Detection system, detection method, program, and detection module

Abstract

To provide a detection system that detects a state such as an abnormality of an object by a virtual area or a virtual volume calculated from pixels selected at a specific distance from a distance image.SOLUTION: A detection system includes: an imaging unit (8) that acquires a distance image representing a distance to a target object (4) in time series; and a processing unit (processing apparatus 12, processing part 64) that detects a state of the target object (4) by dividing pixels included in the distance image into two or more blocks by the perspective relationship and comparing ratios of pixels included in each block. Furthermore, the processing unit (processing apparatus 12, processing part 64) compares two or more front and back distance images between frames and detects a change in the state of the target object (4) from a difference.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a detection technology used, for example, to detect the state of an object such as a person. [Background technology]

[0002] A ToF camera (Time-of-Flight Camera) is a camera that can measure three-dimensional information (distance image) from an object by shining light on it and using the arrival time of the reflected light.

[0003] Regarding detection technology using this ToF camera, it is known that a difference image is obtained from a captured image using background subtraction processing, the head is estimated from a human object contained in this difference image, the distance between the head and the floor of the target space is calculated to determine the posture of the person, and the behavior of the person is detected from the posture and object position information (for example, Patent Document 1).

[0004] Regarding detection of an abnormality in an object, it is known to measure the time that the object remains stationary, and if this time exceeds a threshold, to determine that an abnormality has occurred (for example, Patent Document 2).

[0005] Regarding abnormality monitoring, it is known to monitor the change over time in the distance of a measurement point in any one area in a distance image, and to recognize an abnormality if this change over time exceeds a certain range (for example, Patent Document 3).

[0006] Regarding detection of a moving object, it is known to calculate a movement vector and a volume of an object in a detection space from a distance image, and to detect the detection target based on the movement vector and the volume (for example, Patent Document 4). [Prior art documents] [Patent documents]

[0007] [Patent Document 1] JP 2015-130014 A [Patent Document 2] JP 2008-052631 A [Patent Document 3] JP 2019-124659 A [Patent Document 4] JP 2022-051172 A Summary of the Invention [Problem to be solved by the invention]

[0008] For example, when the object to be detected for its behavior or other status is a human, there are issues such as attribute information such as portraits, information regarding privacy, etc., which should be given equal or higher priority than obtaining status information such as anomaly detection. Even if images taken with a general camera can detect anomalies, it cannot protect personal information such as privacy.

[0009] In contrast, distance images obtained by ToF cameras can prevent the disclosure of privacy and personal information, even if the target is a human. However, distance images are three-dimensional information that includes range and distance information of the target, and it is not easy to detect the state of the target from this three-dimensional information.

[0010] The inventors of the present disclosure have discovered that by selecting pixels at a specific distance from a distance image representing the distance between an object and a sensor, it is possible to detect conditions such as abnormalities in the object using the selected image.

[0011] In view of the above problems and findings, an object of the present disclosure is to detect conditions such as abnormalities in an object using a virtual area or virtual volume calculated from pixels selected at a specific distance from a distance image. [Means for solving the problem]

[0012] In order to achieve the above-mentioned objective, according to one aspect of the detection system disclosed herein, the system includes an imaging unit that acquires distance images representing the distance to an object in time series, and a processing unit that detects the state of the object by dividing pixels included in the distance images into two or more blocks based on perspective and comparing the ratio of pixels included in each block.

[0013] In this detection system, the processing unit may compare two or more front and rear distance images and detect a change in state of the object from the difference therebetween.

[0014] In this detection system, the processing unit may compare the pixels between frames of the range image.

[0015] In this detection system, the processing unit may calculate a virtual area and / or a virtual volume of the object using pixels included in the block, and detect a change in the state of the object by comparing the virtual area between two or more front and rear positions or comparing the volume between two or more front and rear positions.

[0016] In this detection system, the processing unit may compare coordinates of pixels contained in two or more of the distance images, virtual area images, or virtual volume images, and detect a change in the state of the object from a difference in the coordinates between before and after.

[0017] In this detection system, the coordinates may include any of a singular point, a centroid point, or a vertex included in the distance image, the virtual area image, or the virtual volume image.

[0018] This detection system may further include an information presenting unit that presents any one or more of the distance image, the virtual area or virtual volume, and status information indicating a status of the object.

[0019] In order to achieve the above-mentioned object, according to one aspect of the detection method disclosed herein, the method includes a step in which an imaging unit acquires distance images representing the distance to an object in a time series, a step in which a processing unit detects the state of the object by dividing the pixels included in the distance images into two or more blocks based on perspective and comparing the ratio of pixels included in each block, and a step in which a virtual area or virtual volume for each block is calculated for at least each state of the object using the pixels included in each block.

[0020] This detection method may include a step in which the processing unit compares two or more front and rear distance images and detects a change in state of the object from the difference between the images.

[0021] In this detection method, the processing unit may include a step of calculating a virtual area and / or a virtual volume of the object using pixels included in the block, and detecting a change in the state of the object by comparing the virtual area between two or more before and after between frames, or comparing the volume between two or more before and after between frames.

[0022] In order to achieve the above-mentioned objective, according to one aspect of the program of the present disclosure, the program is executed by a computer, and causes the computer to perform the following functions: acquiring a distance image representing the distance to an object in time series; and detecting the state of the object by dividing pixels contained in the distance image into two or more blocks based on perspective and comparing the ratio of pixels contained in each block.

[0023] This program may cause the computer to execute the following functions: a function of acquiring distance images representing the distance to an object in time series; a function of detecting the state of the object by dividing the pixels contained in the distance images into two or more blocks based on perspective and comparing the ratio of pixels contained in each block; and a function of calculating a virtual area or virtual volume for each block using the pixels contained in each block, for at least each state of the object.

[0024] The program may cause the computer to execute a function of comparing two or more front and rear distance images and detecting a change in state of the object from the difference between the images.

[0025] In order to achieve the above-mentioned objective, according to one aspect of the detection module of the present disclosure, the detection module includes an imaging unit that acquires distance images representing the distance to an object in time series, and a processing unit that detects the state of the object by dividing pixels included in the distance images into two or more blocks based on perspective and comparing the ratio of pixels included in each block.

[0026] In this detection module, the processing unit may compare two or more front and rear distance images and detect a change in state of the object from the difference therebetween.

[0027] In this detection module, the processing unit may calculate a virtual area and / or a virtual volume of the object using pixels included in the block, and detect a change in the state of the object by comparing the virtual area between two or more previous and subsequent images, or by comparing the volumes between two or more previous and subsequent images between frames. Effect of the Invention

[0028] According to the present disclosure, any of the following effects can be obtained. (1) The pixels contained in the distance image are divided into two or more blocks based on perspective, and a virtual area or virtual volume is calculated using the pixels in each block. The ratios of each virtual area or virtual volume are then compared, making it possible to detect the state of the object easily and with high accuracy.

[0029] (2) Since the state of the object is detected based on the ratio of the virtual area or virtual volume of each block, if the object is, for example, a human, information other than the state of the object, such as attribute information such as gender, can be omitted. This reduces the amount of information used in the detection process, reduces the load on information processing, and speeds up processing.

[0030] (3) The state of an object can be detected by comparing frames that represent a virtual area or volume divided into blocks from a range image. [Brief description of the drawings]

[0031] [Figure 1] FIG. 1 is a diagram showing a detection system according to a first embodiment. [Diagram 2] FIG. 2 is a diagram illustrating an example of the detection information database according to the first embodiment. [Diagram 3] FIG. 3 is a flowchart of a process of detecting a state according to the first embodiment. [Figure 4] 4A is a diagram showing state A of the object, FIG. 4B is a diagram showing state B, and FIG. 4C is a diagram showing state C. In FIG. [Diagram 5] FIG. 5A is a diagram showing a distance image of the object in state B (FIG. 4B), and FIG. 5B is a diagram showing a virtual area image. [Figure 6] A of Figure 6 is a diagram showing a virtual area image of the first block (B of Figure 5), B of Figure 6 is a diagram showing a virtual area image of the second block (B of Figure 5), and C of Figure 6 is a diagram showing a virtual area image of the third block (B of Figure 5). [Figure 7] FIG. 7A is a diagram showing a distance image of the object in state C (C in FIG. 4), and FIG. 7B is a diagram showing a virtual area image. [Figure 8] A of FIG. 8 is a diagram showing a virtual area image of the first block (B of FIG. 7), B of FIG. 8 is a diagram showing a virtual area image of the second block (B of FIG. 7), and C of FIG. 8 is a diagram showing a virtual area image of the third block (B of FIG. 7). [Figure 9] FIG. 9 is a diagram illustrating an example of the detection information database according to the second embodiment. [Figure 10] FIG. 10 is a flowchart illustrating a processing procedure of the detection system according to the second embodiment. [Figure 11]FIG. 11A is a diagram showing a distance image of the object in state B (FIG. 4B), and FIG. 11B is a diagram showing the first block, the virtual volumetric image. [Figure 12] A of Figure 12 is a diagram showing a virtual volume image of the first block (B of Figure 11), B of Figure 12 is a diagram showing a virtual volume image of the second block (B of Figure 11), and C of Figure 12 is a diagram showing a virtual volume image of the third block (B of Figure 11). [Figure 13] FIG. 13A is a diagram showing a distance image of the object in state C (C in FIG. 4), and FIG. 13B is a diagram showing a virtual volumetric image. [Figure 14] A of Figure 14 is a diagram showing a virtual volume image of the first block (B of Figure 13), B of Figure 14 is a diagram showing a virtual volume image of the second block (B of Figure 13), and C of Figure 14 is a diagram showing a virtual volume image of the third block (B of Figure 13). [Figure 15] FIG. 15 is a diagram illustrating a detection module according to an embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0032] First Embodiment Fig. 1 is a diagram showing a detection system 2 according to a first embodiment. The configuration shown in Fig. 1 is an example, and the present disclosure is not limited to such a configuration.

[0033] This detection system 2 is a system that detects the state of an object 4 by using a distance image Gd acquired from the object 4. The object 4 is a moving object, and if the object 4 whose state is to be detected is, for example, a human, behavior information indicating the movements of the head 4a, torso 4b, limbs 4c, etc. appears in the distance image Gd (e.g., FIG. 5).

[0034] The detection system 2 shown in Fig. 1 includes a light emitting unit 6, an imaging unit 8, a control unit 10, a processing device 12, etc. The light emitting unit 6 receives a drive output from a light emitting drive unit 14 under the control of the control unit 10 to emit light intermittently, and irradiates the object 4 with the light Li. Reflected light Lf is obtained from the object 4 that receives this light Li. The time from the point in time when the light Li is emitted to the point in time when the reflected light Lf is received represents the distance.

[0035] The imaging unit 8 is an example of an imaging unit of the present disclosure, and includes a light receiving unit 16 and a distance image generating unit 18. The light receiving unit 16 receives reflected light Lf from the object 4 in time series in synchronization with the emission of light by the light emitting unit 6 under the control of the control unit 10, and outputs a light reception signal. The distance image generating unit 18 receives the light reception signal from the light receiving unit 16 and generates a distance image Gd in time series. Therefore, the imaging unit 8 obtains a distance image Gd representing the distance between the object 4 and the imaging unit 8 in frame units in time series.

[0036] The control unit 10 is, for example, a computer, and executes an imaging program to control the light emission of the light emitting unit 6 and the imaging of the imaging unit 8. The light emitting unit 6, the imaging unit 8, the control unit 10, and the light emission driving unit 14 are an example of the detection module 20 of the present disclosure, and can be configured, for example, as a discrete element in one package, such as a one-chip IC. This detection module 20 constitutes the above-mentioned ToF camera.

[0037] The processing device 12 is an example of a processing unit of the present disclosure. In this embodiment, the processing device 12 is, for example, a personal computer equipped with a communication function, and includes a processor 22, a storage unit 24, an input / output unit (I / O) 26, an information presentation unit 28, a communication unit 30, and the like.

[0038] The processor 22 executes an operating system (OS) in the storage unit 24 and a detection program of the present disclosure, and executes information processing required for detecting the state of the target object 4.

[0039] The storage unit 24 stores an OS, a detection program, and detection information databases 32-1 (FIG. 2) and 32-2 (FIG. 9) used for information processing required for status detection. The storage unit 24 includes memory elements such as a ROM (Read-Only Memory) and a RAM (Random-Access Memory). The input / output unit 26 inputs and outputs information under the control of the processor 22.

[0040] An operation input unit (not shown) is connected to the input / output unit 26 in addition to the information presentation unit 28. The input / output unit 26 receives operation input information by user operation or the like, and obtains output information based on information processing by the processor 22.

[0041] The information presenting unit 28 is an example of an information presenting unit in the present disclosure, and is configured, for example, by an LCD (Liquid Crystal Display) etc. Under the control of the processor 22, the information presenting unit 28 presents image information Dg including one or more of a distance image Gd, a virtual area Vs described below, and status information Sx representing the status of the object 4. The operation input unit may be, for example, a touch panel provided on the screen of the LCD of the information presenting unit 28.

[0042] The communication unit 30 is controlled by the processor 22 to be connected to information devices such as a communication terminal (not shown) via a public line or the like via wired or wireless connection, and can present status information of the object 4, etc. to the communication terminal.

[0043] <Control by the control unit 10> The control by the control unit 10 includes processes such as a) emission control of light Li, b) reception control of reflected light Lf, c) generation process of distance image Gd, and d) transmission control of distance image Gd.

[0044] a) Light emission control of light Li The control unit 10 controls the light emission of the light-emitting unit 6 to generate reflected light Lf from the object 4. To cause the light-emitting unit 6 to emit light intermittently, a drive signal is provided from the light-emitting drive unit 14 to the light-emitting unit 6 under the control of the control unit 10. This causes the light-emitting unit 6 to emit intermittent light Li, which is irradiated onto the object 4.

[0045] b) Light reception control of reflected light Lf In order to receive the reflected light Lf from the object 4 that has received the light Li, the control unit 10 controls the light receiving unit 16. As a result, the reflected light Lf from the object 4 is received by the light receiving unit 16. In response to this reception, a light receiving signal is generated from the light receiving unit 16 and provided to the distance image generating unit 18.

[0046] c) Generation process of distance image Gd Distance image generator 18 generates a distance image Gd using the light reception signals under the control of controller 10. This distance image Gd is composed of pixels gi having different light reception distances depending on the unevenness of object 4 and the distance.

[0047] d) Transmission control of distance image Gd The control unit 10 receives the distance image Gd from the distance image generating unit 18, and sends this distance image Gd to the processing device 12 on a frame-by-frame basis.

[0048] <Information processing by the processing device 12> The information processing of the processing device 12 includes processes such as e) acquiring a distance image Gd, f) partitioning the distance image Gd, g) generating a virtual area image Gs, h) calculating the virtual area for each block, i) calculating the ratio of the blocks, j) detecting changes in the distribution of distance information, k) detecting the presence and status of an object 4, l) presenting the distance image, virtual area image, status information, and judgment information, and m) generating and updating a detection information database 32-1.

[0049] e) Acquisition of distance image Gd The processing device 12 acquires distance images Gd in time series under the control of the processor 22. The distance images Gd are acquired on a frame-by-frame basis.

[0050] f) Segmentation of the range image Gd Under the control of the processor 22, the processing device 12 divides the pixels gi included in the distance image Gd into two or more blocks based on the perspective relationship, for example into a first block, a second block, and a third block.

[0051] g) Generation of virtual area image Gs The processing device 12, under the control of the processor 22, generates a virtual area image Gs divided into blocks from the distance image Gd divided into blocks.

[0052] h) Calculation of virtual area Vs for each block The processing device 12 calculates virtual areas Vs1, Vs2, Vs3 for the first block, the second block, and the third block using pixels gi included in the first block, the second block, and the third block, at least for each state of the object 4.

[0053] If pixel gi included in the first block is g1, pixel gi included in the second block is g2, pixel gi included in the third block is g3, and the conversion coefficient for converting pixel gi to area is k, then the virtual area Vs1 of the first block, the virtual area Vs2 of the second block, and the virtual area Vs3 of the third block can be expressed by Equation 1, Equation 2, and Equation 3.

[0054] Vs1=k·g1 (Formula 1) Vs2=k·g2 (Formula 2) Vs3=k g3 (Equation 3)

[0055] i) Calculation of the ratios R11, R12, and R13 for each block The processor 12 calculates the ratios R11, R12 of the first block, the second block, and the third block. The ratios R11, R12, and R13 of each block based on the virtual area Vs1 of the first block can be expressed by Equation 4, Equation 5, and Equation 6.

[0056] R11=Vs1 / Vs1=1 (Formula 4) R12=Vs2 / Vs1=g2 / g1 (Formula 5) R13=Vs3 / Vs1=g3 / g1 (Formula 6)

[0057] The state of the object 4 can be detected using the ratios R11, R12, and R13 of each block.

[0058] Moreover, it may be possible to detect whether the object 4 is normal or abnormal by using status information indicating the status of the object 4 detected using the ratios R11, R12, and R13 of each block.

[0059] j) Detection of changes in the distribution of distance information The processor 12 performs inter-frame comparison using the ratios R11, R12, R13 of each block, and detects a variation in the distribution of distance information in the distance image Gd from the difference ΔR between the ratios R11, R12, R13.

[0060] k) Detection of the presence and state of object 4 The processing device 12 obtains a variation amount M that indicates the degree of variation in the distance information distribution detected from the distance image Gd, and compares this variation amount M with a threshold value Mth for detecting an abnormality to detect the presence and state of the object 4. In this case, since the state is detected based on the presence or absence of behavior of the object 4, if the variation amount M is greater than the threshold value Mth (M>Mth), normality is detected, and if the variation amount M is equal to or less than the threshold value Mth (M≦Mth), an abnormality is detected.

[0061] A combination of the ratios R11, R12, and R13 of each block and the above-mentioned j) detection of variation in distance information distribution may be used to detect the state, normality, or abnormality of the object 4. In this case, for example, the normality or abnormality of the object 4 may be detected when a specific state a changes to a specific state b.

[0062] l) Presentation of distance image, virtual area image, status information, and judgment information Under the control of the processor 22, the processing device 12 presents the distance image Gd, the virtual area for each block, the status information, and the judgment information on the information presenting unit 28. According to this presented information, the presence, status, and judgment information showing whether the status of the object 4 is normal or abnormal can be visually confirmed.

[0063] For this information presentation, the processing device 12 can wirelessly connect the communication unit 30 to the corresponding communication terminal under the control of the processor 22, and present the same information as that presented by the information presentation unit 28 to the corresponding communication terminal.

[0064] m) Creation and updating of detection information database 32-1 The processing device 12 generates and updates the detection information database 32 - 1 stored in the storage unit 24 under the control of the processor 22 .

[0065] <Detection Information Database 32-1> In this detection information database 32-1, control information of the control unit 10 for detecting the state of the object 4, control information of the processing device 12, processing information of the distance image Gd, state detection information of the object 4, and the like are stored.

[0066] FIG. 2 shows a detection information database 32-1 (hereinafter simply referred to as "database 32-1") that stores detection information.

[0067] The database 32-1 is an example of a database disclosed in the present disclosure, and includes a date and time information section 34, a light emission information section 36, a light reception information section 38, a distance image section 40, a section information section 42, a block image information section 44, a virtual area / ratio section 46, a distance information distribution section 48, a fluctuation amount information section 49, a status information section 50, a detection information section 52, a presentation information section 54, and a history information section 56.

[0068] The date and time information section 34 stores date and time information indicating the date and time when the state of the target object 4 was detected.

[0069] The light emission information section 36 stores specification information of the light emitting elements of the light emitting section 6, light emission timing, light emission control information, and the like.

[0070] The light receiving information section 38 stores specification information of the light receiving element of the light receiving section 16, light receiving timing, light receiving control information, and the like.

[0071] Distance image section 40 stores image information representing distance image Gd that distance image generating section 18 generates using received light information.

[0072] The division information section 42 stores division information such as perspective information that indicates the perspective relationship for dividing the distance image Gd into, for example, a first block, a second block, and a third block.

[0073] A first block section 44-1, a second block section 44-2, and a third block section 44-3 are set in the block image information section 44. Image information representing image information Gd1 corresponding to the first block is stored in the first block section 44-1, image information Gd2 corresponding to the second block is stored in the second block section 44-2, and image information Gd3 corresponding to the third block is stored in the third block section 44-3.

[0074] The virtual area / ratio section 46 stores, for example, image information representing the virtual area Vs1 of the first block, the virtual area Vs2 of the second block, and the virtual area Vs3 of the third block, and ratio information representing the ratios R11, R12, and R13 of the first, second, and third blocks based on the virtual area Vs1 of the first block.

[0075] Distance information distribution section 48 stores distribution information representing the distribution of distance information of the first block, the second block, and the third block.

[0076] The variation information section 49 stores variation information that indicates changes in behavior, such as repetition of a motion, of the object 4. This variation across blocks may also be included.

[0077] The state information section 50 stores state information that is associated with the fluctuation amount information section 49 and indicates the state of the target object 4 .

[0078] The detection information section 52 stores detection information indicating whether the state of the object 4 is normal or abnormal, determined from the distance information distribution or the like.

[0079] The presentation information section 54 stores presentation information such as the distance image Gd presented on the information presentation section 28.

[0080] The history information section 56 stores information indicating a processing history including state detection and the like.

[0081] <Processing procedure for detecting the state of object 4> This processing procedure is a processing procedure for detecting a state using the distance image Gd acquired by the detection module 20 through imaging.

[0082] 3 shows a processing procedure for detecting the state of the object 4. This processing procedure includes imaging (S101), acquiring a distance image Gd (S102), block processing of the distance image Gd (S103), calculating virtual areas Vs1, Vs2, and Vs3 for each block (S104), calculating block ratios R11, R12, and R13 (S105), acquiring variation information of the distance information distribution (S106), judging the amount of variation M against a threshold value (S107), detecting an abnormality (S108), detecting normality (S109), and presenting information (S110, S111).

[0083] According to this processing procedure, the imaging unit 8 images the object 4 under the control of the control unit 10 (S101). In the imaging unit 8, the distance image generation unit 18 acquires a light reception signal from the light receiving unit 16 and generates a distance image Gd representing the object 4 from the light reception signal.

[0084] Under the control of the processor 22, the processing device 12 acquires a distance image Gd from the control unit 10 of the detection module 20 (S102).

[0085] The processing device 12 executes block processing of the distance image Gd through information processing by the processor 22, and divides the distance image Gd into a first block 60-1, a second block 60-2, and a third block 60-3 (B in FIG. 5) (S103).

[0086] The processing device 12 uses information processing by the processor 22 to calculate virtual areas Vs1, Vs2, and Vs3 for each block using the block-processed distance image Gd (S104).

[0087] The processing device 12 calculates the block ratios R11, R12, and R13 through information processing by the processor 22 (S105).

[0088] The processing device 12 uses the block ratios R11, R12, and R13 through information processing by the processor 22 to obtain variation information of the distance information distribution for each state through comparison calculations (S106).

[0089] The processing device 12 acquires the amount of fluctuation M through information processing by the processor 22, and compares the amount of fluctuation M with a threshold value Mth to determine which is larger (S107).

[0090] If M≦Mth (YES in S107), the processing device 12 determines that the object 4 has no behavior and performs abnormality detection (S108). If M>Mth (NO in S107), the processing device 12 determines that the object 4 has behavior and performs normality detection (S109).

[0091] The processing device 12 executes information presentation (S110, S111) under the control of the processor 22, and in the information presentation related to S110, information such as detection information indicating an abnormality and a distance image Gd is presented. In addition, in the information presentation related to S111, information such as detection information indicating normality and a distance image Gd is presented.

[0092] If there is an abnormality in the object 4, this process is terminated, and if there is a normal state, the process returns from S111 to S101 and the state detection continues.

[0093] <Subject 4 behavior> The object 4 to be detected for status is, for example, a human, and the distance image Gd obtained from the detection module 20 is a collection of pixels gi that represent the distance between the light receiving unit 16 and the object 4. Therefore, in order to simulate the detection of the status of the object 4, an actual image of the object 4 is shown as an example in FIG.

[0094] This behavior includes, for example, state A (A in FIG. 4), state B (B in FIG. 4), and state C (C in FIG. 4).

[0095] As shown in FIG. 4A, state A shows the object 4 standing up, as viewed from the light receiving unit 16 above the head.

[0096] As shown in FIG. 4B, state B shows the target object 4 in a crouching state after transitioning from state A, as viewed from the light receiving unit 16 above the head.

[0097] As shown in Fig. 4C, state C shows the crouching state of the target object 4, which has transitioned from state B, as seen from the light receiving unit 16 above the head. The dashed lines show the movement of the limbs 4c, specifically, the movement of the left arm.

[0098] In the behavior of this object 4, as a simulation of state detection, if the behavior of the object 4 stops at state B, and there is no change even after a certain period of time has passed, it is determined to be in an abnormal state. On the other hand, if the object 4 changes its behavior, such as transitioning from state B to state C, it is determined to be in a normal state.

[0099] <Behavior of object 4 and detection of its status> This state detection is state detection using the fluctuation amount information stored in the fluctuation amount information section 49 of the database 38-1 described above.

[0100] Comparing at least the frames before and after the amount of change in the object 4 can be used to detect the state of the object 4 and its periodicity. The amount of change information unit 49 may store tolerance information indicating a tolerance for the detected periodicity, and an abnormal state of the object 4 may be determined by a amount of change exceeding this tolerance. The tolerance may include the elapsed time, the amount of change, and the number of changes. For example, when the behavior of the left arm of the limbs of the object 4 is stopped, the behavior of the right arm moving may be determined to be an abnormal state. By comparing the transition and trajectory of the amount of change information recorded in the amount of change information unit 49, the order of the state of the object 4 can also be detected. For example, when the order of behavior detected from the object 4 is different from the state before the behavior, it can be determined to be an abnormal state by setting a tolerance value for the range of the behavior. For example, if the behavior of the left arm of the object 4 transitions from state C to state A to state B as shown in FIG. 4 as the previous state, then if the behavior transitions from state C to state B to state A, this can be processed to determine that the behavior is different from the previous state and that this is an abnormal state, and the fluctuation amount information stored in the fluctuation amount information unit 49 can be effectively utilized.

[0101] <Distance image Gd-B in state B, first block 60-1, second block 60-2, and third block 60-3 of distance image Gd-B, virtual area images Gs1-B, Gs2-B, and Gs3-B for each block, virtual areas Vs1-B, Vs2-B, and Vs3-B, and ratios R11-B, R12-B, and R13-B>

[0102] Fig. 5A shows a distance image Gd-B on frame 58-1 obtained from state B (Fig. 4B) of object 4. This distance image Gd-B includes pixels gi corresponding to first block 60-1, pixels gi corresponding to second block 60-2, and pixels gi corresponding to third block 60-3.

[0103] 5B shows virtual area images Gs1-B, Gs2-B, and Gs3-B generated from distance image Gd-B. Virtual area image Gs1-B represents a portion of object 4 and its virtual area calculated from pixel gi included in first block 60-1 in state B. Virtual area image Gs2-B represents a portion of object 4 and its virtual area calculated from pixel gi included in second block 60-2 in state B. Virtual area image Gs3-B represents a portion of object 4 and its virtual area calculated from pixel gi included in third block 60-3 in state B.

[0104] 6A shows a virtual area image Gs1-B corresponding to the first block 60-1 on the frame 58-3 separated from the virtual area image Gs-B. The virtual area Vs1-B of the first block 60-1 can be calculated by the pixels gi included in the virtual area image Gs1-B. In this case, the ratio R11 is R11-B.

[0105] 6B shows a virtual area image Gs2-B corresponding to the second block 60-2 on the frame 58-4 separated from the virtual area image Gs-B. The virtual area Vs2-B of the second block 60-2 can be calculated by the pixels gi included in this virtual area image Gs2-B. In this case, the ratio R12 is R12-B.

[0106] 6C shows a virtual area image Gs3-B corresponding to the third block 60-3 on the frame 58-5 separated from the virtual area image Gs-B. The virtual area Vs3-B of the third block 60-3 can be calculated by the pixels gi included in this virtual area image Gs3-B. In this case, the ratio R13 is R13-B.

[0107] Fig. 7A shows a distance image Gd-C on frame 58-6 obtained from state C (C in Fig. 4) of object 4. This distance image Gd-C includes pixels gi corresponding to the first block 60-1, pixels gi corresponding to the second block 60-2, and pixels gi corresponding to the third block 60-3.

[0108] 7B shows virtual area images Gs1-C, Gs2-C, and Gs3-C generated from distance image Gd-C in which pixels gi included in virtual area image Gs-C are blocked on frame 58-7 based on perspective. Virtual area image Gs1-C shows a part of object 4 and its virtual area calculated from pixels gi included in first block 60-1 in state C. Virtual area image Gs2-C shows a part of object 4 and its virtual area calculated from pixels gi included in second block 60-2 in state C. Virtual area image Gs3-C shows a part of object 4 and its virtual area calculated from pixels gi included in third block 60-3 in state C.

[0109] 8A shows a virtual area image Gs1-C corresponding to a first block 60-1 on a frame 58-8 separated from the virtual area image Gs-C. The virtual area Vs1-C of the first block can be calculated by pixels gi included in the virtual area image Gs1-C. In this case, the ratio R11 is R11-C.

[0110] 8B shows a virtual area image Gs2-C corresponding to the second block 60-2 on the frame 58-9 separated from the virtual area image Gs-C. The virtual area Vs2-C of the second block can be calculated by the pixels gi included in this virtual area image Gs2-C. In this case, the ratio R12 is R12-C.

[0111] 8C shows a virtual area image Gs3-C corresponding to the third block 60-3 on the frame 58-10 separated from the virtual area image Gs-C. The virtual area Vs3-C of the third block can be calculated by the pixels gi included in this virtual area image Gs3-C. In this case, the ratio R13 is R13-C.

[0112] <Comparison and judgment of fluctuation information of distance information distribution in states B and C> The comparative calculation of the variation information of the distance information distribution in states B and C is to detect whether the object 4 is normal or abnormal. Comparing the ratios R11-B, R12-B, and R13-B shown in A, B, and C of Fig. 6 obtained from state B with the ratios R11-C, R12-C, and R13-C shown in A, B, and C of Fig. 8 obtained from state C, it is found that in state C, as shown in A of Fig. 8, the arm part of the limb 4c of the object 4 is added to the distance image Gd1-B of the first block 60-1, so that the virtual area Vs1-C is enlarged, and as shown in C of Fig. 8, the distance image Gd3-C of the third block changes and the virtual area Vs3-C is reduced.

[0113] In this case, the amount of fluctuation M is obtained from the fluctuation information of the distance information distribution in states B and C by the processing described above, and when the amount of fluctuation M is compared with the threshold value Mth, in states B and C, M>Mth is established, it is determined that the object 4 is behaving, and normal detection is performed.

[0114] In this case, the amount of fluctuation M is obtained from the fluctuation information of the distance information distribution in states B and C by the processing described above, and the amount of fluctuation M is compared with a threshold value Mth. If M≦Mth holds, it is determined that there is no behavior of the object 4 and an abnormality is detected.

[0115] <Advantages of the First Embodiment> According to the first embodiment, any one of the following effects can be obtained.

[0116] (1) The pixels gi included in the distance image Gd are divided into a first block 60-1, a second block 60-2 and a third block 60-3 based on the perspective relationship, and the virtual areas Vs1-B, Vs2-B, Vs3-B, Vs1-C, Vs2-C and Vs3-C for states B and C are calculated using the pixels gi for each of the first block 60-1, the second block 60-2 and the third block 60-3. The ratios R11-B, R12-B and R13-B for state B are compared with the ratios R11-C, R12-C and R13-C for state C, so that the state of the object 4 can be detected easily and with high accuracy.

[0117] (2) The state of the object 4 is detected based on the ratios R11-B, R12-B, R13-B of state B and the ratios R11-C, R12-C, R13-C of state C of the virtual areas Vs1-B, Vs2-B, Vs3-B, Vs1-C, Vs2-C, Vs3-C for each block. Therefore, if the object 4 is, for example, a human, attribute information such as gender and other information other than the object's state can be omitted. This reduces the amount of information used in the detection process, reduces the load on information processing, and speeds up processing.

[0118] (3) The state of the object 4 can be detected by comparing frames representing distance images Gd1-B, Gd2-B, and Gd3-B, which are divided into a first block 60-1, a second block 60-2, and a third block 60-3 from the distance image Gd, with frames representing distance images Gd1-C, Gd2-C, and Gd3-C.

[0119] Second Embodiment In the second embodiment, the state of the object 4 is detected by calculating virtual volumes Vv1, Vv2, and Vv3 of the object 4 divided into a first block 60-1, a second block 60-2, and a third block 60-3 from the distance image Gd.

[0120] <Detection system 2 according to the second embodiment> A detection system 2 according to the second embodiment has a common configuration to that shown in FIG. 1, and therefore a description thereof will be omitted.

[0121] <Control by the control unit 10 according to the second embodiment> Control by the control unit 10 in the second embodiment similarly includes processes such as a) emission control of light Li, b) reception control of reflected light Lf, c) generation process of distance image Gd, and d) transmission of distance image Gd.

[0122] <Information processing by the processing device 12 according to the second embodiment> The information processing of the processing device 12 includes processes such as n) acquiring a distance image Gd, o) partitioning the distance image Gd, p) generating a virtual volume image Gv, q) calculating the virtual volume for each block, r) calculating the ratio of the blocks, s) detecting changes in the distribution of distance information, t) detecting the presence and status of an object 4, u) presenting the distance image, virtual volume image, status information, and judgment information, and v) generating and updating a detection information database 32-1.

[0123] n) Acquisition of distance image Gd The processing device 12 acquires distance images Gd in time series under the control of the processor 22. The distance images Gd are acquired on a frame-by-frame basis.

[0124] o) Segmentation of the range image Gd Under the control of the processor 22, the processing device 12 divides the pixels gi included in the distance image Gd into two or more blocks based on the perspective relationship, for example into a first block, a second block, and a third block.

[0125] p) Generation of a virtual volume image Gv; Under the control of the processor 22, the processing device 12 generates a virtual volumetric image Gv for each block from the distance image Gd divided into blocks.

[0126] q) Calculation of virtual volume for each block The processing device 12 calculates virtual volumes Vv1, Vv2, Vv3 for the first block, the second block, and the third block using pixels gi included in the first block, the second block, and the third block, at least for each state of the object 4.

[0127] If pixel gi included in the first block is g1, pixel gi included in the second block is g2, pixel gi included in the third block is g3, and the conversion coefficient for converting pixel gi to volume is q, then the virtual volume Vv1 of the first block, the virtual volume Vv2 of the second block, and the virtual volume Vv3 of the third block can be expressed by Equation 7, Equation 8, and Equation 9.

[0128] Vv1=q·g1 (Formula 7) Vv2 = q·g2 ···(Equation 8) Vv3 = q·g3 ···(Equation 9)

[0129] r) Calculation of the ratios R11, R12, and R13 of each block The processing device 12 calculates the ratios R11 and R12 of the first block, the second block, and the third block. Based on the virtual volume Vv1 of the first block, the ratios R11, R12, and R13 of each block can be expressed by Equation 10, Equation 11, and Equation 12.

[0130] R11 = Vv1 / Vv1 = 1 ···(Equation 10) R12 = Vv2 / Vv1 = g2 / g1 ···(Equation 11) R13 = Vv3 / Vv1 = g3 / g1 ···(Equation 12)

[0131] The state of the object 4 can be detected using the ratios R11, R12, and R13 of each block.

[0132] Also, it may be possible to detect whether the object 4 is normal or abnormal using the state information representing the state of the object 4 detected using the ratios R11, R12, and R13 of each block.

[0133] s) Detection of fluctuations in the distance information distribution The processing device 12 performs a comparison between frames using the ratios R11, R12, and R13 of each block, and detects fluctuations in the distance information distribution in the distance image Gd from the difference ΔR between the ratios R11, R12, and R13.

[0134] t) Detection of the presence and state of the object 4 The processing device 12 obtains a variation amount M representing the degree of fluctuations in the distance information distribution detected from the distance image Gd, compares this variation amount M with a threshold value Mth for detecting an abnormality, and detects the presence and state of the object 4. In this case, since the state is detected based on the presence or absence of the behavior of the object 4, if the variation amount M is greater than or equal to the threshold value Mth (M ≥ Mth), normality is detected, and if the variation amount M is less than the threshold value Mth (M < Mth), an abnormality is detected.

[0135] A combination of the ratios R11, R12, and R13 of each block and the above-mentioned s) detection of variation in the distance information distribution may be used to detect the state, normality, or abnormality of the object 4. In this case, for example, the normality or abnormality of the object 4 may be detected when a specific state a changes to a specific state b.

[0136] u) Presentation of distance images, virtual volume images, status information, and judgment information Under the control of the processor 22, the processing device 12 presents the distance image Gd, the virtual volume for each block, the status information, and the judgment information on the information presenting unit 28. According to this presented information, the presence, status, and judgment information showing whether the status of the object 4 is normal or abnormal can be visually confirmed.

[0137] For this information presentation, the processing device 12 can wirelessly connect the communication unit 30 to the corresponding communication terminal under the control of the processor 22, and present the same information as that presented by the information presentation unit 28 to the corresponding communication terminal.

[0138] v) Creation and updating of detection information database 32-2 The processing device 12 generates and updates the detection information database 32 - 2 stored in the storage unit 24 under the control of the processor 22 .

[0139] <Detection Information Database 32-2> As in the first embodiment, this detection information database 32-2 stores control information of the control unit 10 for detecting the state of the object 4, control information of the processing device 12, processing information of the distance image Gd, state detection information of the object 4, and the like.

[0140] FIG. 9 shows a detection information database 32-2 (hereinafter simply referred to as "database 32-2") that stores detection information.

[0141] This database 32-2 is an example of a database of the present disclosure. In this database 32-2, the same parts as those in the database 32-1 are given the same reference numerals. The database 32-2 includes a date and time information section 34, a light emission information section 36, a light reception information section 38, a distance image section 40, a division information section 42, a block image information section 44, a virtual volume / ratio section 47, a distance information distribution section 48, a status information section 50, a detection information section 52, a presentation information section 54, and a history information section 56.

[0142] Date and time information section 34, light emission information section 36, light reception information section 38, distance image section 40, classification information section 42, The block image information section 44, distance information distribution section 48, state information section 50, detection information section 52, presentation information section 54, and history information section 56 are the same as those in the database 32-1, and therefore description thereof will be omitted.

[0143] The virtual volume / ratio section 47 stores, for example, image information representing the virtual volume Vv1 of the first block, the virtual volume Vv2 of the second block, and the virtual volume Vv3 of the third block, and ratio information representing the ratios R11, R12, and R13 of the first block, the second block, and the third block based on the virtual volume Vv1 of the first block.

[0144] <Processing procedure for detecting the state of object 4> This processing procedure is a processing procedure for detecting a state using the distance image Gd acquired by imaging with the detection module 20, similar to the first embodiment.

[0145] 10 shows a processing procedure for detecting the state of the object 4. This processing procedure includes imaging (S201), acquiring a distance image Gd (S202), block processing of the distance image Gd (S203), calculating virtual volumes Vv1, Vv2, and Vv3 for each block (S204), calculating block ratios R11, R12, and R13 (S205), acquiring variation information of the distance information distribution (S206), judging the amount of variation M against a threshold value (S207), detecting an abnormality (S208), detecting normality (S209), and presenting information (S210, S211).

[0146] According to this processing procedure, the imaging unit 8 images the object 4 under the control of the control unit 10 (S201). In the imaging unit 8, the distance image generation unit 18 acquires a light reception signal from the light receiving unit 16 and generates a distance image Gd representing the object 4 from the light reception signal.

[0147] Under the control of the processor 22, the processing device 12 acquires a distance image Gd from the control unit 10 of the detection module 20 (S202).

[0148] The processing device 12 executes block processing of the distance image Gd through information processing by the processor 22, and divides the distance image Gd into a first block 60-1, a second block 60-2, and a third block 60-3 (B in FIG. 5) (S203).

[0149] The processing device 12 uses information processing by the processor 22 to calculate virtual volumes Vv1, Vv2, and Vv3 for each block using the block-processed distance image Gd (S204).

[0150] The processing device 12 calculates the block ratios R11, R12, and R13 through information processing by the processor 22 (S205).

[0151] The processing device 12 uses the block ratios R11, R12, and R13 through information processing by the processor 22 to obtain variation information of the distance information distribution for each state through a comparison operation (S206).

[0152] The processing device 12 acquires the amount of fluctuation M through information processing by the processor 22, and compares the amount of fluctuation M with a threshold value Mth to determine which is larger (S207).

[0153] If M≦Mth (YES in S207), the processing device 12 determines that the object 4 has no behavior and performs abnormality detection (S208). If M>Mth (NO in S207), the processing device 12 determines that the object 4 has behavior and performs normality detection (S209).

[0154] The processing device 12 executes information presentation (S210, S211) under the control of the processor 22, and in the information presentation related to S210, information such as detection information indicating an abnormality and a distance image Gd is presented. In addition, in the information presentation related to S211, information such as detection information indicating normality and a distance image Gd is presented.

[0155] If there is an abnormality in the object 4, this process is terminated, and if there is a normal state, the process returns from S211 to S201 and the state detection continues.

[0156] <Subject 4 behavior> The object 4 for state detection is the same as in the first embodiment, and description thereof will be omitted. Regarding behavior, state A (A in FIG. 4), state B (B in FIG. 4), and state C (C in FIG. 4) will be referred to.

[0157] <Distance image Gd-B of state B, first block 60-1, second block 60-2 and third block 60-3 of distance image Gd-B, virtual volume images Gv1-B, Gv2-B, Gv3-B for each block, virtual volumes Vv1-B, Vv2-B, Vv3-B and ratios R11-B, R12-B, R13-B>

[0158] A in Fig. 11 shows a distance image Gd-B on frame 62-1 obtained from state B (B in Fig. 4) of object 4. This distance image Gd-B includes pixels gi corresponding to the first block 60-1, pixels gi corresponding to the second block 60-2, and pixels gi corresponding to the third block 60-3.

[0159] 11B shows virtual volume images Gv1-B, Gv2-B, and Gv3-B generated from distance image Gd-B. Virtual volume image Gv1-B shows a part of object 4 and its virtual volume calculated from pixels gi included in the first block 60-1 of state B. Virtual volume image Gv2-B represents a part of object 4 and its virtual volume calculated from pixels gi included in the second block 60-2 of state B. Virtual volume image Gv3-B represents a part of object 4 and its virtual volume calculated from pixels gi included in the third block 60-3 of state B.

[0160] 12A shows a virtual volume image Gv1-B corresponding to the first block 60-1 on the frame 62-3 separated from the virtual volume image Gv-B. The virtual volume Vv1-B of the first block 60-1 can be calculated by the pixels gi included in this virtual volume image Gv1-B. In this case, the ratio R11 is R11-B.

[0161] 12B shows a virtual volume image Gv2-B corresponding to the second block 60-2 on the frame 62-4 separated from the virtual volume image Gv-B. The virtual volume Vv2-B of the second block 60-2 can be calculated by the pixels gi included in this virtual volume image Gv2-B. In this case, the ratio R12 is R12-B.

[0162] 12C shows a virtual volume image Gv3-B corresponding to the third block 60-3 on the frame 62-5 separated from the virtual volume image Gv-B. The virtual volume Vv3-B of the third block 60-3 can be calculated by the pixels gi included in this virtual volume image Gv3-B. In this case, the ratio R13 is R13-B.

[0163] A in Fig. 13 shows a distance image Gd-B on frame 62-1 obtained from state C (C in Fig. 4) of object 4. This distance image Gd-C includes pixels gi corresponding to the first block 60-1, pixels gi corresponding to the second block 60-2, and pixels gi corresponding to the third block 60-3.

[0164] 13B shows virtual volume images Gv1-C, Gv2-C, and Gv3-C generated from distance image Gd-B. Virtual volume image Gv1-C shows a part of object 4 and its virtual volume calculated from pixels gi included in the first block 60-1 in state C. Virtual volume image Gv2-C represents a part of object 4 and its virtual volume calculated from pixels gi included in the second block 60-2 in state C. Virtual volume image Gv3-C represents a part of object 4 and its virtual volume calculated from pixels gi included in the third block 60-3 in state C.

[0165] 14A shows a virtual volume image Gv1-C corresponding to the first block 60-1 on the frame 62-8 separated from the virtual volume image Gv-C. The virtual volume Vv1-C can be calculated from the pixels gi included in this virtual volume image Gv1-C. In this case, the ratio R11 is R11-C.

[0166] 14B shows a virtual volume image Gv2-C corresponding to the second block 60-2 on the frame 62-9 separated from the virtual volume image Gv-C. The virtual volume Vv2-C can be calculated from the pixels gi included in this virtual volume image Gv2-C. In this case, the ratio R12 is R12-C.

[0167] 14C shows a virtual volume image Gv3-C corresponding to the third block 60-3 on the frame 62-10 separated from the virtual volume image Gv-C. The virtual volume Vv3-C can be calculated from the pixels gi included in this virtual volume image Gv3-C. In this case, the ratio R13 is R13-C.

[0168] <Comparison and judgment of fluctuation information of distance information distribution in states B and C> The comparative calculation of the variation information of the distance information distribution in states B and C is to detect whether the object 4 is normal or abnormal, as in the first embodiment. Comparing the ratios R11-B, R12-B, and R13-B shown in A, B, and C of Fig. 12 obtained from state B with the ratios R11-C, R12-C, and R13-C shown in A, B, and C of Fig. 14 obtained from state C, as shown in A of Fig. 14, the arm portion of the limb 4c of the object 4 is added to the virtual volume image Gv1-C of the first block, so that the virtual volume Vv1-C is enlarged, and as shown in C of Fig. 14, the virtual volume image Gv3-C of the third block changes and the virtual volume Vv3-C is reduced.

[0169] Therefore, by using the processing described above to obtain the amount of fluctuation M from the fluctuation information of the distance information distribution in states B and C, and comparing the amount of fluctuation M with the threshold value Mth, in states B and C, M>Mth holds, it is determined that the object 4 is exhibiting behavior, and normal detection is obtained.

[0170] In this case, the amount of fluctuation M is obtained from the fluctuation information of the distance information distribution in states B and C by the processing described above, and the amount of fluctuation M is compared with a threshold value Mth. If M≦Mth holds, it is determined that there is no behavior of the object 4 and an abnormality is detected.

[0171] <Advantages of the Second Embodiment> According to the second embodiment, any one of the following effects can be obtained.

[0172] (1) The same effects as those of the first embodiment can be obtained.

[0173] (2) In the second embodiment, the state of the object 4 is detected based on the ratios R11-B, R12-B, R13-B of state B and the ratios R11-C, R12-C, R13-C of state C of the virtual volumes Vv1-B, Vv2-B, Vv3-B, Vv1-C, Vv2-C, Vv3-C. Therefore, if the object 4 is, for example, a human, the state can be detected by taking into account information about the thickness direction of the object 4, thereby further improving the detection accuracy. EXAMPLES

[0174] 15 illustrates an example of a single chip detection module 20. This detection module 20 includes a processing unit 64 having the same functions as the processing device 12. In this detection module 20, the same reference numerals are used for the parts common to the detection system 2 described above, and the description thereof will be omitted.

[0175] <Effects of the embodiment> According to this embodiment, any one of the following effects can be obtained. (1) It can be widely used to detect the state of an object 4 such as a human being.

[0176] (2) The state of the object 4 can be detected without regard for privacy, such as gender, and the like, and the device can be used to detect the state of the object in a bathroom, toilet, etc.

[0177] Other Embodiments The present disclosure includes the following modifications: (1) In this detection system 2, the processing device 12 may compare the coordinates of pixels gi contained in two or more distance images Gd, virtual area images Gs or virtual volume images Gv, and detect a change in the state of the object 4 from the difference in coordinates between the front and back.

[0178] (2) In this detection system 2, the coordinates on the image may include any of the singular points (including feature points of the object 4), center of gravity points, or vertices contained in the distance image Gd, the virtual area image Gs, or the virtual volume image Gv.

[0179] (3) In the above embodiment, the distance image is divided into three blocks: a first block, a second block, and a third block. However, it is also possible to apply division into two or four or more blocks using the distance image obtained from the object 4.

[0180] (4) In the above embodiment, a human is used as the object 4, but a moving object other than a human, such as a moving object such as an automobile or a robot, may be used as the object 4.

[0181] (5) In the above embodiment, a single detection module is illustrated. However, multiple detection modules obtained by using multiple cameras may be used in combination.

[0182] (6) Regarding detection of the state of the object 4, a detection time may be set, and whether the object 4 is normal or abnormal may be detected based on the presence or absence of behavior within this detection time.

[0183] (7) Regarding blocking of distance images or volumetric images, elevation information representing the height distance of pixels gi from the distance image may be defined, and blocks may be formed for each group of pixels associated with the height of the pixels contained in the image information represented by this elevation information.

[0184] (8) In the above embodiment, the processing device 12 may detect a change in state of the object 4 from the difference between before and after by comparing the virtual area or virtual volume between frames.

[0185] As described above, the most preferred embodiment of the present invention has been described. The technology of the present disclosure is not limited to the above description. Various modifications and changes are possible for those skilled in the art based on the gist of the invention described in the claims or disclosed in the specification. It goes without saying that such modifications and changes are included in the scope of the present invention. [Industrial Applicability]

[0186] According to the disclosed system, method, program, and detection module for status detection, it is possible to easily and accurately detect the status of an object, such as a human, using only a distance image obtained from the object. [Explanation of symbols]

[0187] 2. Detection System 4. Object 4a head 4b Torso 4c Limbs 6 Light emitting part 8. Imaging unit 10 Control section 12 Processing equipment 14 Light Emitting Driver 16 Light receiving part 18 Distance image generation unit 20 Detection Module 22 processors 24 Memory section 26 Input / output section 28 Information presentation section 30 Communications Department 32-1, 32-2 Database 34 Date and Time Information Department 36 Light-emitting information section 38 Light reception information section 40 Distance image section 42 Classification Information Department 44 Block Image Information Section 44-1 First Block 44-2 Second block section 44-3 Third Block 46 Virtual Area and Ratio Section 47 Virtual Volume / Ratio Section 48 Distance information distribution part 50 Status Information Section 52 Detection Information Department 54 Presentation Information Department 56 History Information Section 58-1, 58-2, 58-3, 58-4, 58-5, 58-6, 58-7, 58-8, 58-9, 58-10, 62-1, 62-2, 62-3, 62-4, 62-5, 62-6, 62-7, 62-8, 62-9, 62-10 Frame 60-1 First Block 60-2 Second Block 60-3 Third Block 64 Processing section

Claims

1. An imaging unit that acquires a distance image representing the distance to an object, A processing unit that divides pixels included in the distance image into two or more blocks according to perspective relationship, and detects the state of the object by comparing the ratios of the pixels included in each block, A detection system including the above.

2. The detection system according to claim 1, wherein the processing unit compares pixels included in distance images between two or more front and rear, and detects a state change of the object from the difference therebetween.

3. The detection system according to claim 1 or claim 2, wherein the processing unit compares the pixels between frames of the distance image.

4. The detection system according to claim 1 or claim 2, wherein the processing unit calculates a virtual area and / or a virtual volume of the object using the pixels included in the block, compares the virtual areas between two or more front and rear, or compares the virtual volumes between two or more front and rear, thereby detecting a state change of the object.

5. The detection system according to claim 1 or claim 2, wherein the processing unit compares coordinates of pixels included in two or more of the distance images, virtual area images or virtual volume images, and detects a state change of the object from the difference in the coordinates between front and rear.

6. The detection system according to claim 5, wherein the coordinates include any one of singular points, centroid points, or vertices included in the distance image, the virtual area image, or the virtual volume image.

7. The detection system according to claim 4, including an information presentation unit that presents any one or two or more of the distance image, the virtual area or the virtual volume, and state information representing the state of the object.

8. A step of the imaging unit acquiring distance images representing the distance to an object in a time series, A step of the processing unit dividing pixels included in the distance image into two or more blocks according to perspective relationship, detecting the state of the object by comparing the ratios of the pixels included in each block, and calculating a virtual area or a virtual volume for each block using the pixels included in each block for at least each state of the object, A detection method including the above.

9. The detection method according to claim 8, including a step of the processing unit comparing distance images between two or more front and rear and detecting a state change of the object from the difference therebetween.

10. The method of claim 8 or claim 9, wherein the processing unit calculates a virtual area and / or a virtual volume of the object using pixels included in the block, compares the virtual areas between two or more before and after frames, or compares the virtual volumes between two or more before and after frames to detect a state change of the object.

11. A program for causing a computer to execute, a function of acquiring a distance image representing a distance to an object in a time series, a function of dividing pixels included in the distance image into two or more blocks based on a perspective relationship and detecting a state of the object by comparing ratios of pixels included in each block, is a program for causing the computer to execute.

12. A function of calculating a virtual area or a virtual volume for each block using pixels included in each block for at least each state of the object, is the program according to claim 11 for causing the computer to execute.

13. The program according to claim 11 or claim 12 for causing the computer to execute a function of comparing distance images between two or more before and after frames and detecting a state change of the object from the difference.

14. An imaging unit that acquires a distance image representing a distance to an object in a time series, a processing unit that divides pixels included in the distance image into two or more blocks based on a perspective relationship and detects a state of the object by comparing ratios of pixels included in each block, is a detection module including.

15. The detection module according to claim 14, wherein the processing unit compares distance images between two or more before and after frames and detects a state change of the object from the difference.

16. The detection module according to claim 14 or claim 15, wherein the processing unit calculates a virtual area and / or a virtual volume of the object using pixels included in the block, compares the virtual areas between two or more before and after frames, or compares the virtual volumes between two or more before and after frames to detect a state change of the object.

Images