MOBILE BODY DETECTION DEVICE, SYSTEM, METHOD, AND PROGRAM

Abstract

The purpose of the present disclosure is to provide a moving body detection device capable of accurately detecting a moving body. A moving body detection device (100) comprises an acquisition unit (110) that acquires a captured video, a first setting unit (120) that sets moving body detection conditions on the basis of related information containing information related to the video, and a detection unit (130) that detects a moving body from frames constituting the video on the basis of the moving body detection conditions. The moving body detection device (100) adjusts the moving body detection conditions on the basis of the related information, and thus can accurately detect a moving body.

Description

MOBILE OBJECT DETECTION DEVICE, SYSTEM, METHOD, AND NON-TRANSITORY COMPUTER-READABLE MEDIUM HAVING PROGRAM STORED THEREON

[0001] The present disclosure relates to a mobile object detection device, a system, a method, and a non-transitory computer-readable medium having a program stored thereon.

[0002] When moving objects such as people are included in video captured by an in-vehicle camera while a vehicle is traveling, it may be necessary to blur the moving objects from the viewpoint of protecting personal information. In order to blur the moving objects included in the video, it is necessary to accurately detect the moving objects from the captured video.

[0003] Patent Document 1 discloses a technology for detecting pedestrians from video while switching the pedestrian recognition level depending on the vehicle speed.

[0004] JP 2009-064274 A

[0005] If a false detection occurs when detecting a moving object from a video, there is a risk that areas of the video that do not contain a moving object, i.e., areas that do not need to be blurred, will be blurred. Therefore, there is a need to improve the accuracy of detecting moving objects in video.

[0006] The present disclosure has been made to solve such problems, and aims to provide a moving body detection device, system, method, and non-transitory computer-readable medium on which a program is stored that can accurately detect moving bodies.

[0007] The moving body detection device according to the present disclosure includes an acquisition unit that acquires captured video, a first setting unit that sets moving body detection conditions based on related information including information related to the video, and a detection unit that detects moving bodies from frames that constitute the video based on the moving body detection conditions.

[0008] The moving object detection system according to the present disclosure comprises an imaging device that captures video of the surrounding area, and a moving object detection device capable of communicating with the imaging device, wherein the moving object detection device comprises an acquisition unit that acquires the video captured by the imaging device, a first setting unit that sets moving object detection conditions based on related information including information related to the video, and a detection unit that detects moving objects from frames that constitute the video based on the moving object detection conditions.

[0009] The moving object detection method according to the present disclosure includes the steps of: a computer acquiring captured video; setting moving object detection conditions based on related information including information related to the video; and detecting a moving object from frames constituting the video based on the moving object detection conditions.

[0010] The non-transitory computer-readable medium of the present disclosure stores a moving object detection program that causes a computer to perform the following processes: acquiring captured video; setting moving object detection conditions based on related information including information related to the video; and detecting moving objects from frames that constitute the video based on the moving object detection conditions.

[0011] The present disclosure can provide a moving body detection device, a system, a method, and a non-transitory computer-readable medium storing a program that can detect moving bodies with high accuracy.

[0012] FIG. 1 is a block diagram showing the configuration of a moving body detection device according to embodiment 1. FIG. 2 is a flowchart showing the flow of a moving body detection method according to embodiment 1. FIG. 3 is a block diagram showing the configuration of a moving body detection system according to embodiment 2. FIG. 4 is a block diagram showing the configuration of a moving body detection device according to embodiment 2. FIG. 5 is a diagram showing an example of a frame in which a moving body is detected. FIG. 6 is a flowchart showing the flow of a moving body detection method according to embodiment 2. FIG. 7 is a block diagram showing the configuration of a moving body detection device according to embodiment 3. FIG. 8 is a flowchart showing the flow of a second threshold setting process in embodiment 3. FIG. 9 is a flowchart showing the flow of a moving body detection method according to embodiment 3. FIG. 10 is a block diagram showing the configuration of a moving body detection system according to embodiment 4. FIG. 11 is a flowchart showing the flow of a second threshold setting process in embodiment 4. FIG. 12 is a flowchart showing the flow of a moving body detection method according to embodiment 4. FIG. 13 is a block diagram showing the configuration of a moving body detection device according to embodiment 5. FIG. 14 is a flowchart showing the flow of a third threshold setting process in embodiment 5. FIG. 15 is a flowchart showing the flow of a moving body detection method according to embodiment 5.

[0013] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and for clarity of explanation, duplicate explanations will be omitted as necessary.

[0014] <First Embodiment> Fig. 1 is a block diagram showing the configuration of a moving body detection device 100 according to a first embodiment. The moving body detection device 100 includes an acquisition unit 110, a first setting unit 120, and a detection unit 130. The moving body detection device 100 is connected to a network 500 (not shown), which may be wired or wireless. An image capturing device 300 (not shown) and the like are connected to the network 500. The image capturing device 300 is installed in a vehicle 310 (not shown), and is a device that captures images of the surroundings of the vehicle. The video captured by the image capturing device 300 is typically a moving image and includes multiple frames.

[0015] The acquisition unit 110 acquires video captured by the imaging device 300 installed in the vehicle 310. Note that the video includes at least one frame, and typically includes multiple frames. The first setting unit 120 sets moving object detection conditions based on related information. The related information is information related to the video, such as the variance and brightness of the frames that make up the video, and the time the video was captured. The detection unit 130 detects moving objects from the frames that make up the video acquired by the acquisition unit 110 based on the moving object detection conditions set by the first setting unit 120. A moving object is something that moves on a road, such as a person, a car, a motorcycle, or an electric kick scooter.

[0016] When a moving object such as a person is clearly visible in a frame constituting a video, it is preferable to detect the moving object and blur it to protect privacy. On the other hand, blurring an unclear moving object results in an unnecessarily large blurred area in the video, which reduces the visibility of the video, and is therefore undesirable. Therefore, when a moving object in a frame is unclear, there is little need to blur the moving object.

[0017] The clarity of the frames that make up a video varies depending on the shooting environment, etc. For example, frames with large variance, i.e., frames that are clearly captured, are clearer than frames with small variance. Clear frames are more likely to contain clear images of moving objects. Therefore, the first setting unit 120 sets the moving object detection conditions so that a moving object is more easily detected when the frame is clear than when the frame is unclear.

[0018] 2 is a flowchart showing the flow of the moving object detection method according to the first embodiment. First, the acquisition unit 110 acquires a captured image (step S101). Next, the first setting unit 120 sets moving object detection conditions based on related information including information related to the image acquired in step S101 (step S102). Next, the detection unit 130 detects moving objects from the frames constituting the image acquired in step S101 based on the moving object detection conditions set in step S102 (step S103). In this way, the moving object detection method according to the first embodiment adjusts the moving object detection conditions depending on the clarity of the frames, thereby enabling accurate detection of moving objects.

[0019] The moving body detection device 100 includes a processor, a memory, and a storage device (not shown). The storage device stores a computer program that implements the processing of the moving body detection method according to the first embodiment. The processor then loads the computer program from the storage device into the memory and executes the computer program. As a result, the processor realizes the functions of the acquisition unit 110, the first setting unit 120, and the detection unit 130.

[0020] The acquisition unit 110, the first setting unit 120, and the detection unit 130 may each be realized by dedicated hardware. Some or all of the components of each device may be realized by general-purpose or dedicated circuits, processors, etc., or a combination of these. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components of each device may be realized by a combination of the above-mentioned circuits, etc., and a program. A CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), etc. may be used as the processor.

[0021] Furthermore, when some or all of the components of the mobile object detection device 100 are realized by multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may be centrally or decentralized. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, or the like, in a form in which each is connected via a communication network. Furthermore, the functions of the mobile object detection device 100 may be provided in a SaaS (Software as a Service) format.

[0022] <Embodiment 2> Embodiment 2 is a specific example of the above-described embodiment 1. In embodiment 2, moving body detection conditions are set using frame variance as related information. FIG. 3 is a block diagram showing the configuration of a moving body detection system 200 according to embodiment 2. The moving body detection system 200 includes an image capture device 300 and a moving body detection device 400. The image capture device 300 is connected to the moving body detection device 400 via a network 500. Note that descriptions that overlap with embodiment 1 will be omitted as appropriate.

[0023] The moving object detection system 200 is a system for detecting a moving object from video captured by a vehicle 310. The vehicle 310 is, for example, an automobile, but may also be a vehicle other than an automobile, such as a motorcycle or a bicycle. An imaging device 300 is installed in the vehicle 310. The imaging device 300 is a device that captures the scenery around the vehicle 310, such as a drive recorder. The imaging device 300 includes an imaging unit 301 and a communication unit 302. The imaging unit 301 is a camera. The imaging unit 301 captures, for example, the scenery ahead of the vehicle 310, i.e., the scenery that can be seen by a driver seated in the driver's seat of the vehicle 310. The communication unit 302 is a communication interface with a network 500. The communication unit 302 transmits the video captured by the imaging unit 301 to the moving object detection device 400 via the network 500.

[0024] Next, the configuration of the moving body detection device 400 will be described in detail with reference to Fig. 4. Fig. 4 is a block diagram showing the configuration of the moving body detection device 400. The moving body detection device 400 includes a memory 410, a communication unit 420, a storage unit 430, and a control unit 440.

[0025] The memory 410 is a storage area that temporarily stores the processing contents of the control unit 440, and is a volatile storage device such as a RAM (Random Access Memory). The communication unit 420 is an interface that communicates with the outside of the moving object detection device 400. The storage unit 430 is a storage device that stores a program 431, a first threshold value 432, and the like. The first threshold value 432 is a numerical value used when detecting a moving object. The program 431 is a computer program that implements the moving object detection process according to the second embodiment.

[0026] The control unit 440 includes an acquisition unit 441, a first setting unit 442, a detection unit 443, and a masking unit 444. The control unit 440 is a control device that controls the operation of the moving body detection device 400, and is, for example, a processor such as a CPU. The control unit 440 loads the program 431 from the storage unit 430 into the memory 410 and executes it. In this way, the control unit 440 realizes the functions of the acquisition unit 441, the first setting unit 442, the detection unit 443, and the masking unit 444.

[0027] The acquisition unit 441 acquires the video transmitted from the image capturing device 300. The video usually includes multiple frames. The video may also include identification information, etc. The identification information is information for identifying the vehicle 310 on which the image capturing device 300 that captured the video is installed.

[0028] The first setting unit 442 sets moving object detection conditions based on the related information. Specifically, the first setting unit 442 first calculates the variance of each frame constituting the video acquired by the acquisition unit 441. The frame variance is a value calculated by subtracting the square of the average from the average of the squares of all pixel values ​​in the frame, and indicates the variation in the number of pixels in the frame. Next, the first setting unit 442 sets a first threshold 432 based on the frame variance and stores it in the storage unit 430. The first threshold 432 is a threshold used when detecting a moving object. The first setting unit 442 sets the first threshold 432 higher when the frame variance is small, i.e., when the frame is blurry, than when the frame variance is large. Furthermore, the first setting unit 442 sets the first threshold 432 lower when the frame variance is large than when the frame variance is small.

[0029] The detection unit 443 detects a moving object from the video acquired by the acquisition unit 441. Specifically, the detection unit 443 calculates a moving object detection score for each frame constituting the video acquired by the acquisition unit 441. The moving object detection score is a numerical value calculated for each region in the frame. The moving object detection score is higher in regions where a moving object is likely to be present than in other regions. Note that the method for calculating the moving object detection score is not particularly limited, and existing technology can be applied. Next, the detection unit 443 determines whether the moving object detection score is less than or equal to the first threshold 432. The detection unit 443 determines that a moving object is present in a location in the frame where the moving object detection score is equal to or greater than the threshold. When the first threshold 432 is low, more regions are detected as regions where a moving object is present than when the first threshold 432 is high. In other words, when the first setting unit 442 sets the first threshold 432 low, a moving object is more likely to be detected from the frame.

[0030] Fig. 5 is a diagram showing an example of a frame in which a moving object is detected. Frame 10 shown in Fig. 5 is a frame constituting the video acquired by the acquisition unit 441. When a moving object 20 is captured in frame 10 as shown in Fig. 5, the moving object detection score in the vicinity of the moving object 20 is calculated to be higher than the moving object detection score in other areas. When the moving object detection score in the vicinity of the moving object 20, i.e., in area 30, is equal to or greater than a threshold, the detection unit 443 determines that a moving object is captured in area 30.

[0031] 4, the description will be continued. The masking unit 444 performs a masking process, i.e., blurs, on the area in which the moving object is detected by the detection unit 443. The method of the masking process is not particularly limited, and the process can be performed using existing technology.

[0032] As described above, the moving body detection device 400 according to the second embodiment sets the threshold value of the moving body detection score low when the variance of the frames is small, i.e., when the moving body captured in the frame is likely to be clear, and therefore the moving body is likely to be detected. Furthermore, the moving body detection device 400 sets the threshold value of the moving body detection score high when the variance of the frames is small, i.e., when the moving body captured in the frame is likely to be unclear, and therefore the moving body is unlikely to be detected unclear. Therefore, the moving body detection device 400 can accurately detect clear moving bodies, i.e., moving bodies that need to be blurred.

[0033] Next, the operation of the moving body detection device 400 when detecting a moving body will be described with reference to Fig. 6. Fig. 6 is a flowchart showing the flow of the moving body detection process.

[0034] First, the acquisition unit 441 acquires video from the image capturing device 300 (step S201). Next, the first setting unit 442 calculates the variance of the frames constituting the video acquired in step S201 (step S202). Next, the first setting unit 442 sets the first threshold 432 based on the variance calculated in step S202 (step S203) and stores it in the storage unit 430. Next, the detection unit 443 calculates a moving object detection score for the frames constituting the video acquired in step S201 (step S204). Next, the detection unit 443 detects a moving object based on the first threshold 432 stored in the storage unit 430 (step S205).

[0035] If the moving object detection score is less than the first threshold 432 in any region within the frame, the detection unit 443 determines that a moving object has not been detected in the frame (step S205: No) and terminates moving object detection. If a region within the frame exists where the moving object detection score is equal to or greater than the first threshold 432, the detection unit 443 determines that a moving object has been detected in the frame (step S205: Yes). When it is determined that a moving object has been detected (step S205: Yes), the masking unit 444 performs a masking process on the region where the moving object has been detected (step S206). In this way, the moving object detection device 400 according to the second embodiment adjusts the first threshold 432 according to the variance of the frame to detect moving objects, and therefore can accurately detect moving objects that require masking.

[0036] <Embodiment 3> Embodiment 3 is a modification of the above-described embodiment 2. In embodiment 3, the need for masking is determined based on related information. FIG. 7 is a block diagram showing the configuration of a moving body detection device 700 according to embodiment 3. Compared to the moving body detection device 400 shown in FIG. 4, the moving body detection device 700 differs in that it includes a memory unit 730 instead of the memory unit 430 and a control unit 740 instead of the control unit 440. Since the other configuration overlaps with embodiment 1 or 2, description thereof will be omitted as appropriate. The memory unit 730 is a storage device that stores a second threshold value 733 in addition to a program 431 and a first threshold value 432. The control unit 740 includes an acquisition unit 441, a first setting unit 442, a detection unit 443, and a masking unit 444, as well as a first measurement unit 745 and a second setting unit 746.

[0037] The acquisition unit 441 acquires video from the imaging device 300 and acquires vehicle information from the recording device 320. The first setting unit 442 sets moving object detection conditions based on the related information. Specifically, first, the first setting unit 442 calculates the variance of each frame constituting the video acquired by the acquisition unit 441. Next, the first setting unit 442 sets a first threshold 432 based on the frame variance and stores it in the storage unit 730. The detection unit 443 detects moving objects from the video acquired by the acquisition unit 441. Specifically, the detection unit 443 calculates a moving object detection score for each frame constituting the video acquired by the acquisition unit 441. Next, the detection unit 443 determines whether the moving object detection score is less than the first threshold 432.

[0038] The first measurement unit 745 calculates the number of pixels in the image of the moving object detected by the detection unit 443. For example, the first measurement unit 745 considers area 30 shown in FIG. 5 as the image in which the moving object is detected, and calculates the number of pixels in area 30. In the third embodiment, the second setting unit 746 sets a second threshold value 733 based on related information and stores it in the storage unit 730. The second threshold value 733 is a threshold value used when determining whether or not masking of the image is required.

[0039] 8 is a flowchart showing the flow of the second threshold setting process in the third embodiment. As shown in FIG. 8 , in the third embodiment, the second setting unit 746 sets the second threshold 733 based on related information. Specifically, the second setting unit 746 sets the second threshold 733 based on the variance of the frame calculated by the first setting unit 442. Specifically, when the variance is equal to or greater than a predetermined value (Yes in step S301), the second setting unit 746 sets the second threshold 733 lower than when the variance is less than the predetermined value (step S302). When the variance is less than the predetermined value (No in step S301), the second setting unit 746 sets the second threshold 733 higher than when the variance is equal to or greater than the predetermined value (step S303).

[0040] Returning to FIG. 7 , the explanation will be continued. In the third embodiment, if the number of pixels in an image in which a moving object is detected is equal to or greater than the second threshold value 733, the masking unit 444 performs a masking process on the image. If the frame variance is small, the moving object in the video is more likely to be blurred than if the frame variance is large. Since there is no need to perform a masking process when the moving object is blurred, the second setting unit 746 sets the second threshold value 733 high when the frame variance is small. This allows the masking unit 444 to extract only images that require masking and perform masking on those images.

[0041] Next, the operation of the moving body detection device 700 when detecting a moving body will be described with reference to Fig. 9. Fig. 9 is a flowchart showing the flow of the moving body detection process.

[0042] First, the acquisition unit 441 acquires video from the image capturing device 300 (step S401). Next, the first setting unit 442 calculates the variance of the frames constituting the video acquired in step S401 (step S402). Next, the first setting unit 442 sets the first threshold 432 based on the variance calculated in step S402 (step S403) and stores it in the storage unit 730. Next, the detection unit 443 calculates a moving object detection score for the frames constituting the video acquired in step S401 (step S404). Next, the detection unit 443 detects a moving object based on the first threshold 432 stored in the storage unit 730 (step S405).

[0043] If the moving object detection score is less than the first threshold 432 in any region within the frame, the detection unit 443 determines that a moving object has not been detected from the frame (step S405: No) and ends the detection of the moving object. If there is a region within the frame where the moving object detection score is equal to or greater than the first threshold 432, the detection unit 443 determines that a moving object has been detected from the frame (step S405: Yes).

[0044] When the first measurement unit 745 determines that a moving object has been detected (step S405: Yes), it calculates the number of pixels in the image in which the moving object has been detected (step S406). Next, the second setting unit 746 sets a second threshold 733 based on the frame variance calculated in step S402 (step S407) and stores the second threshold 733 in the storage unit 730. Next, the masking unit 444 determines whether masking is required for the image detected in step S405 (step S408). If the number of pixels calculated in step S406 is less than the second threshold 733, the masking unit 444 determines that masking is not required for the image (step S408: No) and terminates the masking process. If the number of pixels calculated in step S406 is equal to or greater than the second threshold 733, the masking unit 444 determines that masking is required for the image (step S408: Yes) and performs the masking process (step S409).

[0045] In this way, the moving body detection device 700 according to the third embodiment sets the second threshold value 733 based on the related information to determine whether or not masking processing is necessary, and therefore can accurately detect images that require masking processing.

[0046] <Fourth Embodiment> The fourth embodiment is a modification of the second and third embodiments described above. In the third embodiment, the case where the second threshold 733 is set based on related information has been described. On the other hand, in the fourth embodiment, the second threshold 733 is set based on vehicle information. FIG. 10 is a block diagram showing the configuration of a moving object detection system 600 according to the fourth embodiment. Compared to the moving object detection system 200 shown in FIG. 3, the moving object detection system 600 further includes a recording device 320. Also, compared to the moving object detection system 200, the moving object detection system 600 differs in that it includes a moving object detection device 700 instead of the moving object detection device 400. The image capturing device 300 and the recording device 320 are each connected to the moving object detection device 700 via a network 500. Note that the other configurations are similar to those described in the second or third embodiment, and therefore will not be described as appropriate.

[0047] The recording device 320 is a device that records vehicle information such as the traveling speed of the vehicle 310. The recording device 320 is installed in the vehicle 310. The recording device 320 includes a measurement unit 321 and a communication unit 322. The measurement unit 321 measures vehicle information including information related to the vehicle 310. The vehicle information is information recorded in the vehicle 310, such as the traveling speed of the vehicle 310. The communication unit 322 is a communication interface with the network 500. The communication unit 322 transmits the vehicle information measured by the measurement unit 321 to the moving object detection device 700 via the network 500.

[0048] In the fourth embodiment, the acquisition unit 441 acquires video from the imaging device 300 and vehicle information from the recording device 320. The second setting unit 746 sets a second threshold value 733 based on the vehicle information and stores the second threshold value in the storage unit 730.

[0049] 11 is a flowchart showing the flow of the second threshold setting process in the fourth embodiment. In the fourth embodiment, the second setting unit 746 sets the second threshold 733 based on the traveling speed of the vehicle 310 at the time when the video was captured. When the traveling speed is less than a predetermined value (Yes in step S501), the second setting unit 746 sets the second threshold 733 lower (step S502) than when the traveling speed is equal to or greater than the predetermined value. When the traveling speed is equal to or greater than the predetermined value (No in step S501), the second setting unit 746 sets the second threshold 733 higher (step S503) than when the traveling speed is less than the predetermined value.

[0050] In the fourth embodiment, if the number of pixels in an image in which a moving object is detected is equal to or greater than the second threshold value 733, the masking unit 444 performs a masking process on the image. If the traveling speed of the vehicle 310 is fast, the moving object in the image is more likely to be blurred than if the traveling speed is slow. Since there is no need to perform a masking process when the moving object is blurred, the second setting unit 746 sets the second threshold value 733 to a high value when the traveling speed is fast. This allows the masking unit 444 to extract only images that require masking processing and perform the masking process on those images.

[0051] Next, the operation of the moving body detection device 700 in the fourth embodiment will be described with reference to Fig. 12. Fig. 12 is a flowchart showing the flow of moving body detection processing in the fourth embodiment.

[0052] First, the acquisition unit 441 acquires video from the imaging device 300 and acquires vehicle information from the recording device 320 (step S601). Next, the first setting unit 442 calculates the variance of the frames constituting the video acquired in step S601 (step S602). Next, the first setting unit 442 sets the first threshold 432 based on the variance calculated in step S602 (step S603) and stores it in the storage unit 730. Next, the detection unit 443 calculates a moving object detection score for the frames constituting the video acquired in step S601 (step S604). Next, the detection unit 443 detects a moving object based on the first threshold 432 stored in the storage unit 730 (step S605).

[0053] If the moving object detection score is less than the first threshold 432 in any region within the frame, the detection unit 443 determines that a moving object has not been detected from the frame (step S605: No) and ends the detection of the moving object. If there is a region within the frame where the moving object detection score is equal to or greater than the first threshold 432, the detection unit 443 determines that a moving object has been detected from the frame (step S605: Yes).

[0054] When the first measurement unit 745 determines that a moving object has been detected (step S605: Yes), it calculates the number of pixels in the image in which the moving object has been detected (step S606). Next, the second setting unit 746 sets a second threshold value 733 based on the vehicle information acquired in step S601 (step S607) and stores the second threshold value 733 in the storage unit 730. Next, the masking unit 444 determines whether or not masking is required for the image detected in step S605 (step S608). If the number of pixels calculated in step S606 is less than the second threshold value 733, the masking unit 444 determines that masking is not required for the image (step S608: No) and terminates the masking process. If the number of pixels calculated in step S606 is equal to or greater than the second threshold value 733, the masking unit 444 determines that masking is required for the image (step S608: Yes) and performs the masking process (step S609).

[0055] In the moving body detection method of embodiment 4, the second threshold value 733 is set based on vehicle information to determine whether or not masking processing is necessary, so that images that require masking processing can be detected with high accuracy.

[0056] <Embodiment 5> Embodiment 5 is a modification of the above-described embodiment 3. In embodiment 3, the case where the necessity of masking is determined based on the variance of frames has been described. On the other hand, in embodiment 5, the necessity of masking is determined based on the brightness of frames. FIG. 13 is a block diagram showing the configuration of a moving object detection device 800 according to embodiment 5. Compared to the moving object detection device 400 shown in FIG. 4, the moving object detection device 800 is different in that it includes a memory unit 830 instead of the memory unit 430 and a control unit 840 instead of the control unit 440. Since the other configuration overlaps with embodiments 1 or 2, etc., description thereof will be omitted as appropriate. The memory unit 830 is a storage device that stores a program 431, a first threshold value 432, and a third threshold value 833. The control unit 740 includes an acquisition unit 441, a first setting unit 442, a detection unit 443, and a masking unit 444, as well as a second measurement unit 845 and a third setting unit 846.

[0057] The second measurement unit 845 calculates the luminance of a frame constituting the video acquired by the acquisition unit 441. The luminance of a frame is a numerical value indicating the brightness within the frame, and is calculated using existing technology. The third setting unit 846 sets a third threshold 833 based on the luminance of the frame, and stores the third threshold 833 in the storage unit 730. The third threshold 833 is a threshold used when determining whether or not masking of the image is required.

[0058] 14 is a flowchart showing the flow of the second threshold setting process in the fifth embodiment. In the fifth embodiment, the third setting unit 846 sets the third threshold 833 based on the luminance of the frame calculated by the second measurement unit 845. Specifically, when the luminance of the frame is equal to or greater than a predetermined value (Yes in step S701), the third setting unit 846 sets the third threshold 833 lower (step S702) than when the luminance of the frame is less than the predetermined value. When the luminance of the frame is less than the predetermined value (No in step S701), the third setting unit 846 sets the third threshold 833 higher (step S703) than when the luminance of the frame is equal to or greater than the predetermined value.

[0059] Returning to FIG. 13 , the explanation will continue. In the fifth embodiment, if the number of pixels in an image in which a moving object is detected is equal to or greater than the third threshold value 833, the masking unit 444 performs a masking process on the image. If the frame is dark, the moving object in the video is more likely to be blurred than if the frame is bright. Since there is no need to perform a masking process when the moving object is blurred, the second setting unit 746 sets the second threshold value 733 low if the frame is bright, i.e., if the luminance of the frame is equal to or greater than a predetermined value. This allows the masking unit 444 to extract only images that require masking and perform masking on those images.

[0060] Next, the operation of the moving body detection device 800 when detecting a moving body will be described with reference to Fig. 15. Fig. 15 is a flowchart showing the flow of moving body detection processing in the fifth embodiment.

[0061] First, the acquisition unit 441 acquires video from the image capturing device 300 (step S801). Next, the first setting unit 442 calculates the variance of the frames constituting the video acquired in step S801 (step S802). Next, the first setting unit 442 sets the first threshold 432 based on the variance calculated in step S802 (step S803) and stores it in the storage unit 730. Next, the detection unit 443 calculates a moving object detection score for the frames constituting the video acquired in step S801 (step S804). Next, the detection unit 443 detects a moving object based on the first threshold 432 stored in the storage unit 730 (step S805).

[0062] If the moving object detection score is less than the first threshold 432 in any region within the frame, the detection unit 443 determines that a moving object has not been detected in the frame (step S805: No) and ends the detection of the moving object. If there is a region within the frame where the moving object detection score is equal to or greater than the first threshold 432, the detection unit 443 determines that a moving object has been detected in the frame (step S805: Yes).

[0063] When the second measurement unit 845 determines that a moving object has been detected (step S805: Yes), it calculates the luminance of the frame in which the moving object has been detected (step S806). Next, the third setting unit 846 sets a third threshold value 833 based on the luminance of the frame calculated in step S806 (step S807) and stores the third threshold value 833 in the storage unit 730. Next, the masking unit 444 determines whether or not masking is required for the image detected in step S805 (step S808). If the number of pixels calculated in step S806 is less than the third threshold value 833, the masking unit 444 determines that masking is not required for the image (step S808: No) and terminates the masking process. If the number of pixels calculated in step S806 is equal to or greater than the third threshold value 833, the masking unit 444 determines that masking is required for the image (step S808: Yes) and performs the masking process (step S809).

[0064] As described above, the moving object detection device 800 according to the fifth embodiment determines whether or not masking is required by setting the third threshold value 833 based on the luminance of the frame, and therefore can accurately detect images that require masking. In the fifth embodiment, the brightness of a frame is calculated by calculating the luminance of the frame. However, the brightness of a frame may be calculated by other methods. For example, the brightness of a frame may be calculated based on the brightness of the frame or may be calculated from the time when the frame was captured.

[0065] When calculating the frame brightness based on the frame brightness, the second measurement unit 845 calculates the brightness of the frames constituting the video acquired by the acquisition unit 441. The frame brightness is a numerical value indicating the brightness within the frame and is calculated using existing technology. In this case, the third setting unit 846 sets the third threshold 833 based on the frame brightness and stores it in the storage unit 730. When the frame brightness is equal to or greater than a predetermined value, the third setting unit 846 sets the third threshold 833 lower than when the frame brightness is less than the predetermined value. When the frame brightness is less than the predetermined value, the third setting unit 846 sets the third threshold 833 higher than when the frame brightness is equal to or greater than the predetermined value.

[0066] When calculating the brightness of a frame based on the time the frame was captured, the third setting unit 846 sets the third threshold 833 based on the time the frame was captured and stores the third threshold 833 in the storage unit 730. Specifically, for example, when a frame was captured between 6:00 AM and 5:00 PM, i.e., when the frame was captured during the daytime, the third setting unit 846 sets the third threshold 833 lower than when the frame was captured at night. When a frame was captured between 5:00 PM and 6:00 AM, i.e., when the frame was captured at night, the third setting unit 846 sets the third threshold 833 higher than when the frame was captured during the daytime.

[0067] Although the above-described embodiment has been described as a hardware configuration, the present disclosure is not limited to this. Any processing in the present disclosure can also be realized by causing a CPU to execute a computer program.

[0068] In the above examples, the program can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-RWs, DVDs (Digital Versatile Discs), and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program may also be supplied to a computer by various types of transitory computer-readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path.

[0069] The present disclosure is not limited to the above-described embodiments, and may be modified as appropriate without departing from the spirit and scope of the present disclosure. In addition, the present disclosure may be implemented by appropriately combining the respective embodiments.

[0070] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes.

[0071] (Appendix A1) A moving body detection device comprising: an acquisition unit that acquires captured video; a first setting unit that sets moving body detection conditions based on related information including information related to the video; and a detection unit that detects moving bodies from frames that constitute the video based on the moving body detection conditions.

[0072] (Appendix A2) The moving body detection device according to Appendix A1, wherein the acquisition unit further acquires vehicle information including information recorded in the vehicle, and the first setting unit sets a moving body detection condition based on the related information and the vehicle information.

[0073] (Appendix A3) The moving body detection device described in Appendix A1, wherein the first setting unit calculates a variance of the frame and sets a first threshold indicating a threshold of a moving body detection score for determining that a moving body is captured based on the variance, and the detection unit calculates a moving body detection score for the frame and detects a moving body from the frame based on the first threshold.

[0074] (Appendix A4) A moving body detection device as described in Appendix A1, further comprising: a first measurement unit that calculates the number of pixels in an image of the detected moving body; a second setting unit that sets a second threshold indicating a threshold value for the number of pixels for determining whether or not masking processing is required for the image; and a masking unit that performs masking processing on the image when the number of pixels is equal to or greater than the second threshold.

[0075] (Appendix A5) The moving object detection device described in Appendix A4, wherein the first setting unit calculates a variance of the frame and sets a first threshold indicating a threshold of a moving object detection score for determining that a moving object is captured based on the variance, and the second setting unit sets a second threshold based on the variance and the number of pixels.

[0076] (Appendix A6) The moving body detection device described in Appendix A4, wherein the acquisition unit further acquires vehicle information including information recorded in the vehicle in which the video was taken, and the second setting unit sets the second threshold based on at least one of the related information and the vehicle information.

[0077] (Appendix A7) The moving body detection device described in Appendix A1 further comprises: a second measurement unit that calculates the brightness of an image of the detected moving body; a third setting unit that sets a third threshold value indicating a brightness threshold value for determining whether or not masking processing is required for the image based on the related information; and a masking unit that performs masking processing on the image when the brightness is equal to or greater than the third threshold value.

[0078] (Appendix B1) A moving object detection system comprising: an imaging device installed in a vehicle that captures video of the area around the vehicle; and a moving object detection device that can communicate with the imaging device, wherein the moving object detection device acquires the video captured by the imaging device, sets moving object detection conditions based on related information including information related to the video, and detects moving objects from frames that make up the video based on the moving object detection conditions.

[0079] (Appendix B2) The moving object detection system described in Appendix B1, wherein the moving object detection device calculates the variance of the frame, sets a first threshold indicating a threshold value of the moving object detection score for determining that a moving object is captured based on the variance, calculates the moving object detection score for the frame, and detects a moving object from the frame based on the first threshold.

[0080] (Appendix C1) A moving object detection method, in which a computer acquires a captured image, sets moving object detection conditions based on related information including information related to the image, and detects a moving object from frames constituting the image based on the moving object detection conditions.

[0081] (Appendix D1) A non-transitory computer-readable medium storing a moving object detection program that causes a computer to execute the following processes: acquiring captured video; setting moving object detection conditions based on related information including information related to the video; and detecting moving objects from frames that constitute the video based on the moving object detection conditions.

[0082] Although the present invention has been described above with reference to the embodiments (and examples), the present invention is not limited to the above-described embodiments (and examples). Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0083] 10 Frame 20 Moving object 30 Area 100 Moving object detection device 110 Acquisition unit 120 First setting unit 130 Detection unit 200 Moving object detection system 300 Imaging device 301 Imaging unit 302 Communication unit 310 Vehicle 320 Recording device 321 Measurement unit 322 Communication unit 400 Moving object detection device 410 Memory 420 Communication unit 430 Storage unit 431 Program 432 First threshold 440 Control unit 441 Acquisition unit 442 First setting unit 443 Detection unit 444 Masking unit 500 Network 600 Moving object detection system 700 Moving object detection device 730 Storage unit 733 Second threshold 740 Control unit 745 First measurement unit 746 Second setting unit 800 Moving object detection device 830 Storage unit 833 Third threshold 840 Control unit 845 Second measurement unit 846 Third setting unit

Claims

1. An acquisition means for acquiring the captured video; a first setting means for setting a moving object detection condition based on related information including information related to the video; a detection means for detecting a moving object from frames constituting the video based on the moving object detection conditions, Mobile object detection device.

2. the first setting means calculates a variance of the frame, and sets a first threshold indicating a threshold of a moving object detection score for determining that a moving object is captured based on the variance; the detection means calculates a moving object detection score for the frame, and detects a moving object from the frame based on the first threshold; The moving body detection device according to claim 1 .

3. a first measuring means for calculating the number of pixels in an image of the detected moving object; a second setting means for setting a second threshold value indicating a threshold value of the number of pixels for determining whether or not masking processing is required for the image; and a masking unit that performs a masking process on the image when the number of pixels is equal to or greater than the second threshold value. The moving body detection device according to claim 1 .

4. the first setting means calculates a variance of the frame, and sets a first threshold indicating a threshold of a moving object detection score for determining that a moving object is captured based on the variance; the second setting means sets a second threshold based on the variance and the number of pixels. The moving body detection device according to claim 3 .

5. The acquisition means further acquires vehicle information including information recorded in the vehicle in which the video was taken, the second setting means sets the second threshold value based on at least one of the related information and the vehicle information. The moving body detection device according to claim 3 .

6. a second measuring means for calculating the brightness of an image of the detected moving object; a third setting means for setting a third threshold value indicating a brightness threshold value for determining whether or not a masking process is required for the image based on the related information; and a masking unit that performs a masking process on the image when the brightness is equal to or greater than the third threshold value. The moving body detection device according to claim 1 .

7. A camera that captures images of the surrounding area; a moving object detection device capable of communicating with the photographing device, The moving object detection device Acquire an image captured by the imaging device; setting a moving object detection condition based on related information including information related to the video; detecting a moving object from the frames constituting the video based on the moving object detection condition; Mobile object detection system.

8. The moving object detection device calculating a variance of the frame, and setting a first threshold indicating a threshold of a moving object detection score for determining that a moving object is captured based on the variance; calculating a moving object detection score for the frame, and detecting a moving object from the frame based on the first threshold; The moving object detection system according to claim 7 .

9. The computer Obtain the captured footage, setting a moving object detection condition based on related information including information related to the video; detecting a moving object from the frames constituting the video based on the moving object detection condition; Mobile object detection method.

10. On the computer, A process of acquiring the captured video; A process of setting a moving object detection condition based on related information including information related to the video; a process of detecting a moving object from frames constituting the video based on the moving object detection conditions; A moving object detection program that executes the above.