the fourteenth aspect of the present invention, it is possible to detect in a situation where there is a difference in the age group of the watching person and the watching target person, such as with parents and children.

  According to a fifteenth aspect, in the fourteenth aspect, the age group is estimated based on a contour of the person extracted from the captured image.

  According to the lost child detection method according to the fifteenth aspect of the present invention, the age group can be easily detected from the captured image.

  In addition, in a sixteenth aspect of the present invention, in any one of the ninth to fifteenth aspects, an alarm for notifying that a lost child has been detected is issued when the person being watched over is determined to be lost. And a reporting step.

  According to the lost child detection method according to the sixteenth aspect of the present invention, when it is determined that the person being watched over is lost, it is possible to issue an alarm notifying that a lost child has been detected.

  Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In this embodiment, for example, in a commercial facility such as a shopping mall or a theme park, a case where a lost child is detected based on a captured image captured by an imaging device will be described. In the present embodiment, it is assumed that the watcher is a parent and the watch target person is a child.

  FIG. 1 is a configuration diagram illustrating an overview of a lost child detection system 1 including a lost child detection device 3 according to the present disclosure. As shown in FIG. 1, the lost child detection system 1 mainly includes an imaging device 2 and a lost child detection device 3. The imaging device 2 and the lost child detection device 3 are connected to each other via a network 4 such as a dedicated line or a LAN (Local Area Network).

  The imaging device 2 is a monitoring camera (video camera) having a well-known shooting function or communication function, and is installed on a wall, ceiling, pole, or the like of various places in a commercial facility, and a predetermined monitoring area is a still image or a moving image. As time series. A captured image (still image or moving image) generated by the imaging of the imaging device 2 is appropriately transmitted to the lost child detection device 3 via the network 4. In addition, as long as a predetermined monitoring area can be imaged, the imaging device 2 is not particularly limited in its form, function, arrangement, quantity, and the like, and various changes can be made.

  The lost child detection device 3 includes a computer having a known configuration, and detects a lost child by analyzing a captured image acquired from the imaging device 2. When a lost child is detected, an alert that reports that a lost child has been detected is issued.

  FIG. 2 is a block diagram illustrating a schematic configuration of the lost child detection device 3. The lost child detection apparatus 3 has a known hardware configuration, and includes a processor 11 that executes each process of lost child detection based on a predetermined control program (for example, a lost child detection program), a work area of the processor 11, and the like. A RAM 12 that functions as a volatile memory, a ROM 13 that stores a control program executed by the processor 11 and data, a ROM 13 that stores data, a storage unit 14 that includes an HDD or a flash memory, a display unit 15 that includes a liquid crystal monitor, a keyboard, It has the input part 16 which consists of input devices, such as a mouse | mouth, and the communication part 17 etc. which perform communication via the network 4.

  Each function of the lost child detection device 3 can be realized by the processor 11 executing a predetermined control program in the hardware configuration shown in FIG. The lost child detection device 3 is not limited to a computer, and other information processing devices (for example, a server) capable of performing the same function can be used. Further, at least a part of the function of the lost child detection device 3 may be replaced by processing by other known hardware.

  FIG. 3 is a flowchart showing the flow of the lost child detection process in the lost child detection device 3. The following processing is performed by the processor 11 of the lost child detection device 3 and is started when a captured image is acquired from the imaging device 2.

  First, a person is detected from the captured image (step ST101). A person is detected using a known method such as a method using a statistical or non-statistical classifier or a method using template matching.

  Subsequently, the person attribute of the person detected in step ST101 is estimated (step ST102). In the present embodiment, the age group is estimated as the person attribute. Thereby, it can be determined whether the person detected in step ST101 is an adult or a child. The person attribute estimation method will be described in detail. First, a person's outline (silhouette) or a part of the outline is extracted from the captured image. Then, based on the extracted contour or a part of the contour, the age group of the person is estimated using a statistical or non-statistical classifier prepared in advance. Note that the extraction of the outline of a person is performed using a known method such as a method using an edge feature amount. For example, the height and body shape of the person can be detected from the contour, and the age group of the person (that is, whether the person is an adult or a child) can be determined based on the detected height and body shape. .

  Next, the person detected in step ST101 is traced (step ST103). Specifically, a unique identifier (ID) is assigned to the person detected in step ST101, and tracking is performed over a predetermined number of frames for each person to which the identifier (ID) is assigned.

  In the subsequent step ST104, the parent and child that are the detection targets of the lost child are detected. Specifically, based on the result of the person tracking in step ST103, two persons who are photographed together over a predetermined number of frames and whose distances are equal to or less than a predetermined threshold in each frame. Detect people. If such two persons are detected, and one of the two persons is an adult and the other is a child, it is determined that the two persons are a parent and a child. Whether each of the two persons is an adult or a child is determined based on the estimation result of the person attribute (yearly group) in step ST102.

FIG. 4 is a diagram illustrating an example of the parent-child detection process in step ST104. In the example of FIG. 4, the first person 21 and the second person 22 are shown together over a predetermined number of frames continuous in time series of frame A... Frame B. Further, the distance D between the first person 21 and the second person 22 is smaller than a predetermined threshold value _Dth1 in each of the frames A, B, and C. Then, it is assumed that the first person 21 is determined as an adult and the second person 22 is determined as a child by the person attribute estimation process in step ST102. In such a case, it is determined that the first person 21 and the second person 22 are parents and children. In this way, it is possible to detect the parent and child that are the detection targets of the lost child.

In the subsequent step ST105, the parent and child detected in step ST104 are tracked in subsequent frames, and it is determined whether or not the distance between the parent and child is equal to or greater than a predetermined threshold for each predetermined number of frames. To do. Specifically, the distance D between the parent 21 and the child 22 is detected, and it is determined whether or not the detected distance D is _greater than or _equal to a predetermined threshold value _Dth2 . Thereby, it can be determined whether or not the child 22 is away from the parent 21. If the child 22 is away from the parent 21, the child 22 may be lost. When it is determined that the detected distance D is _{equal to} or greater than the threshold _Dth2 (step ST105: Yes), the process proceeds to step ST106, and when it is determined that the detected distance D is not _{equal to} or greater than the threshold _Dth2 (step ST105: No) ) Terminates the process.

FIG. 5 is a diagram illustrating an example of a process for determining the distance D between the parent and the child in step ST105. In FIG. 5A, since the distance D between the parent 21 and the child 22 is _{equal to} or greater than a predetermined threshold value _Dth2 , the child 22 is away from the parent 21, that is, the child 22 may be lost. It is determined that there is. In FIG. 5B, since the distance D between the parent 21 and the child 22 is less than a predetermined threshold value _Dth2 , the child 22 is not separated from the parent 21, that is, the child 22 may be lost. It is determined that there is no.

  In the next step ST106, the face orientation of the parent 21 is detected. Specifically, a facial feature amount is extracted from the face area of the first person 21 using a known method, and a statistical or non-statistic classifier prepared in advance is used based on the extracted facial feature amount. Detect face orientation. The face area is detected using a known method such as a method using a statistical or non-statistical classifier or a method using template matching.

  In step ST107, it is determined whether or not the face direction of the parent 21 deviates from the child 22. Specifically, first, based on the face orientation of the parent 21 detected in step ST106, a visual field range 23 of a predetermined angle α is set. Next, it is determined whether or not the child 22 exists within the visual field range 23 of the parent 21. Then, when it is determined that the child 22 does not exist within the visual field range 23 of the parent 21, and when it exceeds a predetermined time (for example, 10 seconds to 60 seconds), the face orientation of the parent 21 is the child. It is determined that it is deviating from 22. When the orientation of the face of the parent 21 is deviated from the child 22, that is, when the attention of the parent 21 is deviated from the child 22, the child 22 can be determined to be lost. When it is determined that the face direction (attention) of the parent 21 has deviated from the child 22 (step ST107: Yes), the process proceeds to step ST108, and the face direction (attention) of the parent 21 has not deviated from the child 22. Is determined (step ST107: No), the process ends.

  FIG. 6 is a diagram showing an example of the parent face orientation determination process in step ST107. FIG. 6 is a view corresponding to FIG. 5A and shows a case where the child 22 may be lost. In FIG. 6A, since the child 22 does not exist within the visual field range 23 of the parent 21, the face direction (attention) of the parent 21 deviates from the child 22, that is, the child 22 is determined to be a lost child. The In FIG. 6B, since the child 22 exists within the field of view range 23 of the parent 21, it is determined that the face direction (attention) of the parent 21 is not deviated from the child 22, that is, the child 22 is not a lost child. The

  In step ST108, an alarm for notifying that a lost child has been detected is issued. Specifically, for example, alarm information such as “lost child detection” is displayed on the display unit 15 (see FIG. 2) of the lost child detection device 3 to issue an alarm for lost child detection. That is, in the present embodiment, the display unit 15 serves as an alarm reporting unit. In addition, you may make it output a warning audio | voice with the alerting | reporting by the display of warning information. In addition, an alarm device (not shown) such as an alarm buzzer or an alarm lamp may be used to issue an alarm for detecting a lost child.

  As described above, according to the lost child detection process described above, when the child 22 is away from the parent 21, it is determined whether or not the child 22 is lost based on the orientation of the parent 21's face. It is possible to prevent false detection of a lost child when watching the child 22 from a distance.

  In this embodiment, the case where there is one parent and one child has been described, but there may be a plurality of parents or parents corresponding to the parent. For example, there may be two parents and one child. In this case, when all of the faces of a plurality of parents (or guardians) deviate from the child, a lost child detection alarm may be issued.

  Further, in this embodiment, the watcher / watching target person is a parent and child, but the watcher / watching target person is not limited to the parent and child, and may be, for example, a kindergarten or elementary school teacher and a child. . Further, it may be a lead person and a lead person for travel or vacation. Moreover, the person to watch over may be other than a person, such as an owner and a pet.

  Further, in the present embodiment, when it is determined that the child 22 does not exist within the field of view range 23 of the parent 21 and it exceeds a predetermined time, the face direction of the parent 21 deviates from the child 22. However, the present invention is not limited to this. For example, when it is determined that the child 22 does not exist within the visual field range 23 of the parent 21 when it is desired to immediately detect the lost child, it is immediately determined that the face direction of the parent 21 deviates from the child 22. Good. Whether or not the control is performed so as not to determine that the face of the parent 21 has deviated from the child 22 until a predetermined time is exceeded, and how long this time is to be set, is an early stage of lost child. In consideration of the balance between the frequency of discovery and false detection, it may be selected as appropriate according to the situation in which this embodiment is applied.

  In the present embodiment, the distance between the watcher and the watchee is detected based on the captured image, but the procedure for detecting the distance is not limited to that based on the captured image. For example, the watcher and the watchee may have a terminal equipped with a positioning function such as GPS and a communication function with the lost child detection device 3, thereby measuring the distance.

  In the present embodiment, the lost child detection device 3 issues a warning display or a warning by itself, but is not limited thereto. For example, the lost child detection device may instruct the terminal or the like possessed by the parent 21 to display an alarm or issue an alarm through wireless communication or the like. Moreover, it is good also as instruct | indicating that the parent 21 is warned from the lost child detection apparatus 3 with respect to the guard or robot etc. which patrols the inside of a facility. That is, when a lost child is detected, it is sufficient that at least the parent 21 is notified of this, and the type of alarm is not limited.

  In the present embodiment, the field-of-view range is estimated from the face orientation of the parent 21, but the present invention is not limited to this. If the position of the eye of the parent 21 can be tracked, such as when a high-resolution camera is used, the view range may be estimated based on that. Also, a plurality of means may be used in combination, such as estimating the view range of the parent 21 away from the monitoring camera from the face direction and estimating the view range of the parent 21 close to the monitoring camera from the position of the black eye.

  In the present embodiment, the age group is estimated from the outline of the person, but the present invention is not limited to this. For example, the age group may be estimated from wrinkles or colors of the person's face. In addition to these, there are various known methods for extracting texture feature quantities of human images and estimating the age group based on the extracted feature quantities. May be. That is, in the present embodiment, it is only necessary to estimate the age of the person who is captured, and the estimation method using the contour is only an example.

  In the present embodiment, it is determined that a person is a parent and child when the person is at a close distance between a predetermined number of frames. However, the parent-child determination method is not limited to this. It is sufficient if it is possible to determine that the child is a parent and child by some means, and the method is not limited. For example, it is conceivable to have a transmitter corresponding to each parent and child.

  Further, in the present embodiment, it is determined that the child 22 is not lost when the orientation of the face of the parent 21 is not deviated from the child 22 (that is, when the child 22 exists within the field of view of the parent 21). Other conditions may be added. For example, when an obstacle 24 such as a wall exists between the parent 21 and the child 22 as shown in FIG. 7A, or when the parent 21 is connected to another person 25 as shown in FIG. When talking, there is a possibility that the parent 21 cannot visually recognize the child 22 or the attention of the parent 21 is deviated from the child 22 even if the face of the parent 21 does not deviate from the child 22. is there. In such a case, even if the face of the parent 21 is not deviated from the child 22, the child 22 may be determined to be lost. Here, the presence / absence of the obstacle 24 can be obtained, for example, by analyzing a plurality of frames of the video of the surveillance camera and detecting an area without movement. Whether or not the parent 21 is talking to the other person 25 can be determined, for example, by confirming whether or not the face direction of the parent 21 and the face direction of the other person 25 are opposite to each other.

  Further, the face of the parent 21 as shown in FIGS. 7A and 7B faces the child 22, but the parent 21 may not be able to see the child 22 or may be distracted. The intensity of the warning may be changed between the case where there is and the case where the face of the parent 21 deviates from the child 22 as shown in FIG. That is, when the direction of the face of the parent 21 is deviated from the child 22, there is a high possibility that the attention of the parent 21 is deviated from the child 22, so that a stronger warning may be issued. The warning intensity may be changed by changing the intensity of the same type of warning (for example, changing the volume or amount of vibration emitted from the alarm device, or the frequency or frequency), or changing the type of warning itself. It may be. When changing the type of warning itself, for example, a low-intensity warning is issued only to the parent 21, and a high-intensity warning is also issued to third parties other than the parent 21 by broadcasting in the hall or simultaneous delivery. It is good to do so.

Further, in the present embodiment, when the distance between the parent 21 and the child 22 is more than the threshold value D _th2 and there is no child 22 in the field of view of the parent 21, there is a possibility of being lost. Although determined, it is not necessary to limit the threshold to one. For example, when there is no child 22 within the field of view of the parent 21, the intensity of the warning may be increased stepwise as the distance between the parent 21 and the child 22 increases.

  As mentioned above, although this indication was explained based on specific embodiments, these embodiments are illustrations to the last, and this indication is not limited by these embodiments. In addition, all the constituent elements of the lost child detection apparatus and the lost child detection method according to the present disclosure shown in the above embodiment are not necessarily essential, and can be appropriately selected as long as they do not depart from the scope of the present disclosure. is there.

  The lost child detection device and the lost child detection method according to the present disclosure are useful as a lost child detection device, a lost child detection method, and the like that can prevent erroneous determination of a lost child when a watcher watches the person being watched from a distance away It is.

DESCRIPTION OF SYMBOLS 1 Lost child detection system 2 Camera 3 Lost child detection apparatus 4 Network 11 Processor 12 RAM
13 ROM
14 storage unit 15 display unit (alarm reporting unit)
16 Input unit 17 Communication unit 21 Parent (watcher)
22 children (persons to watch over)
23 Visibility range

Claims (16)

A processor;
A communication unit that performs communication with the imaging device;
The processor is
Obtaining a captured image including a person from the imaging device;
From the captured image, a monitoring target person who is a target of watching the behavior and a watcher who is a person watching the behavior of the watching target person are detected, and a distance between the watcher and the watching target person is detected. ,
Based on the image of the person's face included in the captured image, the view range of the watcher is calculated,
When it is determined that the distance is equal to or greater than a predetermined threshold, and when it is determined that the person being watched is out of the field of view of the watcher, determining that the person being watched is lost A lost child detection device.   The lost child detection apparatus according to claim 1, wherein the visibility range is calculated based on a face direction of the watcher.   3. The lost child detection apparatus according to claim 2, wherein the visual field range is a range of a predetermined angle set based on an orientation of the face of the watcher. The processor is
An obstacle is detected from the captured image,
In the case where the distance is determined to be equal to or greater than a predetermined threshold and the obstacle exists between the watcher and the watch target person, the watch target person exists within the view range. 4. The lost child detection apparatus according to claim 1, wherein the watching target person is determined to be lost. The processor is
From the captured image, detect a person different from the watcher,
In the case where the distance is determined to be equal to or greater than a predetermined threshold and the watcher and a person different from the watcher are facing each other, even if the watch target person is within the field of view, The lost child detection apparatus according to claim 1, wherein the watching target person is determined to be lost. The processor is
Estimating the age of the person included in the captured image,
6. The method according to any one of claims 1 to 5, wherein, based on the estimated age group, the person having a higher age group is determined to be a watcher, and the person having a lower age group is determined to be a target person. The stray child detection apparatus described. The processor is
The lost child detection apparatus according to claim 6, wherein an outline of the person is extracted from the captured image, and the age group is estimated based on the extracted outline. It further includes an alarm notification unit that issues an alarm notifying that a lost child has been detected,
The processor is
The lost child detection apparatus according to any one of claims 1 to 7, wherein when the person to be watched over is determined to be lost, the alarm notification unit issues the alarm. Acquiring a captured image of a person from the imaging device;
From the captured image, a monitoring target person who is a target of watching a behavior and a watcher who is a person watching the behavior of the watching target person are detected, and a distance between the watching person and the monitoring target is detected. Steps,
Calculating a view range of the watcher based on an image of a person's face included in the captured image;
Determining that the person being watched is lost when it is determined that the distance is greater than or equal to a predetermined threshold and that the person being watched is out of the field of view of the watcher; A lost child detection method comprising:   The lost child detection method according to claim 9, wherein the visibility range is calculated based on a face direction of the watcher.   11. The lost child detection method according to claim 10, wherein the visibility range is a range of a predetermined angle set based on an orientation of the face of the watcher. Detecting an obstacle from the captured image;
In the case where the distance is determined to be equal to or greater than a predetermined threshold and the obstacle exists between the watcher and the watch target person, the watch target person exists within the view range. The lost child detection method according to claim 9, further comprising a step of determining that the person being watched over is a lost child. Detecting a person different from the watcher from the captured image;
In the case where the distance is determined to be equal to or greater than a predetermined threshold and the watcher and a person different from the watcher are facing each other, even if the watch target person is within the field of view, The lost child detection method according to claim 9, further comprising a step of determining that the person being watched over is a lost child. Estimating a person's age group included in the captured image;
The method further comprises the steps of: determining a person with a higher age as a watcher based on the estimated age group, and determining as a person to watch over a person with a lower age group. 14. The lost child detection method according to any one of 13.   The lost child detection method according to claim 14, wherein the age group is estimated based on an outline of the person extracted from the captured image.   16. The method according to claim 9, further comprising a step of issuing an alarm notifying that a lost child has been detected when it is determined that the person being watched over is lost. Lost child detection method.

Images