Object detection device

Abstract

To effectively reduce a computation source required to detect a specific object included in an image.SOLUTION: An object detection device 10 according to one embodiment comprises: a first detection unit 12 that executes object detection on a first frame F1 of an image and detects an object region A1 in which a human body 20 is present in the first frame F1; a second detection unit 13 that executes moving body detection on a second frame F2 after the first frame F1 and acquires detection result information including a detection result of a moving body on the inner side and the outer side of the object region A1; and a control unit that determines whether it is possible to estimate an object region A2 in which the human body 20 is present in the second frame F2 on the basis of the object region A1 and the detection result information, controls the first detection unit 12 so as not to execute object detection on the second frame F2 when the object region A2 can be estimated, and causes the first detection unit 12 to execute object detection on the second frame F2 to detect the object region A2 when the object region A2 cannot be estimated.SELECTED DRAWING: Figure 1

Description

Technical Field

[0001] One aspect of the present invention relates to an object detection device.

Background Art

[0002] Patent Document 1 discloses a method for improving the detection accuracy of whether a human body has passed through a predetermined line segment (detection line) based on the detection results of both moving object detection and human body detection. Patent Document 2 discloses a method for obtaining an image that does not include a protected object (human body) by synthesizing a separate image (for example, an image subjected to blurring processing, watermarking processing, mosaic processing, filling processing, etc.) in both the region detected by moving object detection and the region detected by human body detection.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the methods described in the above Patent Documents 1 and 2, basically, in order to detect a specific object (human body), object detection (human body detection) is performed together with moving object detection at each detection timing. Here, object detection requires a larger processing load (computation amount) compared to moving object detection. Therefore, if it is possible to detect (estimate) the region where a specific object exists while reducing the execution frequency of object detection, the computational resources (resources) required to detect a specific object included in the video can be effectively reduced. Patent Documents 1 and 2 do not disclose any such mechanism.

[0005] Therefore, one aspect of the present invention aims to provide an object detection device that can effectively reduce the computational resources required to detect a specific object included in a video.

Means for Solving the Problems

[0006] An object detection device according to one aspect of the present invention includes a first detection unit that detects a first object region, which is a region where a predetermined specific object exists in a first frame, by performing object detection on the first frame of the video; a second detection unit that acquires detection result information including a detection result of a moving object inside the first object region and a detection result of a moving object outside the first object region by performing moving object detection on a second frame later than the first frame; and a control unit that determines whether a second object region, which is a region where a specific object exists in the second frame, can be estimated based on the first object region and the detection result information, controls the first detection unit not to perform object detection on the second frame when it is determined that the second object region can be estimated, and causes the first detection unit to perform object detection on the second frame to detect the second object region when it is not determined that the second object region can be estimated.

[0007] In the object detection device according to one aspect of the present invention, when the second object region, which is a region where a specific object exists in the second frame, can be estimated based on the first object region obtained by object detection on the first frame by the first detection unit and the detection result information obtained by moving object detection on the second frame by the second detection unit, the process of object detection on the second frame by the first detection unit is omitted. Therefore, according to the object detection device according to one aspect of the present invention, the computational resources required to detect a specific object included in a video can be effectively reduced.

Effects of the Invention

[0008] According to one aspect of the present invention, it is possible to provide an object detection device that can effectively reduce the computational resources required to detect a specific object included in a video.

Brief Description of the Drawings

[0009]

Figure 1

Figure 2

Figure 3

Figure 4

Embodiments for Carrying Out the Invention

[0010] Hereinafter, an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In the description of the drawings, the same or corresponding elements are denoted by the same reference numerals, and redundant descriptions are omitted.

[0011] FIG. 1 is a diagram showing an example of an object detection device 10 according to an embodiment. The object detection device 10 is a device that detects a predetermined specific object from images (videos) sequentially acquired by an imaging unit such as a camera that is installed (fixed) at a predetermined location (for example, a monitoring area) and has a fixed imaging direction. In this embodiment, as an example, the specific object is a human body. However, the specific object may be a living thing other than a human, such as a dog or a cat, or a non-living thing such as a robot. The object detection device 10 is configured to detect (estimate) an object area that is an area where a human body (specific object) exists in the image. In this embodiment, as an example, a rectangular area including a human body is detected as the object area. However, the shape of the object area is not limited to the above, and may be a shape corresponding to the shape of the detected human body. For example, the outer edge of the object area may be set along the boundary line between the detected human body and the background.

[0012] The object detection device 10 is used, for example, in a system for monitoring a certain location while protecting the privacy of people captured in an image. As an example, the object detection device 10 can function as part of a system that detects an area containing privacy information (in this embodiment, an object area in which a human body is captured) included in an image, and replaces the detected object area (privacy information) with another image to protect the privacy of the people captured in the image. However, the use of the object detection device 10 is not limited to the above.

[0013] As shown in FIG. 1, the object detection device 10 includes an image acquisition unit 11, a first detection unit 12, a second detection unit 13, and a control unit 14.

[0014] The image acquisition unit 11 sequentially acquires images at predetermined intervals from an imaging unit such as a camera installed (fixed) at a predetermined location (for example, a monitoring area). The images sequentially acquired by the image acquisition unit 11 (that is, the frames constituting the video (moving image)) are provided to the first detection unit 12 and the second detection unit 13. Note that the above imaging unit may be provided in the object detection device 10 itself, or may be an external device configured to be capable of data communication with the object detection device 10.

[0015] As shown in FIG. 2, the first detection unit 12 detects an object area A1 (first object area), which is an area where the human body 20 (specific object) exists in the first frame F1, by performing object detection on the first frame F1 of the video. The first detection unit 12 detects the object area A1 by using a known method such as pattern matching, for example. The first detection unit 12 detects the human body 20 shown in the first frame F1 by comparing the first frame F1 with a previously prepared pattern image, for example, and specifies the object area A1 including the human body 20. However, the method of object detection by the first detection unit 12 is not limited to the above example, and various known methods can be used. For example, the first detection unit 12 may input the first frame F1 (feature amount of the first frame F1) into a machine learning model learned by deep learning or the like, and acquire the output result from the machine learning model as the object area A1.

[0016] The second detection unit 13 executes moving object detection on a second frame F2 after the first frame F1, thereby obtaining detection result information including the detection result of moving objects inside the object region A1 and the detection result of moving objects outside the object region A1. The frame interval between the first frame F1 and the second frame F2 (that is, the number of frames existing between the first frame F1 and the second frame F2) can be arbitrarily set in advance. More specifically, the frame interval can be arbitrarily set according to the frequency of performing object detection on the video (the interval of detection timings). The second detection unit 13 detects moving objects shown in the second frame F2 by using a known method such as a background subtraction method or a statistical background subtraction method. For example, the second detection unit 13 detects moving objects shown in the second frame F2 based on a comparison between the second frame F2 and one or more frames acquired in the past compared to the second frame F2. Note that the detected moving object may be a human body 20 or an object other than the human body 20. By moving object detection alone, it is not possible to determine whether the detected moving object is a human body 20.

[0017] As described above, various methods can be used for object detection (human body detection) by the first detection unit 12 and moving object detection by the second detection unit 13. Generally, however, object detection requires more computational resources than moving object detection. Therefore, in the object detection device 10, in a case where object detection (the process of the first detection unit 12) can be omitted in order to reduce computational resources, it is configured to actively omit the execution of object detection. Specifically, the object detection device 10 has a control unit 14 described later.

[0018] The control unit 14 determines whether it is possible to estimate an object area A2 (second object area), which is an area where the human body 20 (specific object) exists in the second frame F2, based on the object area A1 and the detection result information obtained by the second detection unit 13. When it is determined that the object area A2 in the second frame F2 can be estimated, the control unit 14 controls the first detection unit 12 so as not to perform object detection on the second frame F2. On the other hand, when it is not determined that the object area A2 in the second frame F2 can be estimated, the control unit 14 causes the first detection unit 12 to perform object detection to detect the object area A2. That is, when the object area A2 in the second frame F2 can be estimated without performing object detection by the first detection unit 12, the control unit 14 has a mechanism for reducing computational resources by omitting the execution of object detection.

[0019] FIG. 2 is a diagram schematically showing an object detection pattern (i.e., a control pattern of the control unit 14) by the object detection device 10. With reference to FIG. 2, specific examples (patterns 1 to 4) of the control pattern of the control unit 14 described above will be described.

[0020] (Pattern 1) As shown in the uppermost row of FIG. 2, pattern 1 corresponds to a case where the detection result information indicates that no moving object is detected both inside and outside the object area A1. For example, as shown in P11 of FIG. 2, pattern 1 is a case where the second frame F2 has hardly changed from the first frame F1. In this case, it is estimated that the human body 20 detected in the first frame F1 continues to exist in the object area A1 also in the second frame F2. Therefore, in this case, as shown in P12 of FIG. 2, the control unit 14 determines that the area where the human body 20 exists in the second frame F2 (i.e., the object area A2) can be estimated, and determines the same area as the object area A1 as the object area A2.

[0021] According to the control of Pattern 1, when the probability that the human body 20 detected in the first frame F1 continues to exist in the object region A1 in the second frame F2 is high, by omitting object detection (the process of the first detection unit 12), the computational resources required to detect the human body in the second frame F2 can be effectively reduced.

[0022] (Pattern 2) As shown in the second row from the top in FIG. 2, Pattern 2 corresponds to the case where the detection result information indicates that a moving object is detected inside the object region A1. For example, as shown in P21 in FIG. 2, Pattern 2 is the case where the human body 20 detected in the object region A1 in the first frame F1 moves to such an extent that it is detected as a moving object by the second detection unit 13. In this case, it is presumed that the human body 20 detected in the first frame F1 continues to exist in the object region A1 in the second frame F2 and is moving inside the object region A1. Therefore, in this case, as shown in P22 in FIG. 2, the control unit 14 determines that, similar to Pattern 1, it is possible to estimate the region where the human body 20 exists in the second frame F2 (that is, the object region A2), and determines the region identical to the object region A1 as the object region A2.

[0023] According to the control of Pattern 2, similar to Pattern 1, when the probability that the human body 20 detected in the first frame F1 continues to exist in the object region A1 in the second frame F2 is high, by omitting object detection (the process of the first detection unit 12), the computational resources required to detect the human body in the second frame F2 can be effectively reduced.

[0024] (Pattern 3) As shown in the third row from the top in FIG. 2, Pattern 3 is the case where the detection result information indicates that a moving object is detected outside the object region A1, and the detected moving object is determined to be the same object as the human body 20 that existed in the object region A1 in the first frame F1.

[0025] As shown in P31 of FIG. 2, when the detection result information indicates that a moving object has been detected outside the object region A1, the control unit 14 determines whether the detected moving object is the same object as the human body 20 that existed in the object region A1 in the first frame F1. For example, the control unit 14 uses a known object tracking method to determine whether the moving object detected by the second detection unit 13 in the second frame F2 is the same object as the human body 20 detected by the first detection unit 12 in the first frame F1.

[0026] As shown in P32 of FIG. 2, Pattern 3 corresponds to the case where, in the above determination process, it is determined that the moving object detected in the second frame F2 is the same object as the human body 20 detected in the object region A1 in the first frame F1 (in other words, when the above object tracking is successful). In this case, even if object detection is not performed on the second frame F2, the region including the moving object detected in the second frame F2 (for example, a region set to the same size and shape as the object region A1) can be determined as the region where the human body 20 is presumed to exist in the second frame F2 (that is, the object region A2). Therefore, in this case, as shown in P33 of FIG. 2, the control unit 14 determines that the region where the human body 20 exists (that is, the object region A2) can be estimated in the second frame F2, and determines the region where the moving object is detected in the second frame F2 as the object region A2. That is, the control unit 14 updates the region where the human body 20 is presumed to exist from the object region A1 where the human body 20 was detected by object detection in the first frame F1 to the object region A2 where the moving object was detected by moving object detection in the second frame F2.

[0027] According to the control of Pattern 3, when the probability that the moving object detected outside the object region A1 in the second frame F2 is the same object as the human body 20 detected in the first frame F1 is high, the region where the moving object is detected is set as the object region A2 and object detection (the process of the first detection unit 12) is omitted, so that the computational resources required to detect the human body in the second frame F2 can be effectively reduced.

[0028] (Pattern 4) As shown in the lowermost row of FIG. 2, pattern 4 corresponds to the case where the detection result information indicates that a moving object has been detected outside the object region A1, and the detected moving object is not determined to be the same object as the human body 20 that existed in the object region A1 in the first frame F1.

[0029] As shown in P41 of FIG. 2, when the detection result information indicates that a moving object has been detected outside the object region A1, the control unit 14 determines, in the same manner as in pattern 3, whether the detected moving object is the same object as the human body 20 that existed in the object region A1 in the first frame F1.

[0030] As shown in P42 of FIG. 2, pattern 4 corresponds to the case where, in the above-described determination process, the moving object detected in the second frame F2 is not determined to be the same object as the human body 20 detected in the object region A1 in the first frame F1 (in other words, when the above-described object tracking fails). Note that cases where the object tracking fails as described above may include cases where the moving object detected in the second frame F2 is actually different from the human body 20, or cases where the moving object detected in the second frame F2 is actually the same object as the human body 20, but the object tracking fails due to, for example, the large movement of the human body 20.

[0031] When the object tracking fails as described above, since the moving object detected outside the object region A1 in the second frame F2 may be different from the human body 20, the region where the moving object is detected cannot be set as the object region A2. That is, in order to detect the human body 20 with a certain degree of accuracy in the second frame F2, it is necessary to perform object detection (human body detection) on the second frame F2. Therefore, in this case, as shown in P43 of FIG. 2, the control unit 14 determines that the region where the human body 20 exists (that is, the object region A2) cannot be estimated in the second frame F2, and causes the first detection unit 12 to perform object detection on the second frame F2 to detect the object region A2.

[0032] According to the control of Pattern 4, when the probability that a moving object detected outside the object region A1 in the second frame F2 is the same object as the human body 20 detected in the first frame F1 is low, and object detection is necessary to detect the human body 20 within the second frame F2, object detection can be appropriately executed.

[0033] Next, with reference to FIG. 3, an example of the operation of the object detection device 10 will be described.

[0034] In step S1, the image acquisition unit 11 acquires the first frame F1 from an external device different from the object detection device 10 or an imaging unit such as a camera included in the object detection device 10.

[0035] In step S2, the first detection unit 12 detects an object region A1 (first object region), which is a region where the human body 20 (specific object) exists in the first frame F1, by performing object detection on the first frame F1.

[0036] In step S3, the image acquisition unit 11 acquires the second frame F2 from the imaging unit. When the first frame F1 and the second frame F2 are not consecutive to each other, the image acquisition unit 11 also acquires video data (each frame) from the imaging unit between acquiring the first frame F1 and acquiring the second frame F2.

[0037] In step S4, the second detection unit 13 executes moving object detection on the second frame F2 after the first frame F1 to obtain detection result information including the detection result of the moving object inside the object region A1 and the detection result of the moving object outside the object region A1.

[0038] In step S5, the control unit 14 determines whether or not a moving object is not detected both inside and outside the object region A1 in the second frame F2. When the result of the above determination is "YES" (that is, when it corresponds to Pattern 1 in FIG. 2), the control unit 14 executes the process of step S6.

[0039] In step S6, when the control unit 14 determines that the area where the human body 20 exists in the second frame F2 (i.e., the object area A2) can be estimated, it determines the area identical to the object area A1 as the object area A2.

[0040] On the other hand, when the result of the determination in step S5 is "NO", the control unit 14 executes the process of step S7.

[0041] In step S7, the control unit 14 determines whether a moving object is detected inside the object area A1. When the result of the above determination is "YES" (i.e., corresponding to pattern 2 in FIG. 2), the control unit 14 executes the process of step S6 described above. When the result of the above determination is "NO", the control unit 14 executes the process of step S8. Note that the determination result of "NO" in step S7 means that a moving object is detected outside the object area A1 in the second frame F2.

[0042] In step S8, the control unit 14 determines whether the moving object detected outside the object area A1 in the second frame F2 is the same object as the human body 20 that existed in the object area A1 in the first frame F1. For example, the control unit 14 executes the above determination by performing the object tracking described above. When the result of the above determination is "YES" (i.e., corresponding to pattern 3 in FIG. 2), the control unit 14 executes the process of step S9.

[0043] In step S9, when the control unit 14 determines that the area where the human body 20 exists in the second frame F2 (i.e., the object area A2) can be estimated, it determines the area where the moving object is detected in the second frame F2 as the object area A2 (see P33 in FIG. 2).

[0044] On the other hand, when the result of the determination in step S8 is "NO" (i.e., corresponding to pattern 4 in FIG. 2), the control unit 14 executes the process of step S10.

[0045] In step S10, when the control unit 14 determines that it is impossible to estimate the area where the human body 20 exists in the second frame F2 (i.e., the object area A2), the control unit 14 causes the first detection unit 12 to perform object detection on the second frame F2 to detect the object area A2 (see P43 in FIG. 2).

[0046] The above series of processes (steps S1 to S10) can be repeatedly executed while the image acquisition unit 11 continues to acquire video. That is, after the above series of processes (steps S1 to S10) are completed, the second frame F2 in the above series of processes is set as the first frame F1 in the next series of processes, and the object area A2 determined in the second frame F2 in the above series of processes is set as the object area A1 in the next series of processes. Then, the next series of processes are executed.

[0047] In the object detection device 10 described above, when the object area A2, which is the area where the human body 20 (specific object) exists in the second frame F2, can be estimated based on the detection result (i.e., the object area A1) obtained by the human body detection (object detection) of the first frame F1 by the first detection unit 12 and the detection result information obtained by the moving object detection of the second frame F2 by the second detection unit 13, the process of object detection of the second frame F2 by the first detection unit 12 is omitted. Therefore, according to the object detection device 10, the computing resources required to detect the human body 20 included in the video can be effectively reduced.

[0048] The object detection device 10 of the present disclosure has the following configuration.

[0049] [1] A first detection unit that detects a first object area, which is an area where a predetermined specific object exists in the first frame, by performing object detection on the first frame of the video; A second detection unit that acquires detection result information including the detection result of a moving object inside the first object area and the detection result of a moving object outside the first object area by performing moving object detection on a second frame after the first frame; Determine whether it is possible to estimate a second object region, which is a region where the specific object exists in the second frame, based on the first object region and the detection result information. When it is determined that the second object region can be estimated, control the first detection unit so as not to perform object detection on the second frame. When it is not determined that the second object region can be estimated, control the first detection unit to perform object detection on the second frame to detect the second object region. A control unit An object detection device comprising

[0050] [2] When the detection result information indicates that no moving object is detected both inside and outside the first object region, the control unit determines that the second object region can be estimated and determines the same region as the first object region as the second object region. The object detection device according to [1].

[0051] [3] When the detection result information indicates that a moving object is detected inside the first object region, the control unit determines that the second object region can be estimated and determines the same region as the first object region as the second object region. The object detection device according to [1] or [2].

[0052] [4] The control unit When the detection result information indicates that a moving object is detected outside the first object region, determine whether the detected moving object is the same object as the specific object that existed in the first object region in the first frame. When it is determined that the detected moving object is the same object as the specific object that existed in the first object region in the first frame, determine that the second object region can be estimated and determine the region where the moving object is detected in the second frame as the second object region. The object detection device according to any one of [1] to [3].

[0053] [5] The control unit When the detection result information indicates that a moving object is detected outside the first object area, determine whether the detected moving object is the same object as the specific object that existed in the first object area in the first frame. When it is not determined that the detected moving object is the same object as the specific object that existed in the first object area in the first frame, determine that the second object area cannot be estimated, and cause the first detection unit to perform object detection on the second frame to detect the second object area. The object detection device according to any one of [1] to [4].

[0054] Also, the block diagram used in the description of the above embodiment shows blocks of functional units. These functional blocks (constituent parts) are realized by any combination of at least one of hardware and software. Also, the method of realizing each functional block is not particularly limited. That is, each functional block may be realized using one physically or logically combined device, or two or more physically or logically separated devices may be directly or indirectly (for example, using wired, wireless, etc.) connected and realized using these multiple devices. The functional block may be realized by combining software with the above one device or the above multiple devices.

[0055] Functions include, but are not limited to, judgment, decision, determination, calculation, computation, processing, derivation, investigation, search, confirmation, reception, transmission, output, access, solution, selection, selection, establishment, comparison, assumption, expectation, regarded as, notification (broadcasting), notification (notifying), communication (communicating), forwarding, configuration (configuring), reconfiguration (reconfiguring), allocation (allocating, mapping), assignment (assigning), etc.

[0056] For example, the object detection device 10 in one embodiment of the present disclosure may function as a computer that performs the object detection method of the present disclosure. FIG. 4 is a diagram showing an example of the hardware configuration of the object detection device 10 according to one embodiment of the present disclosure. Physically, the object detection device 10 may be configured as a computer device including a processor 1001, a memory 1002, a storage 1003, a communication device 1004, an input device 1005, an output device 1006, a bus 1007, and the like.

[0057] In the following description, the term "device" can be read as a circuit, a device, a unit, or the like. The hardware configuration of the object detection device 10 may be configured to include one or more of each device shown in FIG. 4, or may be configured without including some of the devices.

[0058] Each function in the object detection device 10 is realized by causing the processor 1001 to read a predetermined software (program) onto hardware such as the processor 1001 and the memory 1002, so that the processor 1001 performs calculations and controls communication by the communication device 1004, or controls at least one of reading and writing data in the memory 1002 and the storage 1003.

[0059] The processor 1001 controls the entire computer by operating an operating system, for example. The processor 1001 may be constituted by a central processing unit (CPU) including an interface with peripheral devices, a control device, an arithmetic device, a register, and the like.

[0060] Also, the processor 1001 reads a program (program code), software module, data, etc. from at least one of the storage 1003 and the communication device 1004 into the memory 1002, and executes various processes according to these. As the program, a program that causes a computer to execute at least a part of the operations described in the above embodiments is used. For example, each functional unit (e.g., the control unit 14, etc.) of the object detection device 10 may be stored in the memory 1002 and realized by a control program operating in the processor 1001, and the same may be true for other functional blocks. Although it has been described that the above various processes are executed by one processor 1001, they may be executed simultaneously or sequentially by two or more processors 1001. The processor 1001 may be implemented by one or more chips. Note that the program may be transmitted from a network via a telecommunication line.

[0061] The memory 1002 is a computer-readable recording medium, and may be constituted by at least one of, for example, ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), RAM (Random Access Memory), etc. The memory 1002 may be referred to as a register, cache, main memory (main storage device), etc. The memory 1002 can store a program (program code), software module, etc. executable for implementing the object detection method according to an embodiment of the present disclosure.

[0062] Storage 1003 is a computer-readable recording medium and may be composed of at least one of, for example, optical discs such as CD-ROM (Compact Disc ROM), hard disk drives, flexible disks, magneto-optical disks (e.g., compact discs, digital versatile discs, Blu-ray (registered trademark) discs), smart cards, flash memories (e.g., cards, sticks, key drives), floppy (registered trademark) disks, magnetic strips, etc. Storage 1003 may also be referred to as an auxiliary storage device. The above-described storage medium may be, for example, a database, a server, or other appropriate media including at least one of memory 1002 and storage 1003.

[0063] Communication device 1004 is hardware (a transmission / reception device) for performing communication between computers via at least one of a wired network and a wireless network, and is also referred to as, for example, a network device, a network controller, a network card, a communication module, etc.

[0064] Input device 1005 is an input device (e.g., a keyboard, a mouse, a microphone, a switch, a button, a sensor, etc.) for receiving an external input. Output device 1006 is an output device (e.g., a display, a speaker, an LED lamp, etc.) for performing an output to the outside. Note that input device 1005 and output device 1006 may have an integrated configuration (e.g., a touch panel).

[0065] Also, each device such as processor 1001 and memory 1002 is connected by a bus 1007 for communicating information. Bus 1007 may be configured using a single bus or may be configured using different buses for each device.

[0066] In addition, the object detection device 10 may be configured to include hardware such as a microprocessor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a field programmable gate array (FPGA), and some or all of the functional blocks may be realized by the hardware. For example, the processor 1001 may be implemented using at least one of these hardware components.

[0067] As described above in detail for this embodiment, it is obvious to those skilled in the art that this embodiment is not limited to the embodiments described in this specification. This embodiment can be implemented as a modified and changed form without departing from the spirit and scope of the present invention as defined by the claims. Therefore, the description in this specification is for the purpose of illustration and has no restrictive meaning for this embodiment.

[0068] The processing procedures, sequences, flowcharts, etc. of each aspect / embodiment described in this disclosure may be reordered as long as there is no contradiction. For example, for the methods described in this disclosure, the elements of various steps are presented using an exemplary order and are not limited to the specific order presented.

[0069] The input and output information, etc. may be stored in a specific location (e.g., memory) or may be managed using a management table. The input and output information, etc. may be overwritten, updated, or appended. The output information, etc. may be deleted. The input information, etc. may be transmitted to other devices.

[0070] The determination may be made based on a value represented by 1 bit (0 or 1), a boolean value (true or false), or a numerical comparison (e.g., comparison with a predetermined value).

[0071] Each aspect / embodiment described in the present disclosure may be used alone, in combination, or switched and used during execution. Further, the notification of predetermined information (for example, the notification of "being X") is not limited to being explicitly performed, and may be performed implicitly (for example, by not performing the notification of the predetermined information).

[0072] Software should be broadly interpreted to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software modules, applications, software applications, software packages, routines, subroutines, objects, executable files, execution threads, procedures, functions, etc., whether called software, firmware, middleware, microcode, a hardware description language, or by any other name.

[0073] Also, software, instructions, information, etc. may be transmitted and received via a transmission medium. For example, when software is transmitted from a website, server, or other remote source using at least one of wired technologies (such as coaxial cables, optical fiber cables, twisted pairs, digital subscriber lines (DSLs), etc.) and wireless technologies (such as infrared rays, microwaves, etc.), at least one of these wired and wireless technologies is included within the definition of the transmission medium.

[0074] The information, signals, etc. described in the present disclosure may be represented using any of a variety of different technologies. For example, data, instructions, commands, information, signals, bits, symbols, chips, etc., which may be referred to throughout the above description, may be represented by voltages, currents, electromagnetic waves, magnetic fields or magnetic particles, optical fields or photons, or any combination thereof.

[0075] In addition, the information, parameters, etc. described in the present disclosure may be represented using absolute values, relative values from a predetermined value, or other corresponding information.

[0076] The names used for the above-described parameters are not limiting names in any way. Furthermore, the mathematical formulas, etc. using these parameters may be different from those explicitly disclosed in the present disclosure. Since various information elements can be identified by any suitable name, the various names assigned to these various information elements are not limiting names in any way.

[0077] In the present disclosure, the description "based on" does not mean "only based on" unless otherwise specified. In other words, the description "based on" means both "only based on" and "at least based on".

[0078] Any reference to an element using designations such as "first", "second", etc. used in the present disclosure does not generally limit the quantity or order of those elements. These designations can be used in the present disclosure as a convenient way to distinguish between two or more elements. Therefore, a reference to a first and a second element does not mean that only two elements can be adopted, or that the first element must precede the second element in some form.

[0079] In the present disclosure, when terms such as "include", "including" and their variants are used, these terms are intended to be inclusive, similar to the term "comprising". Furthermore, the term "or" used in the present disclosure is not intended to be an exclusive disjunction.

[0080] In the present disclosure, for example, when articles are added by translation, such as a, an and the in English, the present disclosure may include that the nouns following these articles are in the plural form.

[0081] In the present disclosure, the term "A and B are different" may mean that "A and B are different from each other". Note that the term may also mean that "A and B are each different from C". Terms such as "separate" and "coupled" may also be interpreted in the same way as "different".

Description of Reference Numerals

[0082] 10... Object detection device, 11... Image acquisition unit, 12... First detection unit, 13... Second detection unit, 14... Control unit, 20... Human body (specific object), A1... Object region (first object region), A2... Object region (second object region), F1... First frame, F2... Second frame.

Claims

1. A first detection unit that detects a first object region, which is a region where a specific object predetermined in the first frame exists, by performing object detection on the first frame of the video; A second detection unit that obtains detection result information including a detection result of a moving object inside the first object region and a detection result of a moving object outside the first object region by performing moving object detection on a second frame after the first frame; A control unit that determines whether a second object region, which is a region where the specific object exists in the second frame, can be estimated based on the first object region and the detection result information, controls the first detection unit not to perform object detection on the second frame when it is determined that the second object region can be estimated, and causes the first detection unit to perform object detection on the second frame to detect the second object region when it is not determined that the second object region can be estimated; An object detection device comprising the above.

2. When the detection result information indicates that no moving object is detected both inside and outside the first object region, the control unit determines that the second object region can be estimated and determines the same region as the first object region as the second object region. The object detection device according to Claim 1.

3. When the detection result information indicates that a moving object is detected inside the first object region, the control unit determines that the second object region can be estimated and determines the same region as the first object region as the second object region. The object detection device according to Claim 1.

4. The control unit When the detection result information indicates that a moving object is detected outside the first object region, determines whether the detected moving object is the same object as the specific object that existed in the first object region in the first frame; When it is determined that the detected moving object is the same object as the specific object that existed in the first object region in the first frame, determines that the second object region can be estimated and determines the region where the moving object is detected in the second frame as the second object region. The object detection device according to Claim 1.

5. The control unit When the detection result information indicates that a moving object is detected outside the first object region, it is determined whether the detected moving object is the same object as the specific object that existed in the first object region in the first frame. When it is not determined that the detected moving object is the same object as the specific object that existed in the first object region in the first frame, it is determined that the second object region cannot be estimated, and the first detection unit is caused to perform object detection on the second frame to detect the second object region. The object detection device according to claim 1.

Images