Detection system, detection method, and program

Abstract

To provide a detection system, a detection method and a program that can estimate a state of a person to be detected.SOLUTION: A detection system 10 comprises: a foot detection part 1 which detects a position of a foot of a person to be detected; an upper half body detection part 2 which detects a position of at least a part of an upper half body of the person to be detected; and an estimation part 3 which estimates a state of the person to be detected based upon a movement distance of the foot and a movement distance of at least the part of the upper half body calculated using the detected position of the foot and the detected position of at least the part of the upper half body.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] The present disclosure relates to a detection system, a detection method, and a program.

Background Art

[0002] The foot contact position tracking device disclosed in Patent Document 1 detects the position where a person's foot touches the ground by receiving an image captured by a camera and performing image processing.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Techniques for detecting the position of a person's body part using image processing are sometimes used, for example, in the generation of teaching data in the field of AI (artificial intelligence) such as machine learning and deep learning.

[0005] The present inventors have discovered the following problems. The state of the detection target person changes, such as the foot of the detection target person being hidden by an obstacle or the detection target person changing their posture. In such a foot contact position tracking device, the correctness of the detection result of the position of a person's foot may change according to the state of the detection target person. Therefore, if the state of the detection target person can be estimated, the detection accuracy of the position of a person's foot can be improved. Accordingly, it is required to be able to estimate the state of the detection target person.

[0006] The present disclosure has been made in view of the above problems, and provides a detection system, a detection method, and a program capable of estimating the state of a detection target person.

Means for Solving the Problems

[0007] The detection system related to this disclosure is A foot detection unit that detects the position of the feet of the person being detected, An upper body detection unit that detects the position of at least a part of the upper body of the person to be detected, The system includes an estimation unit that estimates the state of the detected subject based on the distance traveled by the feet and the distance traveled by at least a part of the upper body, calculated using the detected foot position and the detected position of at least a part of the upper body.

[0008] Furthermore, in the detection system described above, if only the distance traveled by the feet exceeds a predetermined value, and only the feet move in the vertical direction, the estimation unit may estimate that at least a part of the lower body of the person being detected is hidden by an obstacle.

[0009] Furthermore, in the detection system described above, if the distance traveled by the feet and the distance traveled by at least a part of the upper body exceed a predetermined value, and the feet and at least a part of the upper body move in the vertical direction, the estimation unit may estimate that the person being detected is going up or down stairs, or that the person being detected is jumping.

[0010] Furthermore, in the detection system described above, if the distance traveled by at least a portion of the upper body exceeds a predetermined value, the estimation unit may estimate that the posture of the person being detected has changed, or that at least a portion of the upper body of the person being detected is hidden by an obstacle.

[0011] Furthermore, the above-mentioned detection system is further equipped with a correction unit, If the estimation unit estimates that at least a part of the lower body of the person being detected is hidden by an obstacle, the correction unit may correct the detected foot position to the foot position based on the skeletal structure of the person being detected.

[0012] The detection method relating to this disclosure is a detection method using a detection system, A step to detect the position of the feet of the person to be detected, A step of detecting at least a part of the upper body position of the detection target person; Based on the moving distance of the foot and the moving distance of at least a part of the upper body calculated using the detected foot position and the detected position of at least a part of the upper body, a step of estimating the state of the detection target person.

[0013] The program according to the present disclosure causes a computer operating in a detection system to A step of detecting the position of the foot of the detection target person; A step of detecting at least a part of the upper body position of the detection target person; Based on the moving distance of the foot and the moving distance of at least a part of the upper body calculated using the detected foot position and the detected position of at least a part of the upper body, a step of estimating the state of the detection target person is executed.

Advantages of the Invention

[0014] According to the present disclosure, the state of the detection target person can be estimated.

Brief Description of the Drawings

[0015] [Figure 1] It is a block diagram showing a configuration example of a detection system according to an embodiment. [Figure 2] It is a flowchart showing an example of a detection method according to an embodiment. [Figure 3] It is a diagram showing an image in an example of a detection method according to an embodiment. [Figure 4] It is a diagram showing an image in an example of a detection method according to an embodiment. [Figure 5] It is a diagram showing an image in an example of a detection method according to an embodiment. [Figure 6] It is a diagram showing an image in an example of a detection method according to an embodiment. [Figure 7] It is a diagram showing an image in an example of a detection method according to an embodiment. [Figure 8]This is a diagram showing an image in an example of the detection method according to the embodiment. [Figure 9] This is a diagram showing an example of the hardware configuration included in the detection system. [Figure 10] This is a flowchart showing another example of the detection method according to the embodiment.

Embodiments for Carrying Out the Invention

[0016] Hereinafter, specific embodiments to which the present invention is applied will be described in detail with reference to the drawings. However, the present invention is not limited to the following embodiments. Also, for clarity of explanation, the following description and drawings are appropriately simplified.

[0017] (Embodiment) <Configuration> A configuration example of the detection system according to the embodiment will be described with reference to FIG. 1.

[0018] As shown in FIG. 1, the detection system 10 includes a foot detection unit 1, an upper body detection unit 2, and an estimation unit 3. Further, the detection system 10 may further include a correction unit 4. Each unit of the detection system 10 may be realized by the cooperation of one or more programs installed in the computer device constituting the detection system 10, the processor of the computer device, and hardware such as a memory.

[0019] The foot detection unit 1 detects the position of the feet of the detection target person from the image. The foot detection unit 1 may detect, for example, the positions of the legs, heels, toes, etc. of the detection target person. The upper body detection unit 2 detects the position of at least a part of the upper body of the detection target person from the image. At least a part of the upper body of the detection target person is, for example, the head, torso, the entire upper body, etc.

[0020] Specifically, the foot detection unit 1 and the upper body detection unit 2 acquire an image in which the subject to be detected is the subject. The foot detection unit 1 and the upper body detection unit 2 identify the subject to be detected within the acquired image and generate information indicating the subject's region. This information is, for example, a bounty box. The foot detection unit 1 detects, for example, the midpoint of the lower side of the rectangle indicated by the bounty box as the position of the subject's feet. The upper body detection unit 2 detects, for example, the midpoint of the upper side of the rectangle indicated by the bounty box as the position of the subject's head.

[0021] The estimation unit 3 estimates the state of the person being detected based on the distance traveled by the feet and the distance traveled by the upper body. Specifically, the estimation unit 3 calculates the distance traveled by the feet using the position of the feet detected by the foot detection unit 1. The estimation unit 3 also calculates the distance traveled by the upper body using the position of at least a part of the upper body detected by the upper body detection unit 2.

[0022] The correction unit 4 corrects the foot position detected by the foot detection unit 1 to the foot position based on the skeletal structure of the person being detected. Specifically, the correction unit 4 identifies the positions of the joints of the person being detected. Based on these joint positions, the correction unit 4 estimates the position of the person's feet. Furthermore, the correction unit 4 corrects the foot position detected by the foot detection unit 1 to this estimated foot position. More specifically, the correction unit 4 identifies the positions of the joints from the head to the ankles of the person being detected, or the positions of the joints in the thigh and lower leg of the person being detected. Furthermore, the correction unit 4 estimates the position of the person's toes based on these identified joint positions. Furthermore, the correction unit 4 corrects the foot position detected by the foot detection unit 1 to this estimated toe position.

[0023] The detection system 10 may also include a generation unit that captures an image that may include the person to be detected as the subject and generates data indicating the captured image. This generation unit is, for example, a camera device. The detection system 10 may also include a storage unit that stores various data, including information that associates the data indicating the captured image with the time when the image was taken. The time when the image was taken may be determined, for example, from the frame rate. The data indicating the captured image may be associated with information indicating the area of ​​the person to be detected, the position of the feet detected by the foot detection unit 1, the position of at least a part of the upper body detected by the upper body detection unit 2, the distance the feet moved calculated by the estimation unit 3, the distance the upper body moved calculated by the estimation unit 3, etc.

[0024] <Detection Method> Next, with reference to Figure 2, an example of a detection method by the detection system 10 according to the embodiment will be described. Figure 2 is a flowchart showing an example of a detection method according to the embodiment.

[0025] Step ST1 detects the positions of the subject's feet and head in the current frame image and the previous frame image.

[0026] Next, the positions of the feet and head of the detected subject are compared with those of the previous frame image to calculate the distance and direction of movement of the feet and head (Step ST2).

[0027] Next, it is determined whether the distance traveled by the feet alone exceeds a predetermined value, and whether only the feet moved vertically (step ST3). This predetermined value is, for example, the distance traveled by the person being detected while walking during the period t that has elapsed from the time the current frame image was captured to the time the previous frame image was captured. The period t can be determined from the frame rate of the camera device described above. The distance traveled by the person being detected while walking during period t can be determined by multiplying the walking speed of the person being detected by period t. The walking speed of the person being detected may be obtained from previously known data.

[0028] If only the distance the feet move exceeds a predetermined value, and only the feet move vertically (Step ST3: YES), it is presumed that at least a part of the lower body of the person being detected is hidden by an obstacle (Step ST4). Therefore, the position of the feet in the current frame image detected in Step ST1 is actually the same as the upper part of the obstacle, and differs from the actual position of the feet. Thus, the position of the feet in the current frame image detected in Step ST1 is incorrect. Furthermore, the position of the feet in the current frame image detected in Step ST1 is corrected to the position of the feet based on the skeleton of the person being detected (Step ST5). This correction improves the accuracy of detecting the position of the feet in the current frame image. After performing Step ST5, this detection method is terminated.

[0029] Otherwise (Step ST3: NO), it is determined whether the distance traveled by the feet and the distance traveled by the head exceeded a predetermined value, and whether the feet and head moved vertically (Step ST6).

[0030] If the distance traveled by the feet and the distance traveled by the head exceeds a predetermined value, and the feet and head move vertically (Step ST6: YES), it is presumed that the person being detected is going up or down stairs, or that the person being detected is jumping (Step ST7).

[0031] Otherwise (Step ST6: NO), it is determined whether the distance the head moves alone exceeds a predetermined value (Step ST8).

[0032] If only the distance the head moves exceeds a predetermined value (Step ST8: YES), it is presumed that the posture of the person being detected has changed, or that at least part of the upper body of the person being detected is hidden by an obstacle (Step ST9). The detection method is terminated.

[0033] Otherwise (Step ST8: NO), this detection method is terminated. Similarly, this detection method is terminated for Steps ST7, ST9 and beyond. Note that if the posture of the person being detected has changed, or if at least part of the upper body of the person being detected is hidden by an obstacle, the position of the feet is presumed to be correct, and therefore no correction of the detected foot position is necessary.

[0034] Based on the above, the state of the person being detected can be estimated. Furthermore, based on this estimation, it is determined whether correction of the detected foot position is necessary, and if necessary, the detected foot position is corrected. As a result, the position of the person's feet can be correctly detected. Additionally, by continuing to detect the position of the person's feet and connecting the points indicating these detected foot positions, the path the person's feet moved can be determined.

[0035] <First specific example of the detection method> Next, with reference to Figures 3 to 6, a first specific example of the detection method by the detection system 10 will be described.

[0036] It should be noted that the right-handed XYZ coordinate system shown in Figure 3 and other drawings is merely for convenience in explaining the positional relationships of the components. Typically, the positive Z-axis direction is vertically upward, and the XY plane is the horizontal plane, and this is consistent across drawings.

[0037] In this specific example, as shown in Figure 3, a person P1 walking on a floor surface F1 on which obstacles OB1 and OB2 are placed is continuously imaged, and the detection method of the detection system 10 is applied to these multiple images. Obstacle OB1 is a wheeled shelf, and obstacle OB2 is a chair. The floor surface F1 extends along the XY plane, that is, the horizontal plane. The person P1 moves along the path DLL shown in Figures 4 and 5 on the floor surface F1. That is, the person P1 moves in the positive Y direction on the floor surface F1, and then moves in the positive X direction. As shown in Figure 3, the skeletal model SK1 is created by estimating from the skeleton of the person P1. The skeletal model SK1 is superimposed on the portion of the image that shows the person P1. Figure 5 shows the current frame image FR2. Figure 4 shows the previous frame image FR1, which was captured immediately before the current frame image FR2 shown in Figure 5.

[0038] In step ST1, a bounty box BB1, which represents the area of ​​the person to be detected P1, is generated in the previous frame image FR1 shown in Figure 4. The foot detection unit 1 detects the midpoint of the lower side of the rectangle represented by the bounty box BB1 as the position DL1 of the foot PL1 of the person to be detected P1. The upper body detection unit 2 detects the midpoint of the upper side of the rectangle represented by the bounty box BB1 as the position DH1 of the head PH1 of the person to be detected P1. This detected position DL1 is approximately the same as the actual position of the foot PL1, and this detected position DH1 is approximately the same as the actual position of the head PH1. Therefore, the positions of the foot PL1 and head PH1 of the person to be detected P1 can be detected with good accuracy.

[0039] Similarly, in the current frame image FR2 shown in Figure 5, a bounty box BB2 is generated, which is the region representing the target person P1. The foot detection unit 1 detects the midpoint of the lower side of the rectangle represented by the bounty box BB2 as the position DL2 of the target person P1's foot PL1. The upper body detection unit 2 detects the midpoint of the upper side of the rectangle represented by the bounty box BB2 as the position DH2 of the target person P1's head PH1. This detected position DH2 is almost the same as the actual position of the head PH1. On the other hand, this detected position DL2 is separated from the actual position of the foot PL1. Therefore, the position of the target person P1's head PH1 was detected with good accuracy, but the position of the foot PL1 was not detected with good accuracy.

[0040] In step ST2, the distance and direction of movement of foot PL1 are determined by comparing positions DL1 and DL2. The distance between positions DL1 and DL2 is the distance of foot PL1. The direction of movement of foot PL1 is diagonal, extending in the positive X-axis and positive Z-axis directions, and includes the vertical and horizontal directions.

[0041] Similarly, the distance and direction of movement of head PH1 are determined by comparing positions DH1 and DH2. The distance between positions DH1 and DH2 is the distance of movement of head PH1. The direction of movement of head PH1 is the horizontal direction extending approximately in the positive X-axis direction.

[0042] In step ST3, it is determined whether only the distance traveled by foot PL1 exceeded a predetermined value, and whether only foot PL1 moved in the vertical direction. The distance traveled by foot PL1 is the distance between positions DL1 and DL2, and it exceeded the predetermined value, while the distance traveled by head PH1 is the distance between positions DH1 and DH2, and it did not exceed the predetermined value. Therefore, only the distance traveled by foot PL1 exceeded the predetermined value. As described above, since foot PL1 also moved in the vertical direction, while head PH1 moved horizontally, only foot PL1 moved in the vertical direction. Therefore, it is determined that only the distance traveled by foot PL1 exceeded the predetermined value, and only foot PL1 moved in the vertical direction (step ST3: YES).

[0043] In step ST4, it is assumed that foot PL1 is hidden by an obstacle. In reality, foot PL1 is hidden by obstacles OB1 and OB2.

[0044] In step ST5, the position DL2 of foot PL1 in the current frame image FR2, which was detected in step ST1, is corrected to the position DL21 of foot PL1 based on the skeleton of the detected subject P1. Specifically, a skeleton model SK1 is estimated from the skeleton of the detected subject P1 from the head to above the knee, which is contained within the bounty box BB1. The skeleton model SK1 is superimposed on the portion of the current frame image FR2 that represents the detected subject P1. The midpoint of both feet of the skeleton model SK1 is corrected to the position DL21 of the detected subject P1's foot PL1. This corrects position DL2 to position DL21. Position DL21 is almost the same as the actual position of foot PL1. Therefore, by correcting the position of the detected subject P1's foot PL1, detection can be performed with good accuracy.

[0045] <Second specific example of the detection method> Next, with reference to Figure 7, a second specific example of the detection method by the detection system 10 will be described.

[0046] In this specific example, as shown in Figure 7, the obstacle OB3 and the subject P2 whose posture is changing were imaged moment by moment, and the detection method of the detection system 10 was applied to these multiple images. The obstacle OB3 is a shelf. Only a portion of the upper part of the subject P2's legs is hidden by the obstacle OB3. Figure 7 shows the previous frame image FR11 and the current frame image FR12. The current frame image FR12 was captured at a time t after the previous frame image FR11 was captured.

[0047] In step ST1, a bounty box BB11, which represents the area of ​​the person to be detected P2, is generated in the previous frame image FR11. The foot detection unit 1 detects the midpoint of the lower side of the rectangle represented by the bounty box BB11 as the position DL11 of the foot PL2 of the person to be detected P2. The upper body detection unit 2 detects the midpoint of the upper side of the rectangle represented by the bounty box BB11 as the position DH11 of the head PH2 of the person to be detected P2. This detected position DL11 is approximately the same as the actual position of the foot PL2, and this detected position DH11 is approximately the same as the actual position of the head PH2. Therefore, the positions of the foot PL2 and head PH2 of the person to be detected P2 can be detected with good accuracy.

[0048] Similarly, in the current frame image FR12, a bounty box BB12 is generated, which is the region representing the target person P2. The foot detection unit 1 detects the midpoint of the lower side of the rectangle represented by the bounty box BB12 as the position DL12 of the target person P2's foot PL2. The upper body detection unit 2 detects the midpoint of the upper side of the rectangle represented by the bounty box BB2 as the position DH12 of the target person P2's head PH2. This detected position DH12 is approximately the same as the actual position of the head PH2, and this detected position DL12 is approximately the same as the actual position of the foot PL2. Therefore, the positions of the target person P2's foot PL2 and head PH1 can be detected with good accuracy.

[0049] In step ST2, the distance and direction of movement of foot PL2 are determined by comparing positions DL11 and DL12. The distance between positions DL11 and DL12 is the distance of foot PL2, which is approximately zero. Therefore, the distance of foot PL2 is approximately zero, and the direction of movement of foot PL2 cannot be determined.

[0050] Similarly, the distance and direction of movement of head PH2 are determined by comparing positions DH11 and DH12. The distance between positions DH11 and DH12 is the distance of movement of head PH2, and it has a predetermined length. The distance of movement of head PH2 exceeds the predetermined value. The direction of movement of head PH2 is the vertical direction extending approximately in the positive Z-axis direction.

[0051] Step ST3 determines whether only the distance traveled by foot PL2 exceeds a predetermined value, and whether only foot PL2 moved in the vertical direction. As described above, the distance traveled by foot PL2 is approximately zero, so it does not exceed the predetermined value. The direction of movement of foot PL2 cannot be determined, and the direction of movement of head PH2 is vertical. Therefore, only foot PL2 did not move in the vertical direction. Thus, it is determined that only the distance traveled by foot PL2 did not exceed a predetermined value, and only foot PL2 did not move in the vertical direction (Step ST3: NO).

[0052] In step ST6, it is determined whether the distance traveled by foot PL2 and head PH2 exceeds a predetermined value, and whether foot PL2 and head PH2 have moved vertically. As described above, the distance traveled by foot PL2 is approximately zero, so it does not exceed the predetermined value. Also, the direction of movement of foot PL2 cannot be determined. It is determined that the distance traveled by foot PL2 and head PH2 exceeds a predetermined value, and that foot PL2 and head PH2 have not moved vertically (step ST6: NO).

[0053] Step ST8 determines whether only the distance traveled by the head PH2 exceeds a predetermined value. As described above, the distance traveled by the feet PL2 does not exceed the predetermined value, while the distance traveled by the head PH2 does. Therefore, it is determined that only the distance traveled by the head PH2 exceeds the predetermined value (Step ST8: YES).

[0054] In step ST9, it is estimated that the posture of the detected person P2 has changed, or that the head PH2 of the detected person P2 is hidden by an obstacle. As shown in Figure 7, in reality, only a portion of the upper part of the legs of the detected person P2 is hidden by the obstacle OB3, and the head PH2 is not hidden by the obstacle, while the posture of the detected person P2 has changed. Therefore, the above estimation result has a certain degree of validity, and its estimation accuracy is good. Furthermore, as mentioned in step ST1, the position of the feet PL2 and the head PH2 of the detected person P2 can be detected with good accuracy, so correction of the detected foot position is unnecessary.

[0055] <Third specific example of the detection method> Next, with reference to Figure 8, a third specific example of the detection method by the detection system 10 will be described.

[0056] In this specific example, as shown in Figure 8, the subject P3, who repeatedly sits down and stands up from an obstacle OB4 (a chair), was continuously imaged, and the detection method of the detection system 10 was applied to these multiple images. The legs of the subject P3 are hidden by the obstacle OB4.

[0057] In this specific example, the process proceeds in the same order as the second specific example of the detection method using the detection system 10 described above: step ST1, step ST2, step ST3, step ST6, step ST8, and step ST9.

[0058] In step ST1, a bounty box BB2 is generated in the current frame image FR22, which represents the area indicating the person to be detected P3. The foot detection unit 1 detects the midpoint of the lower side of the rectangle indicated by the bounty box BB2 as the position DL22 of the foot PL3 ​​of the person to be detected P3. Although the foot PL3 ​​of the person to be detected P3 is hidden by the obstacle OB4, it is in almost the same position as position DL22. The upper body detection unit 2 detects the midpoint of the upper side of the rectangle indicated by the bounty box BB2 as the position DH22 of the head PH3 of the person to be detected P3. This detected position DH22 is almost the same as the actual position of the head PH3. This detected position DL22 is almost the same as the actual position of the foot PL3. Therefore, the positions of the foot PL3 ​​and head PH1 of the person to be detected P3 can be detected with good accuracy.

[0059] In step ST9, it is estimated that the posture of the detected person P3 has changed, or that the head PH3 of the detected person P3 is hidden by an obstacle. As shown in Figure 8, in reality, the legs of the detected person P3 are hidden by obstacle OB4, but the head PH3 is not hidden by the obstacle. On the other hand, since the detected person P3 repeatedly sits and stands, the posture of the detected person P3 has changed. Therefore, the above estimation result has a certain degree of validity, and its estimation accuracy is good. Furthermore, as mentioned in step ST1, since the position of the feet PL3 ​​and the head PH3 of the detected person P3 can be detected with good accuracy, correction of the detected foot position is unnecessary.

[0060] (Other embodiments, etc.) The detection system according to the above embodiment may have the following hardware configuration. Figure 9 is a diagram showing an example of the hardware configuration included in the detection system. As described in the various embodiments above, the procedure of the detection method in the detection system can also take the form of a detection method.

[0061] The detection system 300 shown in Figure 9 includes a processor 301 and a memory 302, along with an interface 303. Each configuration of the detection system 10 described in the above-described embodiment (see Figure 1) is realized by the processor 301 reading and executing a program stored in the memory 302. In other words, this program is a control program that causes the processor 301 to function as the detection system 10 or as a part thereof.

[0062] The program described above, when loaded into a computer, includes a set of instructions (or software code) for causing the computer to perform one or more of the functions described in the embodiments. The program may be stored on a non-temporary computer-readable medium or a physical storage medium. Examples, but not limited to, include random-access memory (RAM), read-only memory (ROM), flash memory, solid-state drive (SSD) or other memory technologies, CD-ROM, digital versatile disc (DVD), Blu-ray® disc or other optical disc storage, magnetic cassette, magnetic tape, magnetic disk storage or other magnetic storage devices. The program may be transmitted over a temporary computer-readable medium or a communication medium. Examples, but not limited to, include temporary computer-readable medium or a communication medium that includes electrically, optically, acoustically, or otherwise propagating signals.

[0063] Furthermore, the program described above can be described as a control program that causes the detection system 10 to execute such a detection method.

[0064] It should be noted that the present invention is not limited to the embodiments described above, and can be modified as appropriate without departing from the spirit of the invention. Furthermore, the present invention may be implemented by combining the above embodiments or examples thereof as appropriate.

[0065] In this embodiment, one example of the detection method involves detecting the position of the subject's head. However, it is also possible to detect the position of at least a part of the upper body, such as the torso or the entire upper body.

[0066] Furthermore, in one example of the detection method by the detection system 10 according to the embodiment, steps ST1 to ST9 were performed, but as shown in Figure 10, steps ST1, ST2, ST31, ST32, ST33, ST4, ST5, ST7, and ST9 may also be performed. In step ST31, it is determined whether at least one of the distance traveled by the feet and the distance traveled by the head exceeds a predetermined value. In step ST32, it is determined whether the distance traveled by the feet exceeds a predetermined value and whether the feet have moved in the vertical direction. In step ST33, it is determined whether the head has moved in the same direction and by the same amount as the feet. In other words, it is determined whether the head has moved in the vertical direction and whether the distance traveled by the head and the distance traveled by the feet are approximately the same. [Explanation of Symbols]

[0067] 10,300 detection systems 1 Foot detection unit 2. Upper body detection unit 3 Estimation part 4. Correction Unit 301 Processor 302 memory 303 Interface BB1, BB2, BB3, BB11, BB12 Bounty Box P1, P2, P3: Individuals subject to detection PH1, PH2, PH3 head PL1, PL2, PL3 feet BB1, BB2, BB3 Bounty Box DH1, DH2, DH11, DH12, DH22 (position of detected head) DL1, DL2, DL11, DL12, DL22 (location of detected feet) Obstacles: OB1, OB2, OB3, OB4 F1 Floor FR1, FR11 front frame images FR2, FR12, FR22 Current Frame Images SK1 Skeleton Model ST1, ST2, ST3, ST31, ST32, ST33, ST4, ST5, ST6, ST7, ST8, ST9 Step t period

Claims

1. A foot detection unit that detects the position of the feet of the person being detected, An upper body detection unit that detects the position of at least a part of the upper body of the person to be detected, The system includes an estimation unit that estimates the state of the detected subject based on the distance traveled by the feet and the distance traveled by at least a part of the upper body, calculated using the detected foot position and the detected position of at least a part of the upper body. If only the distance traveled by the foot exceeds a predetermined value, and only the foot moves in the vertical direction, the estimation unit estimates that at least a part of the lower body of the person being detected is hidden by an obstacle. Detection system.

2. If the distance traveled by the feet and the distance traveled by at least a part of the upper body exceed a predetermined value, and the feet and at least a part of the upper body move vertically, the estimation unit estimates that the person being detected is ascending or descending stairs, or that the person being detected is jumping. The detection system according to claim 1.

3. If the distance traveled by at least a portion of the upper body exceeds a predetermined value, the estimation unit estimates that the posture of the detected person has changed, or that at least a portion of the upper body of the detected person is hidden by an obstacle. The detection system according to claim 1.

4. It also includes a correction unit, If the estimation unit estimates that at least a portion of the lower body of the person being detected is hidden by an obstacle, the correction unit corrects the detected foot position to the foot position based on the skeletal structure of the person being detected. The detection system according to claim 1.

5. A detection method using a detection system, A step to detect the position of the feet of the person to be detected, The steps include detecting the location of at least a portion of the upper body of the person to be detected, The process includes the step of estimating the state of the person being detected based on the distance traveled by the feet and the distance traveled by at least a part of the upper body, calculated using the detected foot position and the detected position of at least a part of the upper body. In the estimation step described above, if only the distance traveled by the foot exceeds a predetermined value, and only the foot moves in the vertical direction, it is estimated that at least a part of the lower body of the person being detected is hidden by an obstacle. Detection method.

6. In the computer operating in the detection system, A step to detect the position of the feet of the person to be detected, The steps include detecting the location of at least a portion of the upper body of the person to be detected, The system is made to perform the step of estimating the state of the detected subject based on the distance traveled by the feet and the distance traveled by at least a part of the upper body, calculated using the detected foot position and the detected position of at least a part of the upper body. In the estimation step described above, if only the distance traveled by the foot exceeds a predetermined value, and only the foot moves in the vertical direction, it is estimated that at least a part of the lower body of the person being detected is hidden by an obstacle. program.

Images