Information processing device, method, and program

Abstract

To provide an information processing device, a method, and a program that improve accuracy of person detection.SOLUTION: In an image processing system in which an image captured by an imaging device is obtained via a network or storage medium, an information processing device 10 includes: an image acquisition unit that obtains a plurality of images from the imaging device; an object detection unit that detects an object like a person in the images; a movement determination unit that determines whether the object is moving on the basis of, similarity between an object detection image where the object has been detected and a plurality of images other than object detection image; and a person detection determination unit that when the object is moving, determines the detected object is a person and that when the object is not moving, determines that the detected object is not a person.SELECTED DRAWING: Figure 3

Description

[Technical field]

[0001] The present invention relates to an information processing device, a method, and a program. [Background technology]

[0002] 2. Description of the Related Art Conventionally, there is known a technique for detecting an intruder by using a security or surveillance camera to detect a person who has invaded an office, a residence, a vehicle, or the like.

[0003] Patent Document 1 discloses a human detection technology in which the shape and size of a bounding box of a human body candidate detected from a fisheye image obtained by a fisheye camera are compared with predetermined shape and size standards. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2020-107070 A Summary of the Invention [Problem to be solved by the invention]

[0005] However, intruders in images captured by security and surveillance cameras may have parts of their bodies hidden (i.e., only parts of their bodies can be identified) or may be in various postures (for example, they may not only be standing, but also crouching or crawling). Therefore, when detecting intruders in images captured by security and surveillance cameras, there is a possibility that objects other than people in the image will be mistakenly detected when using the shape and size of the bounding box. Also, if there is a still object in the shape of a human, such as a mannequin, in the capture area, there is a possibility that it will be mistakenly detected as a person.

[0006] Therefore, an object of the present invention is to reduce erroneous detection of objects other than humans as humans and to detect humans with high accuracy. [Means for solving the problem]

[0007] An information processing apparatus according to an embodiment of the present invention includes an image acquisition unit that acquires a plurality of images from an imaging device, an object detection unit that detects a human-like object in the images, and an object detection image in which the object is detected. , the said The image processing device includes a motion determination unit that determines whether or not the object is moving based on whether the image is similar to a plurality of images other than the body detection image, and a human detection determination unit that determines that the detected object is a human if the object is moving, and determines that the detected object is not a human if the object is not moving. Effect of the Invention

[0008] According to the present invention, it is possible to reduce erroneous detection of objects other than humans as humans, and to detect humans with high accuracy. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram for explaining an overview according to one embodiment of the present invention. [Diagram 2] 1 is a diagram showing an overall system configuration according to an embodiment of the present invention; [Diagram 3] 1 is a functional block diagram of an information processing device according to an embodiment of the present invention; [Figure 4] 10 is a flowchart of a human detection determination process according to an embodiment of the present invention. [Diagram 5] 10 is a flowchart of a motion determination process according to an embodiment of the present invention. [Figure 6] FIG. 10 is a diagram for explaining motion determination according to an embodiment of the present invention. [Figure 7] 1 is a block diagram showing an example of a hardware configuration of an information processing device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the drawings.

[0011] FIG. 1 is a diagram for explaining an overview according to an embodiment of the present invention. In one embodiment of the present invention, an imaging device 20 is installed in a monitoring area. The imaging device 20 is equipped with a mechanism for detecting an intruder using a human sensor such as infrared rays or an image processing technology, and when it detects an object such as a person, it transmits a plurality of image data captured within a few seconds before and after the detection to a monitoring center. In an information processing device 10 in the monitoring center, when an object (specifically, an object assumed to be a person) is detected in the image data captured by the imaging device 20, the object detection area in which the object was detected is compared with an area of ​​other image data having the same coordinate position in the image data, and the similarity is calculated to detect the movement of the object. As a result, if the object moves, it can be determined that the object is a person, and if there is no movement, it can be determined that the object is not a person.

[0012] In step 1 (S1), a plurality of images are acquired, which are taken by a security camera, a surveillance camera, etc. After the images are acquired, the process proceeds to step 2.

[0013] In step 2 (S2), an object (specifically, an object assumed to be a person) is detected in the multiple images of S1. Here, it is assumed that an object has been detected, and the process proceeds to step 3.

[0014] In step 3 (S3), it is determined whether the detection score (detection reliability) of S2 is equal to or greater than a threshold value or less than the threshold value. If it is equal to or greater than the threshold value (S3: detection score is large), the process proceeds to step 6, where the object detected in S2 is determined to be a person. If it is less than the threshold value (S3: detection score is small), the process proceeds to step 4.

[0015] In step 4 (S4), it is determined whether the object detected in S2 is moving. If there is movement, the process proceeds to step 6, where the object detected in S2 is determined to be a person. If there is no movement, the process proceeds to step 5.

[0016] In step 5 (S5), if there is no movement of the object detected in S2 (S4: no movement), it is determined that the object detected in S2 is not a person.

[0017] In step 6 (S6), if the detection score (detection reliability) in S2 is equal to or greater than a threshold, or if the detection score (detection reliability) in S2 is smaller than a threshold and there is movement of the object detected in S2, it is determined that the object detected in S2 is a person.

[0018] Fig. 2 is a diagram showing the overall system configuration according to one embodiment of the present invention. As shown in Fig. 2, the image processing system 1 includes an information processing device 10 and an imaging device 20 such as a security or surveillance camera. The information processing device 10 can acquire images captured by the imaging device 20 via an arbitrary network or storage medium. Each of these will be described below.

[0019] When an object (specifically, an object assumed to be a person) is detected in an image captured by the imaging device 20, the information processing device 10 determines whether the object is a person or not. The information processing device 10 is a computer such as a server. The information processing device 10 will be described in detail later with reference to FIG. 3.

[0020] The imaging device 20 is a security camera or a surveillance camera that captures an image of a person who has invaded an office, a residence, a car, or the like. For example, when an intruder detection unit (not shown) such as an infrared sensor detects an object, the imaging device 20 records an image captured several seconds before and after the detection in an internal memory (not shown) and transmits the image to the information processing device 10. The infrared sensor or the like may be installed separately from the imaging device 20, and when the infrared sensor or the like detects an object, the imaging device 20 may be linked to capture an image of the target area. In addition, when the infrared sensor or the like transmits a detection signal to the information processing device 10, the information processing device 10 may request the imaging device 20 to transmit the captured image to itself according to the content of the detection signal.

[0021] Fig. 3 is a functional block diagram of an information processing device 10 according to an embodiment of the present invention. As shown in Fig. 3, the information processing device 10 can include an image acquisition unit 101, an object detection unit 102, a detection score determination unit 103, a movement determination unit 104 (having a similarity calculation unit 141 and a determination unit 142), and a human detection determination unit 105. In addition, the information processing device 10 can function as the image acquisition unit 101, the object detection unit 102, the detection score determination unit 103, the movement determination unit 104 (having a similarity calculation unit 141 and a determination unit 142), and the human detection determination unit 105 by executing a program.

[0022] The image acquiring unit 101 acquires a plurality of images (i.e., a video consisting of a plurality of frames (still images)) captured by the imaging device 20. Alternatively, the image acquiring unit 101 may receive a detection signal from the above-mentioned infrared sensor or the like, and request the imaging device 20 to transmit the captured images to itself according to the contents of the detection signal, and acquire the plurality of images transmitted by the imaging device 20 according to the request.

[0023] The object detection unit 102 detects an object (specifically, a body part or the whole body assumed to be a person) in each of the multiple images (i.e., each frame) acquired by the image acquisition unit 101. The object detection unit 102 stores coordinate information of an area (e.g., a rectangle) in which an object is detected in an image, and a detection score (detection reliability) in a memory or the like (not shown) in the information processing device 10. Hereinafter, an image (frame) in which the object detection unit 102 detects an object is also referred to as an object detection image, and an area in which an object is detected in an object detection image is also referred to as an object detection area.

[0024] For example, the object detection unit 102 can detect an object in an image by machine learning such as deep learning. Specifically, the object detection unit 102 inputs an image into a trained model that has previously trained images of the entire and partial human body using a neural network or the like, detects any object that is assumed to be a person in the image, and outputs the object detection area in the image and the detection score (detection reliability). Here, "detection of people and objects using anchor boxes" is shown as an example. For example, in object detection methods such as "Single Shot Multibox Detector (SSD)", "M2Det", and "Faster R-CNN", anchor boxes with multiple aspect ratios are applied to each cell of a feature map obtained by inputting an image, and candidates for "human rectangles" and "human detection scores" are obtained. After that, NMS (Non-Maximum Suppression) is applied, and if the overlap of the "human rectangles" is equal to or greater than a certain level, only rectangles with high "human detection scores" are left and output. There are various methods for human and object detection, but any method can be used as long as it outputs a "human rectangle (object detection area)" and a "human detection score."

[0025] Note that an object may be detected in one or more images (frames).

[0026] The detection score determination unit 103 determines whether or not the score of the detection by the object detection unit 102 (detection reliability (indicating the accuracy of prediction / output by machine learning)) is smaller than a threshold value.

[0027] The motion determination unit 104 determines whether or not there is motion of the object detected by the object detection unit 102. Specifically, the motion determination unit 104 determines whether or not there is motion of the object based on whether or not there is similarity between the object detection image (a frame in which an object assumed to be a person (human-like) is detected) and other images (i.e., other frames included in the video). The following describes the motion determination unit 104 separately as a similarity calculation unit 141 and a determination unit 142.

[0028] The similarity calculation unit 141 calculates the similarity between the object detection image (a frame in which a human-like object is detected) and another image (i.e., another frame included in the video). Specifically, the similarity calculation unit 141 compares an area in the object detection image in which an object is included (object detection area) with an area in the other image at the same coordinate position as the object detection area in the object detection image. The other frames may be all other frames included in the video, or may be some other frames included in the video. In a method of comparing the entire image to determine the similarity, since the size of a person in the entire image is generally small in many cases, the method of comparing and determining the similarity by focusing on the object detection area in the object detection image has the effect of making it easier to find the difference in similarity.

[0029] In addition, when a human-like object is detected in multiple images (frames), the similarity calculation unit 141 calculates the similarity between each object detection image (each frame) and each of the other images (i.e., other frames included in the video).

[0030] <<Calculating Similarity>> Here, the calculation of the similarity will be described in detail. For example, the similarity calculation unit 141 can use a method of ZNCC (Zero-mean Normalized Cross Correlation). For example, it is assumed that the similarity between a rectangle of M pixels x N pixels including an object and a rectangle of M pixels x N pixels in another image is calculated. The pixels (T(i,j) and I(i,j)) at the same coordinates of the two rectangles are used. The similarity calculation unit 141 calculates the similarity by:

[0031]

number

[0032]

number

[0033]

number

[0034]

number

[0035] The similarity is not limited to the ZNCC method, but may be calculated by any template matching method such as NCC (Normalized Cross-Correlation), SSD (Sum of Squared Difference), or SAD (Sum of Absolute Difference).

[0036] The determination unit 142 determines whether or not there are a predetermined number or more of other images whose similarity is equal to or less than the threshold for each object detection region in the object detection image in which the object detection unit 102 detects an object. Specifically, the determination unit 142 determines that there is object movement when the number of other images whose similarity is equal to or less than the threshold is equal to or more than the predetermined number in at least one object detection region. The determination unit 142 determines that there is no object movement when the number of other images whose similarity is equal to or less than the threshold is less than the predetermined number in all object detection regions. The predetermined number may be one or may be two or more. In addition, when there are multiple object detection regions in the same object detection image, these determination processes are performed for each object detection region, and if the number of other images whose similarity is equal to or less than the threshold is equal to or more than the predetermined number in at least one object detection region, it can be determined that there is object movement.

[0037] The human detection determination unit 105 determines that the object detected by the object detection unit 102 is a human because the object is moving, or determines that the object detected by the object detection unit 102 is not a human because the object is not moving.

[0038] <Method> Hereinafter, the human detection determination process will be described with reference to FIG. 4, and the movement determination process will be described with reference to FIG.

[0039] FIG. 4 is a flowchart of a human detection and determination process according to an embodiment of the present invention.

[0040] In step 11 (S11), the image acquisition unit 101 acquires a plurality of images captured by the imaging device 20 (that is, a moving image made up of a plurality of frames (still images)).

[0041] In step 12 (S12), the object detection unit 102 detects an object assumed to be a person (human-like) in each of the multiple images (i.e., each frame) acquired in S11. Note that an object may be detected in one or more images (frames). If an object is detected, the process proceeds to step 13, and if a human-like object is not detected, the process ends.

[0042] In step 13 (S13), the detection score determination unit 103 determines whether the detection score (detection reliability) of S12 is smaller than a threshold value. If it is determined that it is less than the threshold value, the process proceeds to step 14, and if it is determined that it is equal to or greater than the threshold value, it is determined that it is a person.

[0043] In step 14 (S14), the motion determination unit 104 determines whether or not the object detected in S12 is moving. If it is determined that there is motion, the process proceeds to step 15, and if it is determined that there is no motion, the process proceeds to step 16.

[0044] In step 15 (S15), the human detection determination unit 105 determines that the object detected in S12 is not a human.

[0045] In step 16 (S16), the human detection determination unit 105 determines that the object detected in S12 is a human.

[0046] FIG. 5 is a flowchart of the motion determination process (S14 in FIG. 4) according to one embodiment of the present invention.

[0047] In step 21 (S21), similarity calculation section 141 selects one of the object detection regions in an image (object detection image) in which object detection section 102 has detected an object assumed to be a person (human-like).

[0048] In step 22 (S22), similarity calculation section 141 calculates the similarity between the object detection region selected in S21 and a region in another image that has the same coordinate position.

[0049] In step 23 (S23), similarity calculation unit 141 determines whether or not calculation of similarities is completed for all object detection regions in which objects have been detected by object detection unit 102. If completed, the process proceeds to step 24, and if not completed, the process returns to step 21.

[0050] In step 24 (S24), determination unit 142 determines, for each object detection region in which object detection unit 102 has detected an object, whether or not there are a predetermined number or more of regions at the same coordinate positions as the object detection region in another image in which the similarity is below the threshold. If the number of regions at the same coordinate positions as the object detection region in another image in which the similarity is below the threshold is equal to or greater than the predetermined number in at least one object detection region, the process proceeds to step 25, and determines whether or not there are a predetermined number of regions at the same coordinate positions as the object detection region in another image in which the similarity is below the threshold in all object detection regions. Below value If the number of areas in another image having the same coordinate position as the object detection area is less than the predetermined number, the process proceeds to step 26.

[0051] In step 25 (S25), the determination unit 142 determines that there is movement of the object.

[0052] In step 26 (S26), the determination unit 142 determines that there is no movement of the object.

[0053] <Movement Judgment> The motion determination will now be described in detail.

[0054] 6 is a diagram for explaining the determination of a movement according to an embodiment of the present invention. It is assumed that a video captured by an imaging device 20 such as a security or surveillance camera and acquired by an image acquisition unit 101 is composed of 15 frames in time series from the 1st frame to the 15th frame. It is also assumed that the object detection unit 102 detects a human-like object in the 10th frame. It is assumed that the detection score (detection reliability) is 0.5, which is less than a threshold value.

[0055] First, similarity calculation section 141 of motion determination section 104 calculates the similarity between the object detection area in which the object is detected in the image (the 10th frame in Figure 6) and areas at the same coordinate position as the object detection area in which the aforementioned object is detected in other frames included in the video (frames 1, 2, 3, 4, 5, 6, 7, 8, 9, 11, 12, 13, 14, and 15 in Figure 6).

[0056] Next, the determination unit 142 of the motion determination unit 104 counts the number of similarities calculated by the similarity calculation unit 141 that are equal to or less than the threshold, and determines whether or not the number is equal to or greater than a predetermined number (e.g., 8). In the example of Fig. 6, the threshold for similarity is set to 0.7, and there are 11 frames whose similarity is equal to or less than the threshold (marked with a circle in Fig. 6). In this case, the motion determination unit 104 determines that there is motion of the object, since the number of other images whose similarity is equal to or less than the threshold is equal to or greater than a predetermined number.

[0057] If an object is detected in multiple images (frames) (i.e., if an object is detected in a frame other than the 10th frame), similarity calculation unit 141 calculates the similarity between each object detection region in an image in which an object is detected (object detection image) and a region in another image (i.e., another frame included in the video) that has the same coordinate position as the object detection region. Then, determination unit 142 determines whether the similarity is greater than or equal to a threshold value for each object detection region in which an object is detected. Below valueIt is determined whether there is a predetermined number of regions at the same coordinate position as the object detection region of another image (that is, a determination similar to that in the 10th frame described above is made). If the number of regions at the same coordinate position as the object detection region of another image whose similarity is below a threshold is equal to or greater than a predetermined number in at least one object detection region, it is determined that there is movement, and if the number of similarities below the threshold in all object detection images is less than a predetermined number, it is determined that there is no movement. Similarly, when there are multiple object detection regions in the same image, the similarity between each object detection region and other images is calculated, and the number of other images (regions) whose similarity is below the threshold is counted to determine movement.

[0058] Here, the similarity is the threshold Below value Determination based on the condition that there are multiple images will be described. When comparing the object detection area of ​​an image in which a human-like object has been detected with other images, if there happens to be an insect or ambient light such as a car light reflected therein, the similarity may be calculated as low. In this case, if the method of calculating and comparing the similarity only with the area at the same coordinate position in the previous and next images, the insect or ambient light may be erroneously detected as a person. By comparing not only the previous and next images but also multiple other images and setting the determination condition to include the number of images (areas) with a similarity below a threshold, it is possible to suppress the occurrence of erroneous detection due to noise such as insects or ambient light, and to accurately determine that it is a moving human body.

[0059] <Other embodiments> Other embodiments will be described below.

[0060] <<Determining the movement of each body part>> In one embodiment of the present invention, the information processing device 10 can detect parts of a person's body (e.g., not limited to the entire body, but parts such as the head, arms, upper body, lower body, left or right half of the body, etc.) and determine the movement of the detected parts of the person's body.

[0061] Specifically, the object detection unit 102 detects human body parts by machine learning or the like. The detection score determination unit 103 determines whether or not the detection score (detection reliability) is smaller than a threshold. The movement determination unit 104 determines whether or not the human body part is moving. In this case, a threshold for the detection score (detection reliability) and a threshold for movement determination may be set for each human body part.

[0062] For example, when learning the shapes of heads and arms, a hat or helmet placed indoors may be erroneously detected as a "head," and a long, thin object such as a chair, a desk frame, or a pillar may be erroneously detected as an "arm." In order to prevent such erroneous detection, if a condition is set to uniformly determine that a person (moving object) is present when the similarity is below a threshold in a larger number of images, there is a risk that the detection of a person may be missed. Therefore, for object detection areas detected as arms, legs, and the like, which are parts that tend to move a lot in typical human movements, it is possible to accurately detect objects that are human by determining that the object is present as a person when the similarity is below a threshold in a larger number of images than for object detection areas detected as parts that move relatively little, such as the head.

[0063] <<Motion detection based on brightness>> The above describes an embodiment in which whether or not the object detection areas of two images (frames) are similar is determined by template matching such as ZNCC. However, the present invention can also be applied to an embodiment in which whether or not two images (frames) are similar is determined based on an evaluation value based on the brightness of the object detection areas of the two images (frames) (e.g., the average brightness difference).

[0064] In addition, a plurality of images obtained by converting the difference in luminance of each pixel when comparing object detection regions can be trained in an AI model for classifying moving images, such as 3DCNN (AI that inputs a series of images (moving images) and outputs their contents), and output which movement pattern the image corresponds to. The trained model may be a model trained based on the similarity between an image (e.g., the first frame) other than the image in which the object detection unit 102 detects an object (in the example of FIG. 6, the tenth frame) and other images. Also, it may be a model trained based on the similarity between images of adjacent frames (e.g., the similarity between the images of the first and second frames, the similarity between the images of the second and third frames, etc.).

[0065] <<Exclusion of cyclical movements>> In one embodiment of the present invention, the motion determination unit 104 can further determine whether the motion of the object is periodic or not. If the motion of the object is periodic, the human detection determination unit 105 determines that the detected object is not a human (for example, a light, flag, curtain fluttering in the wind, a blinking car headlight, or the like).

[0066] Specifically, the motion determination unit 104 can input the similarity between the object detection area where the object detection unit 102 detected the object and the area at the same coordinate position in another image (in the example of FIG. 6, the similarity between the 10th frame and the 1st to 9th and the 11th to 15th frames) to a trained model using a method such as a support vector machine or a random forest, and output whether the motion is periodic or not. The trained model may be a model trained based on the similarity between an image (for example, the 1st frame) other than the image where the object detection unit 102 detected the object (in the example of FIG. 6, the 10th frame) and another image. Also, it may be a model trained based on the similarity between images of adjacent frames (for example, the similarity between the images of the 1st and 2nd frames, the similarity between the images of the 2nd and 3rd frames, etc.).

[0067] <<Learning human-like movements>> The trained model may have previously trained patterns of human-like movements (such as a person moving or standing still). The movement determination unit 104 may output which movement pattern corresponds to which of multiple classes from multiple frames.

[0068] <Effects> In this way, in one embodiment of the present invention, it is possible to accurately determine whether an object that is assumed to be human and detected in an image captured by a security or surveillance camera, etc. is a human or not. Furthermore, in one embodiment of the present invention, by setting a detection score (detection reliability) threshold and a movement determination threshold for each part of a person's body, it is possible to improve the accuracy of determining an intruder whose body is partially hidden or in various postures.

[0069] <Hardware configuration> 7 is a block diagram showing an example of a hardware configuration of an information processing device 10 according to an embodiment of the present invention. The information processing device 10 has a CPU (Central Processing Unit) 1001, a ROM (Read Only Memory) 1002, and a RAM (Random Access Memory) 1003. The CPU 1001, the ROM 1002, and the RAM 1003 form a so-called computer.

[0070] The information processing device 10 may also have an auxiliary storage device 1004, a display device 1005, an operation device 1006, an I / F (Interface) device 1007, and a drive device 1008. The hardware components of the information processing device 10 are connected to each other via a bus B.

[0071] The CPU 1001 is a computing device that executes various programs installed in the auxiliary storage device 1004 .

[0072] The ROM 1002 is a non-volatile memory. The ROM 1002 functions as a main storage device that stores various programs, data, etc. required for the CPU 1001 to execute various programs installed in the auxiliary storage device 1004. Specifically, the ROM 1002 functions as a main storage device that stores boot programs such as a BIOS (Basic Input / Output System) and an EFI (Extensible Firmware Interface).

[0073] The RAM 1003 is a volatile memory such as a dynamic random access memory (DRAM) or a static random access memory (SRAM). The RAM 1003 functions as a main storage device that provides a working area in which various programs installed in the auxiliary storage device 1004 are expanded when the CPU 1001 executes them.

[0074] The auxiliary storage device 1004 is an auxiliary storage device that stores various programs and information used when the various programs are executed.

[0075] The display device 1005 is a display device that displays the internal state of the information processing device 10 and the like.

[0076] The operation device 1006 is an input device through which an administrator of the information processing device 10 inputs various instructions to the information processing device 10 .

[0077] The I / F device 1007 is a communication device for connecting to a network and communicating with other devices.

[0078] The drive device 1008 is a device for setting the storage medium 1009. The storage medium 1009 here includes media that record information optically, electrically, or magnetically, such as a CD-ROM, a flexible disk, a magneto-optical disk, etc. The storage medium 1009 may also include semiconductor memories that record information electrically, such as an EPROM (Erasable Programmable Read Only Memory), a flash memory, etc.

[0079] The various programs to be installed in the auxiliary storage device 1004 are installed, for example, by setting the distributed storage medium 1009 in the drive device 1008 and reading out the various programs recorded in the storage medium 1009 by the drive device 1008. Alternatively, the various programs to be installed in the auxiliary storage device 1004 may be installed by being downloaded from a network via the I / F device 1007.

[0080] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to the specific embodiments described above, and various modifications and variations are possible within the scope of the gist of the present invention as defined in the claims. [Explanation of symbols]

[0081] 1. Image Processing System 10. Information processing device 20 Imaging device 101 Image acquisition unit 102 Object detection unit 103 Detection score judgment unit 104 Motion Judgment Unit 105 Human detection and judgment unit 141 Similarity calculation unit 142 Judgment section 1001 CPU 1002 ROM 1003 RAM 1004 Auxiliary storage device 1005 Display device 1006 Operating device 1007 I / F device 1008 Drive device 1009 Storage medium

Claims

1. an image acquisition unit that acquires a plurality of images from an imaging device; an object detection unit that detects an object that is likely to be a part of a human body within the image; a motion determination unit that determines whether or not an object is moving based on whether an object detection image in which the object is detected is similar to a plurality of images other than the object detection image, the threshold value being set based on the magnitude of movement of each part of the person's body, and the threshold value set for parts with large movement, including at least one of the arms and legs, is set to a value greater than the threshold value set for parts with little movement, including at least the head; and a human detection determination unit that determines that the detected object is a human if the reliability of the detection of the object in the image is greater than a threshold value set for each part of the person's body for determining the reliability of the detection of the object and if the object is moving, and determines that the detected object is not a human if the object is not moving; An information processing device comprising:

2. The information processing device according to claim 1 , wherein the motion determination unit determines whether or not the object is moving based on whether an object detection area in the object detection image is similar to an area at the same coordinate position as the object detection area in a plurality of images other than the object detection image.

3. 3. The information processing device according to claim 1, wherein the motion determination unit determines whether an object detection area in the object detection image is similar to an area at the same coordinate position as the object detection area in a plurality of images other than the object detection image, based on a similarity obtained by pattern matching.

4. The information processing device according to claim 1 or 2, wherein the motion determination unit determines whether an object detection area in the object detection image is similar to an area at the same coordinate position as the object detection area in a plurality of images other than the object detection image, based on a difference in brightness.

5. The motion determination unit further determines whether the motion of the object is a periodic motion; The information processing device according to claim 1 , wherein the human detection determination unit determines that the detected object is not a human when the motion of the object is a periodic motion.

6. A method executed by an information processing device, comprising: acquiring a plurality of images from an imaging device; detecting an object in the image that is likely to be a part of a human body; a step of determining whether or not an object is moving based on whether an object detection image in which the object is detected is similar to a plurality of images other than the object detection image, the threshold value for determining whether or not an object is moving is set based on the magnitude of movement of each part of the person's body, the threshold value set for parts with large movement including at least one of the arms and legs being set to a value greater than the threshold value set for parts with little movement including at least the head; determining that the detected object is a person when the reliability of the detection of the object in the image is greater than a threshold value set for each part of the person's body for determining the reliability of the detection of the object and when the object is moving, and determining that the detected object is not a person when the object is not moving; The method includes:

7. Information processing device an image acquisition unit that acquires a plurality of images from an imaging device; an object detection unit that detects an object that is likely to be a part of a human body within the image; a motion determination unit that determines the presence or absence of object motion based on whether an object detection image in which the object is detected is similar to a plurality of images other than the object detection image, based on a threshold value for determining the presence or absence of object motion, the threshold value being set based on the magnitude of motion of each part of the person's body, the threshold value being set for parts with large motion including at least one of the arms and the legs being set to a value greater than the threshold value being set for parts with little motion including at least the head; a human detection determination unit that determines that the detected object is a human if the reliability of the detection of the object in the image is greater than a threshold value set for each part of the person's body for determining the reliability of the detection of the object and if there is movement of the object, and determines that the detected object is not a human if there is no movement of the object. A program to function as a

Images