Detection system

Abstract

To provide a detection method, a detection system, and a program capable of accurately detecting a situation in which a person carrying a carrying article may be in trouble.SOLUTION: A detection system 100 comprises: position detection means 121 for detecting positional information representing a predetermined portion of a person and a position of a carrying article having a specific shape associated with the person; and separation detection means 122 for detecting when the carrying article has separated from the person based on the positional information, in which when the separation detection means detects that the carrying article has left a predetermined portion of the person, positional information of a camera is transmitted to an information processing terminal as positional information indicating a presence of the person.SELECTED DRAWING: Figure 7

Description

Technical Field

[0001] The present invention relates to a detection method, a detection system, and a program for detecting the situation of a person carrying an accessory.

Background Art

[0002] When a person with a physical disability goes about their daily life, they may use various tools to assist with the movements associated with living. For example, visually impaired people use a white cane as an assistive device when walking. The white cane is used for purposes such as ensuring the safety of the tip of the cane of a visually impaired person, collecting information necessary for walking, and making others aware that the user is visually impaired.

[0003] On the other hand, visually impaired people may be involved in contact accidents or traffic accidents. In particular, the white cane of a visually impaired person may come into contact with others, automobiles, bicycles, or trains and be caught. Therefore, when using a white cane, visually impaired people often do not grip it tightly in order to prevent accidents such as the cane being caught. As a result, the cane may become detached from the hand of the visually impaired person.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

Non-Patent Documents

[0005]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] However, if the white cane is separated from the hand of a visually impaired person, it will be difficult to pick up the white cane afterwards. For this reason, it is also necessary to detect that the visually impaired person has released the white cane from their hand or that the visually impaired person is searching for the white cane, notify the surroundings, and provide assistance.

[0007] Here, Patent Document 1 describes mounting a sensor for detecting acceleration on a white cane and detecting the fall of the white cane from the detected acceleration. However, it is difficult to more accurately detect that the white cane has been separated from the hand of a visually impaired person only from the acceleration of the white cane, and there is a possibility of false detection. Also, in this case, it is not possible to detect the action of a person searching for an accessory such as a white cane. For this reason, there arises a problem that it is not possible to accurately detect a situation in which a person would be in trouble, such as a situation where a person has dropped a white cane or a situation where a person is searching for a white cane. And such a problem can occur not only in the case of a person carrying a white cane, but also in any situation where a person is carrying an accessory.

[0008] An object of the present invention is to provide a detection method, a detection system, and a program that can solve the above-described problem of being unable to accurately detect a situation in which a person carrying an accessory would be in trouble.

Means for Solving the Problems

[0009] A detection method according to one aspect of the present invention is to detect position information representing the positions of a predetermined part of a person and an accessory having a specific shape carried by the person, and based on the position information, detect that the accessory has been separated from the person. It has such a configuration.

[0010] Also, a detection system according to one aspect of the present invention is Position detection means for detecting position information representing the position of a predetermined part of a person and an accessory of a specific shape attached to the person, Separation detection means for detecting, based on the position information, that the accessory has separated from the person, Comprising, Adopts the following configuration.

[0011] Further, a program according to an aspect of the present invention, Causes an information processing apparatus, Position detection means for detecting position information representing the position of a predetermined part of a person and an accessory of a specific shape attached to the person, Separation detection means for detecting, based on the position information, that the accessory has separated from the person, To be realized, Adopts the following configuration.

Advantages of the Invention

[0012] With the present invention configured as described above, it is possible to accurately detect that an accessory has separated from a person.

Brief Description of the Drawings

[0013]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5A

Figure 5B

Figure 6

Figure 7

Figure 8

Mode for Carrying Out the Invention

[0014] <Embodiment 1> The first embodiment of the present invention will be described with reference to FIGS. 1 to 6. FIGS. 1 to 2 are diagrams for explaining the configuration of the detection system, and FIGS. 3 to 6 are diagrams for explaining the processing operation of the detection system.

[0015] [Configuration] The detection system in the present embodiment is used to detect that a person P such as a visually impaired person has left the white cane W in his hand. For this reason, the detection system is used for places visited by people, such as stations, airports, shopping streets, and shopping malls. However, the object detected by the detection system is not limited to the white cane, and any accessory may be targeted as long as it is an accessory with a specific shape attached to a predetermined part of the person P. For example, it may be used to detect glasses, hats, bags, etc. of the person P.

[0016] As shown in FIG. 1, the detection system includes a camera C and a detection device 10. Further, the detection device 10 is connected to an information processing terminal UT operated by a monitor U who monitors people who have visited such a place at the place where the detection system is used as described above. The camera C is a photographing device that photographs the person P, and may be newly installed for the detection system at the place where it is used, or may have been installed in advance as a security camera or a surveillance camera. Then, the camera C continuously photographs the user U, for example, and transmits the photographed image to the detection device 10.

[0017] The above detection device 10 is composed of one or more information processing devices including an arithmetic device and a storage device. As shown in FIG. 2, the detection device 10 includes a position detection unit 11, a distance detection unit 12, an attitude detection unit 13, and a notification unit 14. The functions of the position detection unit 11, the distance detection unit 12, the attitude detection unit 13, and the notification unit 14 can be realized by the arithmetic device executing programs for realizing the respective functions stored in the storage device. Further, the detection device 10 includes a model storage unit 15. The model storage unit 15 is composed of a storage device. Hereinafter, each configuration will be described in detail.

[0018] The above position detection unit 11 (position detection means) acquires a captured image captured by the camera C. Then, the position detection unit 11 detects the person P reflected in the captured image and detects the position information of a preset part of the person P. Specifically, the position detection unit 11 uses a posture estimation technique for detecting the skeleton of the person P as described in Non-Patent Document 1 to identify each part of the person P and detect the position information of each part. At this time, the position detection unit 11 uses a learning model for detecting the human skeleton stored in the model storage unit 15 to detect the position information of each part of the person P. As an example, as shown in the left figure of FIG. 3, the position detection unit 11 detects, as the position information of each part, the position information of the wrists, elbows, shoulders, pelvis, knees, and ankles, which are the joints of the user U, and the position information of the eyes, nose, and ears, which are the parts of the user U. And the position detection unit 11 in the present embodiment particularly detects the position information of the wrists. However, the position detection unit 11 may detect the position information of any part of the person P.

[0019] In addition, the position detection unit 11 detects the position information of the white cane W as an accessory with a specific shape attached to the person P from within the captured image. For example, as shown in the left diagram of FIG. 3, the position detection unit 11 detects the position information of the wrist part of the person P from within the captured image as described above, and detects a white, elongated rod-shaped object existing near such a wrist part as the white cane W, and detects the position information of the white cane W. At this time, the position detection unit 11 detects the position information of both end parts in the length direction of the white cane W. Then, the position detection unit 11 associates the position information of the wrist part of the person P with the position information of the end part closer to the wrist among both end parts of the white cane W, and always performs the detection of these position information at a constant time interval for a new captured image.

[0020] In addition, the position detection unit 11 is not necessarily limited to detecting the position information of each part of the person P using the posture estimation technique for detecting the skeleton of the person P described above, and the position information of each part of the person may be detected by any method. Also, the position detection unit 11 is not limited to performing the position information of the white cane W by the method described above, and may be performed by any method. For example, the position detection unit 11 may detect each position information using sensors attached to a predetermined part such as the wrist of the person P or sensors mounted on the white cane W without using the captured image. Note that when the position detection unit 11 detects the position information of an accessory other than the white cane W, the accessory in the captured image may be extracted based on the shape information of the accessory set in advance, and the position information of such an accessory may be detected.

[0021] As described above, the separation detection unit 12 (separation detection means) calculates the distance D between a predetermined part of the person P and a predetermined part of the white cane W using the position information of the person P detected as described above and the position information of the white cane W. Then, the separation detection unit 12 detects that the white cane W has moved away from the person P based on the calculated distance D. For example, as shown in the right diagram of FIG. 3, the separation detection unit 12 calculates these distances D from the position information of the wrist of the person P and the position information of the end of the white cane W close to the position of the wrist. Then, the separation detection unit 12 detects that the white cane W has moved away from the person P when the calculated distance D is separated by a preset distance or more for a preset time or more. As an example, the separation detection unit 12 detects that the white cane W has moved away from the person P when the calculated distance D is 1 m or more and such a distance D continues for 5 seconds or more.

[0022] However, the method described above is just an example, and the separation detection unit 12 may detect that the white cane W has moved away from the person P by other methods. For example, the separation detection unit 12 may calculate the distance between the center-of-gravity position of the person P and the center-of-gravity position of the white cane W, and detect that the white cane W has moved away from the person P based on such a distance.

[0023] As described above, the above-mentioned posture detection unit 14 (separation detection means) detects the posture of the person P after detecting that the white cane W has separated from the person P. For example, the posture detection unit 14 acquires a captured image captured by the camera 1, detects the person P reflected in the captured image, and detects the position information of a preset part of the person P. Specifically, similarly to the above, the posture detection unit 14 uses a posture estimation technique for detecting the skeleton of the person P to identify each part of the person P and detects the position information of each part. For example, as shown in the left figure of FIG. 4, the posture detection unit 14 detects, as the position information of each part of the person P, the position information of the wrists, elbows, shoulders, pelvises, knees, and ankles, which are the joints of the user U, and the position information of the eyes, nose, and ears, which are the parts of the user U. Then, the posture detection unit 14 detects the posture of the person P from the positional relationship of the position information of each part. For example, in the example of the left figure of FIG. 4, from the positional relationship of each joint of the person P, it is detected that the person P is in a bent posture and that the person P is trying to find the white cane W. Further, the posture detection unit 14 detects, for example, the posture such as the position of the head of the person P and the direction of the eyes, and detects from such a posture that the person P is trying to find the white cane W. Then, the posture detection unit 14 always performs the detection of the posture of the person P at regular time intervals for a new captured image. Thereby, the posture detection unit 14 may detect the movement of the person P. For example, when the posture of the person P changes from the left figure to the right figure of FIG. 4, it can be detected that the person P is taking an action to search for the dropped white cane W.

[0024] As described above, when the above-mentioned notification unit 15 (notification means) detects that the white cane W has separated from the person P, it performs a notification process of transmitting notification information including information indicating that there is a person P who has dropped the white cane W to the information processing terminal UT of the monitor U. At this time, the notification unit 15 specifies the position of the camera C from the identification information of the camera C that has captured the captured image when it is detected that the white cane W has separated from the person P, and transmits the position information of the camera C to the information processing terminal UT as the position information where the person P exists.

[0025] Further, as described above, the notification unit 15 (second notification means) detects the posture of the person P after detecting that the white cane W has separated from the person P, and performs a notification process (second notification process) of transmitting notification information to the information processing terminal UT of the monitor U according to the posture and movement. For example, when the notification unit 15 detects that the posture of the person P is a bent posture or the movement of the person P is a movement of searching for the white cane W, the notification unit 15 transmits, as notification information, to the information processing terminal UT the fact that the person P is searching for the white cane W and the position information that can be specified from the camera C that captured the captured image in which this was detected.

[0026] Note that the notification information notified to the information processing terminal UT of the monitor U by the above-described notification unit 15 is not limited to the information of the above-described content, and may be other information. Further, the notification unit 15 is not necessarily limited to notifying the information processing terminal UT of the notification information including the information that there is a person P who dropped the above-described white cane W, and may operate to notify only the notification information including the information that the person P is searching for the white cane W according to the subsequent posture of the person P.

[0027] [Operation] Next, the operation of the detection device 10 described above will be mainly described with reference to the flowchart of FIG. 5A. First, the detection device 10 always acquires a captured image captured by the camera C, and detects the position information of the person P and the white cane W from such a captured image (step S1). For example, the detection device 10 uses a posture estimation technique for detecting the skeleton of the person P to identify each part of the person P and detect the position information of each part. Further, the detection device 10 detects the position information of the white cane W based on the shape and color characteristics of the white cane W. In particular, the detection device 10 detects, for example, the position of the wrist of the person P and the position of the end of the white cane W.

[0028] Then, the detection device 10 calculates the distance between the person P and the white cane W, and detects that the white cane W has moved away from the person P according to such distance (Yes in step S2, step S3). For example, as shown in FIG. 3, the detection device 10 calculates the distance D between the wrist position of the person P and the end position of the white cane W, and detects that the white cane W has moved away from the person P when they are separated by a preset distance or more for a preset time or more. At this time, the detection device 10 may transmit notification information including information indicating that there is a person P who has dropped the white cane W to the information processing terminal UT of the supervisor U.

[0029] After that, after detecting that the white cane W has moved away from the person P, the detection device 10 uses the captured image obtained thereafter to detect the posture of the person P (step S4). For example, the detection device 10 uses a posture estimation technique for detecting the skeleton of the person P to identify each part of the person P, detects the position information of each part, and detects the posture of the person P according to the positional relationship of each part. Then, as shown in FIG. 4, for example, when the detection device 10 detects from the positional relationship of each joint of the person P that the person P is in a bent posture or is taking an action to search for the white cane W dropped by the person P (Yes in step S5), it notifies the information processing terminal UT of the supervisor U that there is a person P searching for the white cane W (step S6).

[0030] As described above, in this embodiment, the position information between the predetermined part of the person P and the white cane W is detected, and it is detected that the white cane W has moved away from the person P based on such position information. Therefore, it is possible to accurately detect that the white cane W has moved away from the person P, and it is possible to take prompt and appropriate support actions for the person P. Further, by detecting the posture of the person P who has left the white cane W, it is possible to accurately detect that the person P is searching for the white cane W, and it is possible to take prompt and appropriate support actions for the person P.

[0031] [Modification Example] Next, another example of the detection device 10 detecting that the person P is searching for the white cane W will be described with reference to the flowchart of FIG. 5B. First, the detection device 10 always acquires the captured image captured by the camera C, detects the position information of the person P and the white cane W from such captured image, and detects the person P holding the white cane W (step S11). For example, the detection device 10 uses a posture estimation technique for detecting the skeleton of the person P to identify each part of the person P and detect the position information of each part. Further, the detection device 10 detects the position information of the white cane W based on the shape and color characteristics of the white cane W. In particular, the detection device 10 detects the position of the wrist of the person P and the position of the end of the white cane W, and detects the person P holding the white cane W in the hand.

[0032] Note that the detection device 10 does not necessarily detect the position information of each part of the person P and the position information of the white cane W as described above, and may detect the person P accompanied by the white cane W by another method. For example, the detection device 10 detects the white cane W based on the shape and color characteristics of the white cane W, and detects the person P located near the white cane W from the feature amount and movement of the object, etc., so as to detect the person P accompanied by the white cane W. Also, different from the above, in this modification, the detection device 10 does not detect that the white cane W has separated from the person P, such as the person P dropping the white cane W.

[0033] Subsequently, after detecting the person P holding the white cane W in the hand, the detection device 10 uses the captured image acquired to detect the posture of such person P (step S12). For example, the detection device 10 uses a posture estimation technique for detecting the skeleton of the person P to identify each part of the person P, detect the position information of each part, and detect the posture of the person P according to the positional relationship of each part. Then, the detection device 10, for example, from the positional relationship of each joint of the person P, when it detects that the person P is in a bent posture as shown in the left figure of FIG. 4, or the person P is lying on the ground searching for something as shown in the right figure of FIG. 4 (Yes in step S13), it notifies the information processing terminal UT of the monitor U that there is a person P searching for the white cane W (step S14).

[0034] As described above, in the present embodiment, first, a person P holding a white cane W is detected, and from the posture of such person P, it is detected that the person P is searching for the white cane W. For this reason, it is possible to accurately detect a situation in which the person P is in trouble, such as the person P searching for an accessory such as the white cane W, and it is possible to take prompt and appropriate support actions for the person P.

[0035] <Embodiment 2> Next, a second embodiment of the present invention will be described with reference to FIGS. 6 to 8. FIGS. 6 to 7 are block diagrams showing the configuration of the detection system in Embodiment 2, and FIG. 8 is a flowchart showing the operation of the detection system. Note that in the present embodiment, an outline of the configuration of the detection system and the detection method described in the above-described embodiment is shown.

[0036] First, with reference to FIG. 6, the hardware configuration of the detection system 100 in the present embodiment will be described. The detection system 100 is configured by a general information processing apparatus, and as an example, it is equipped with the following hardware configuration. ·CPU (Central Processing Unit) 101 (arithmetic unit) ·ROM (Read Only Memory) 102 (storage device) ·RAM (Random Access Memory) 103 (storage device) ·Program group 104 loaded into RAM 103 ·Storage device 105 that stores program group 104 ·Drive device 106 that reads and writes external storage medium 110 of the information processing apparatus ·Communication interface 107 connected to communication network 111 outside the information processing apparatus ·Input / output interface 108 that performs input / output of data ·Bus 109 that connects each component

[0037] Then, by the CPU 101 acquiring the program group 104 and executing it, the detection system 100 can construct and equip the position detection means 121 and the separation detection means 122 shown in FIG. 7. The program group 104 is stored in advance in, for example, the storage device 105 or the ROM 102, and is loaded into the RAM 103 by the CPU 101 and executed as necessary. Further, the program group 104 may be supplied to the CPU 101 via the communication network 111, or may be stored in advance in the storage medium 110, and the drive device 106 may read out the program and supply it to the CPU 101. However, the above-described position detection means 121 and separation detection means 122 may be constructed of dedicated electronic circuits for realizing such means.

[0038] Note that FIG. 6 shows an example of the hardware configuration of the information processing apparatus which is the detection system 100, and the hardware configuration of the information processing apparatus is not limited to the above-described case. For example, the information processing apparatus may be configured from a part of the above-described configuration such as not having the drive device 106.

[0039] Then, the detection system 100 executes the detection method shown in the flowchart of FIG. 8 by the functions of the position detection means 121 and the separation detection means 122 constructed by the program as described above.

[0040] As shown in FIG. 8, the detection system 100 detects position information representing the positions of a predetermined part of a person and an accessory having a specific shape attached to the person (step S101), detects that the accessory has separated from the person based on the position information (step S102), and executes such processing.

[0041] With the present invention configured as described above, the position information between a predetermined part of a person and an accessory is detected, and it is detected that the accessory has separated from the person based on such position information. Therefore, it is possible to accurately detect that the white cane has separated from the person, that is, it is possible to accurately detect a situation in which the person may be in trouble, and it is possible to take prompt and appropriate support actions for the person P.

[0042] Note that the above-described program can be stored using various types of non-transitory computer readable media and supplied to a computer. Non-transitory computer readable media include various types of tangible storage media. Examples of non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROM (Read Only Memory), CD-R, CD-R / W, semiconductor memories (e.g., mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory)). Also, the program may be supplied to the computer by various types of transitory computer readable media. Examples of transitory computer readable media include electrical signals, optical signals, and electromagnetic waves. The transitory computer readable media can supply the program to the computer via wired communication paths such as electric wires and optical fibers, or wireless communication paths.

[0043] The present invention has been described above with reference to the above-described embodiments and the like. However, the present invention is not limited to the above-described embodiments. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. Further, at least one or more of the functions of the above-described position detection means 121 and the separation detection means 122 may be executed by an information processing apparatus installed and connected at any location on the network, that is, may be executed by so-called cloud computing.

[0044] <Appendix> Some or all of the above embodiments may also be described as follows. Hereinafter, an outline of the configuration of the detection method, detection system, and program in the present invention will be described. However, the present invention is not limited to the following configuration. (Appendix 1) Detect position information representing the position of a predetermined part of a person and an accessory having a specific shape attached to the person, Based on the position information, detect that the accessory has moved away from the person, Detection method. (Appendix 2) The detection method according to Appendix 1, Detect the position information of the predetermined part of the person and the accessory from a photographed image of the person by detecting the skeleton of the person, Detection method. (Appendix 3) The detection method according to Appendix 1 or 2, Detect that the accessory has moved away from the person by a preset distance or more, Detection method. (Appendix 4) The detection method according to any one of Appendices 1 to 3, Detect that the accessory has moved away from the person for a preset time or more, Detection method. (Appendix 5) The detection method according to any one of Appendices 1 to 4, When it is detected that the accessory has moved away from the person, perform a preset notification process, Detection method. (Appendix 6) The detection method according to any one of Appendices 1 to 5, detecting the posture of the person after detecting that the accessory has left the person, detection method. (Appendix 7) The detection method according to Appendix 6, detecting the posture of the person by detecting the skeleton of the person from a captured image obtained by capturing the person after detecting that the accessory has left the person, detection method. (Appendix 8) The detection method according to Appendix 6 or 7, detecting the movement of the person based on the detected posture of the person, detection method. (Appendix 9) The detection method according to Appendix 7 or 8, performing a preset second notification process based on the detected posture of the person, detection method. (Appendix 10) The detection method according to any one of Appendices 1 to 9, wherein the accessory is a rod-shaped body having a predetermined length, detection method. (Appendix 11) The detection method according to Appendix 10, wherein the accessory is a white cane, detection method. (Appendix 12) Position detection means for detecting position information representing the position of a predetermined part of a person and an accessory of a specific shape attached to the person, Separation detection means for detecting that the accessory has left the person based on the position information, A detection system comprising: (Appendix 13) The detection system according to Appendix 12, wherein the position detection means detects the position information of the predetermined part of the person and the accessory by detecting the skeleton of the person from a captured image of the person, Detection system. (Appendix 14) The detection system according to Appendix 12 or 13, wherein the separation detection means detects that the accessory is separated from the person by a preset distance or more. Detection system. (Appendix 15) The detection system according to any one of Appendices 12 to 14, wherein the separation detection means detects that the accessory is separated from the person for a preset time or more. Detection system. (Appendix 16) The detection system according to any one of Appendices 12 to 15, comprising notification means for performing a preset notification process when it is detected that the accessory has separated from the person. Detection system. (Appendix 17) The detection system according to any one of Appendices 12 to 16, comprising posture detection means for detecting the posture of the person after it is detected that the accessory has separated from the person. Detection system. (Appendix 18) The detection system according to Appendix 17, wherein the posture detection means detects the posture of the person by detecting the skeleton of the person from a captured image of the person taken after it is detected that the accessory has separated from the person. Detection system. (Appendix 19) The detection system according to Appendix 17 or 18, wherein the posture detection means detects the movement of the person based on the detected posture of the person. Detection system. (Appendix 20) The detection system according to Appendix 18 or 19, comprising second notification means for performing a preset second notification process based on the detected posture of the person. Detection system. (Appendix 21) An information processing apparatus, position detection means for detecting position information representing the position of a predetermined part of a person and an accessory of a specific shape attached to the person; separation detection means for detecting that the accessory has separated from the person based on the position information; A computer-readable storage medium storing a program for realizing the above. (Appendix 21.1) A computer-readable storage medium storing a program stored in a computer according to Appendix 21, wherein the information processing apparatus further comprises: notification means for performing a preset notification process when it is detected that the accessory has separated from the person; A computer-readable storage medium storing a program for realizing the above. (Appendix 22) A computer-readable storage medium storing a program stored in a computer according to Appendix 21, wherein the information processing apparatus further comprises: posture detection means for detecting the posture of the person after it is detected that the accessory has separated from the person; A computer-readable storage medium storing a program for realizing the above. (Appendix 22.1) A computer-readable storage medium storing a program stored in a computer according to Appendix 22, wherein the information processing apparatus further comprises: second notification means for performing a preset second notification process based on the detected posture of the person; A computer-readable storage medium storing a program for realizing the above. (Appendix A1) Detecting a person with an accessory, then detecting the posture of the person, and detecting that the person takes a preset specific posture based on the detected posture of the person; Detection method. (Appendix A2) The detection method according to Appendix A1, Detecting the posture of a person by detecting the skeleton of the person from a captured image of the person. Detection method. (Appendix A3) The detection method according to Appendix A1 or A2, Detecting that the person takes a posture of searching for an accessory as the specific posture based on the detected posture of the person. Detection method. (Appendix A4) The detection method according to any one of Appendices A1 to A3, When it is detected that the person takes the specific posture, performing a preset notification process. Detection method.

Explanation of symbols

[0045] 10 Detection device 11 Position detection unit 12 Separation detection unit 13 Posture detection unit 14 Notification unit 15 Model storage unit C Camera P Person U Monitor UT Information processing terminal 100 Detection system 101 CPU 102 ROM 103 RAM 104 Program group 105 Storage device 106 Drive device 107 Communication interface 108 Input / output interface 109 Bus 110 Storage medium 111 Communication network 121 Position detection means 122 Separation detection means

Claims

1. an object having a sensor; A detection device that performs detection based on video; An information processing terminal; A detection system comprising: A means for acquiring position information of a body part of a person based on an image; means for acquiring an output from the sensor; a means for notifying the information processing terminal of information relating to a position of the person in response to detection of the object moving away from the person based on an output from the sensor; Equipped with Detection system.

2. 2. The detection system of claim 1, means for acquiring a position of the object based on an output from the sensor; a means for calculating a distance based on a position of the object and position information of a body part of the person; Further equipped with If the distance is equal to or greater than a preset distance, it is determined that the object has been detected as having moved away from the person. Detection system.

3. 2. The detection system of claim 1, The body part of the person includes a knee or ankle. Detection system.

4. 2. The detection system of claim 1, a means for identifying a position of a camera that captured the image in response to detecting that the object has moved away from the person; Detection system.

5. 5. The detection system of claim 4, The information regarding the position of the person includes the position of the camera. Detection system.

6. 2. The detection system of claim 1, The object having the sensor is at least one of a white cane, glasses, a hat, and a bag. Detection system.

7. an object having a sensor; A detection device that performs detection based on video; An information processing terminal; A detection method in a detection system comprising: The detection device, Obtaining the location information of a person's body parts based on the video, acquiring an output from the sensor; In response to detection based on an output from the sensor that the object has moved away from the person, the information processing terminal is notified of information regarding a position of the person. Detection method.

8. an object having a sensor; A detection device that performs detection based on video; An information processing terminal; The detection device of the detection system includes: Obtaining the location information of a person's body parts based on the video, acquiring an output from the sensor; In response to detection based on an output from the sensor that the object has moved away from the person, the information processing terminal is notified of information regarding a position of the person. A program that executes a process.

Images