JP2019128791A - Image processing device and control method thereof - Google Patents

Abstract

To make it possible to efficiently set parameters for detecting an object included in an image.SOLUTION: An image processing device, for setting a detection area for detecting a predetermined dynamic body in an image captured by an imaging device and a dynamic body size of the predetermined dynamic body in the detection area, has: acquisition means for acquiring a dynamic image from the imaging device; first extraction means for extracting a dynamic body image from each of a plurality of images included in the dynamic image; generation means for generating a superimposed image in which a plurality of dynamic body images extracted by the first extracting means are superimposed; first setting means for setting the detection area on the basis of the superimposed image; second extraction means for extracting dynamic body images included in the detection area among the plurality of dynamic body images extracted by the first extraction means; determination means for determining a dynamic body image having the maximum size and a dynamic body image having the minimum size of the dynamic body images extracted by the second extracting means; and second setting means for setting the dynamic body size in the detection area on the basis of the dynamic body image having the maximum size and the dynamic body image having the minimum size determined by the determination means.SELECTED DRAWING: Figure 5

Description

  The present invention relates to an image processing technique related to moving object detection.

  2. Description of the Related Art Conventionally, a technique for detecting and counting (counting) an object such as a human body by analyzing an image captured by a camera is known. In order to speed up the human body detection process, it is effective to use a method for limiting the detection area, which is a target area for the detection process, and the human body size to be detected for the video. Therefore, a method is conceivable in which a user manually sets a detection area and a human body size while actually capturing an image of a person standing in real space and viewing an image obtained by the image capturing. However, when actually imaging a person standing in real space, it is necessary to mobilize many people, and there is a problem that it takes time and cost.

  Therefore, it is conceivable to create a video that imitates a person standing. In Patent Document 1, there is provided a display device which generates an output image by superimposing a trajectory of a moving object on a video composed of a plurality of frame images sequentially obtained by imaging means controlled so that the moving object enters an area. It is disclosed. Further, in Patent Document 2, a technology for highlighting the trajectory of a moving object moved in a time zone specified by the user, highlighting a moving object moving at a speed higher than the moving velocity specified by the user or a moving object moving at a low speed Technology is disclosed.

JP 2011-254289 A U.S. Patent Application Publication 2012/01636657

  However, in the above-described conventional technology, it is necessary for the user to visually confirm and set the maximum size and the minimum size used for limiting the human body size. In particular, in order to speed up the human body detection process, it is necessary to set the minimum size and the maximum size of the human body size for each detection area in the image. For this reason, a complicated operation is required for setting, and there is a problem that the cost efficiency is low.

  The present invention has been made in view of such problems, and an object of the present invention is to provide a technique that can efficiently set parameters for detecting an object included in an image.

In order to solve the above-described problems, an image processing apparatus according to the present invention has the following configuration. That is, an image processing device for setting a detection area for detecting a predetermined moving object in a captured image by the imaging device and a moving object size of the predetermined moving object in the detection area,
Acquisition means for acquiring a moving image from the imaging device;
First extraction means for extracting a moving body image from each of a plurality of images included in the moving image;
Generation means for generating a superimposed image in which a plurality of moving body images extracted by the first extraction means are superimposed and displayed;
First setting means for setting the detection area based on the superimposed image;
Second extracting means for extracting a moving body image included in the detection area among the plurality of moving body images extracted by the first extracting means;
A determining unit that determines a moving object image of maximum size and minimum size among moving object images extracted by the second extracting unit;
Second setting means for setting the moving object size in the detection area based on the moving object image of the maximum size and the minimum size determined by the determining means;
Have.

  ADVANTAGE OF THE INVENTION According to this invention, the technique which enables the parameter for detecting the object contained in an image to be set efficiently can be provided.

It is a figure showing the whole composition of the image processing system in a 1st embodiment. It is a figure which shows the hardware constitutions and function structure of an imaging device. It is a figure which shows the hardware constitutions and function structure of a client apparatus. It is a figure explaining the setting of the detection area and human body size with respect to a captured image. It is a flowchart which shows operation | movement of the image processing system in 1st Embodiment. It is a figure explaining the movement of a moving body, and the setting of a detection area. It is a figure explaining acquisition of the maximum and the minimum size. It is a figure explaining setting of human body size. It is a flow chart which shows acquisition processing of a frame of the maximum size / minimum size in a 2nd embodiment. FIG. 7 is a view exemplarily showing various GUIs for displaying candidate frames. It is a figure explaining adjustment of frame superposition number.

  Hereinafter, an example of an embodiment of the present invention will be described in detail with reference to the drawings. The following embodiment is merely an example and is not intended to limit the scope of the present invention.

First Embodiment
As a first embodiment of an image processing apparatus according to the present invention, an image processing system that detects a moving body (human body) included in an image acquired by an imaging apparatus will be described below as an example. In particular, a method for improving the efficiency of setting the human body size in the detection area in the video will be described.

<System and Configuration of Each Device>
FIG. 1 is a diagram illustrating an overall configuration of an image processing system according to the first embodiment.

  The imaging device 110 is an imaging device such as a network camera that performs imaging. The client device 120 is an information processing device such as a personal computer, a server device, or a tablet device that drives the imaging device 110 and displays a captured image captured by the imaging device 110.

  The input device 130 includes a mouse, a keyboard and the like, and performs user input to the client device 120. The display device 140 includes a display or the like, and displays an image output by the client device 120.

  Here, the client device 120, the input device 130, and the display device 140 are shown as independent devices. However, for example, the client device 120 and the display device 140 may be integrated, or the input device 130 and the display device 140 may be integrated. Also, the client device 120, the input device 130, and the display device 140 may be integrated.

  The network 150 communicably connects the imaging device 110 and the client device 120 to each other. The network 150 is configured of, for example, a plurality of routers, switches, cables, and the like that meet communication standards such as a local network. Here, any communication standard, scale, and configuration may be used as long as communication between the imaging device 110 and the client device 120 can be performed. For example, the network 150 may be configured by the Internet, a wired LAN (Local Area Network), a wireless LAN, a WAN (Wide Area Network), or the like. Further, the number of imaging devices 110 connected to the client device 120 is not limited to one, and may be a plurality.

  FIG. 2 is a diagram illustrating a hardware configuration and a functional configuration of the imaging apparatus. FIG. 2A shows an example of a hardware configuration, and FIG. 2B shows an example of a functional configuration.

  The imaging device 110 includes a CPU 211, a main storage device 212, an auxiliary storage device 213, a driving unit 214, an imaging unit 215, and a network I / F 216. The respective elements are communicably connected to one another via a system bus 217.

  The CPU 211 is a central processing unit that controls the operation of the imaging device 110. The main storage device 212 is a storage device such as a random access memory (RAM) that functions as a work area for the CPU 211 and a temporary storage location for data. The auxiliary storage device 213 is a storage device such as a hard disk drive (HDD) that stores various programs, various setting data, and the like, a read only memory (ROM), and a solid state drive (SSD). The drive unit 214 is a drive unit that drives the imaging device 110 to change the orientation and the like of the imaging device 110 and change the shooting direction and the angle of view of the imaging unit 215.

  The imaging unit 215 is a functional unit for acquiring an image of a subject, and includes an imaging element and an optical system. Examples of the image sensor include a complementary metal-oxide semiconductor (CMOS) and a charged coupled device (CCD). The network I / F 216 is an interface used for communication with an external device such as the client device 120 via the network 150.

  When the CPU 211 executes processing based on a program stored in the auxiliary storage device 213, functions and processing of the imaging device 110 described later are realized.

  The imaging apparatus 110 includes an imaging control unit 231, a signal processing unit 232, a drive control unit 233, and a communication control unit 234 as functional configurations.

  The imaging control unit 231 images the surrounding environment via the imaging unit 215. The signal processing unit 232 processes an image captured by the imaging control unit 231. The signal processing unit 232, for example, encodes an image captured by the imaging control unit 231. In the case of a still image, the signal processing unit 232 encodes an image using an encoding method such as JPEG (Joint Photographic Experts Group), for example. Further, in the case of a moving image, the signal processing unit 232 performs the H.264 process. The image is encoded using a coding method such as H.264 / MPEG-4 AVC (hereinafter simply referred to as H.264), HEVC (High Efficiency Video Coding), or the like. Note that the signal processing unit 232 performs image encoding using, for example, the encoding method selected by the user via the operation unit of the imaging device 110 from among a plurality of encoding methods set in advance. You may

  The drive control unit 233 performs control to change the shooting direction and the angle of view of the imaging control unit 231 via the drive unit 214. However, only one of the shooting direction and the angle of view by the imaging control unit 231 may be changed. In addition, the shooting direction and the angle of view of the imaging control unit 231 may be fixed. The communication control unit 234 transmits the image captured by the imaging control unit 231 and processed by the signal processing unit 232 to the client device 120 via the network I / F 216. Further, the communication control unit 234 receives a control command for the imaging device 110 from the client device 120 via the network I / F 216.

  FIG. 3 is a diagram illustrating a hardware configuration and a functional configuration of the client apparatus. FIG. 3A shows an example of a hardware configuration, and FIG. 3B shows an example of a functional configuration.

  The client device 120 includes a CPU 221, a main storage device 222, an auxiliary storage device 223, an input I / F 224, an output I / F 225, and a network I / F 226. The elements are communicably connected to one another via a system bus 227.

  The CPU 221 is a central processing unit that controls the operation of the client device 120. The main storage device 222 is a storage device such as a work area of the CPU 221 and a RAM that functions as a temporary storage location of data. The auxiliary storage device 223 is a storage device such as an HDD, a ROM, or an SSD that stores various programs, various setting data, and the like. The input I / F 224 is an interface used when receiving an input from the input device 130 or the like. The output I / F 225 is an interface used to output information to the display device 140 or the like. The network I / F 216 is an interface used for communication with an external device such as the imaging device 110 via the network 150.

  When the CPU 221 executes processing based on the program stored in the auxiliary storage device 223, functions and processing of the client device 120 described later are realized.

  The client device 120 includes an input information acquisition unit 241, a communication control unit 242, an image acquisition unit 243, a detection unit 244, a video recording unit 245, a moving object acquisition unit 246, a drawing unit 247, and a display control unit 248 as functional components.

  The input information acquisition unit 241 receives an input by the user via the input device 130. The communication control unit 242 receives an image transmitted from the imaging device 110 via the network 150. Further, the communication control unit 242 transmits a control instruction to the imaging device 110 via the network 150. The image acquisition unit 243 acquires an image captured by the imaging device 110 as an image that is a subject of subject detection processing via the communication control unit 242. In addition, the image acquisition unit 243 may acquire the image stored in the auxiliary storage device 223 as an image that is a subject of subject detection processing. Here, the image may be a moving image (a plurality of frame images) or a still image.

  The detection unit 244 performs subject detection processing based on the image characteristics for the image acquired by the image acquisition unit 243. The video recording unit 245 records the real-time video shot by the imaging device 110 according to an input from the user. The moving body acquisition unit 246 cuts out the moving body from the video acquired by the video recording unit by moving body difference. However, the present invention is not limited to this, and processing may be performed on previously recorded video in the auxiliary storage device 223.

  The display image generation unit 247 generates an image in which the moving object frame image acquired by the moving object acquisition unit 246 is superimposed at predetermined intervals. Further, the display image generation unit 247 extracts the frames included in the detection area and extracts the maximum and minimum frames from the frames. Then, the acquired maximum and minimum size frames are emphasized and a video superimposed on the background image is generated. The display control unit 248 outputs a subject detection result or a moving object frame superimposition result to the display device 140 in accordance with an instruction from the CPU 221.

  Here, a mode is described in which the client device 120 acquires a captured image from the imaging device 110 and performs processing on the captured image. However, the processing may be performed in the imaging device 110.

<System operation>
As described above, the client device 120 performs human body detection on the captured image acquired from the imaging device 110. Specifically, one or more detection areas are set, the maximum and minimum human body sizes are set for each set detection area, and the set human body detection process is performed.

  FIG. 4 is a diagram for explaining setting of a detection area and a human body size for a captured image. Specifically, a captured image as a reference is acquired, and the detection area and the human body size are set with reference to the captured image.

  FIG. 4A is a diagram showing how the imaging device 200 images a subject. The subjects 210, 211, 220, and 221 indicate four people. That is, FIG. 4A shows a scene in which the subjects 210 and 211 exist at positions relatively close to the imaging device 200 and the subjects 220 and 221 exist at positions relatively far.

  FIG. 4B is a diagram exemplarily showing a display image captured by the imaging device 200 and displayed on the client device in the state shown in FIG. Objects 240, 241, 250, and 251 on the display image 230 are human body images shown in the imaging. The object 240 is a captured video of the subject 210 in FIG. 4A, and similarly, the object 241 is a captured subject 211, the object 250 is a captured video of the subject 220, and the object 251 is a captured video of the subject 221.

  The user visually sets the detection area by visually observing the display image 230 displayed on the client device. For example, the detection area is set to be surrounded by a frame so as to include the upper body of the human body images 240, 241, 250, and 251. Here, the reason why the setting is made so as to include the upper body image is that it is convenient for the matching processing based on the feature image of the human body when the human body is detected.

  Rectangular areas 260 and 270 in FIG. 4B are detection areas set by the user. Note that the size of the detection area can be arbitrarily changed according to the area of the detection area to be counted. Therefore, the number of required subjects may change depending on the size of the detection area. Further, although two detection areas are designated in FIG. 4B, the setting can be increased or decreased according to the number of detection areas to be counted.

  FIG. 4C is a view showing a user interface (UI) of human body size setting. The user sets the human body size for each detection area via the UI.

  Human body models 280, 281, 290, and 291 are models for human body size setting. The user can set the human body size by operating the human body model 280, 281, 290, 291 with a mouse.

  For example, the moving body size (human body size) can be set for the detection area 260 by operating the human body models 280 and 281. Here, it is assumed that the human body model 280 is operated to set the maximum human body size, and the human body model 281 is operated to set the minimum human body size. Similarly, the human body models 290 and 291 can be operated for the detection area 270 to set the maximum and minimum human body sizes.

  However, in the above-mentioned method, it is necessary to set people in the real space, which increases the cost due to the labor cost. In addition, it takes time for the user to visually find the maximum and minimum human bodies in each detection area. Therefore, in the first embodiment, in order to streamline detection area setting and human body size setting, a method of acquiring and highlighting the maximum size and the minimum size of the human body in the detection area will be described.

  FIG. 5 is a flowchart showing the operation of the image processing system in the first embodiment. That is, the flow of processing for extracting and highlighting the maximum size and the minimum size of the human body is shown.

  In step S <b> 301, the imaging device 110 captures a moving human and stores the obtained moving image in the memory 223 in the client device 120.

  FIG. 6 is a diagram for explaining the movement of the moving object and the setting of the detection area. FIG. 6A is a diagram illustrating an example of a recorded video imaged by the imaging device 110. This image shows a human body 501 as a subject moving in the space in the direction indicated by the arrow with time.

  In step S302, the moving body acquisition unit 246 cuts out a moving body image (frame including a moving subject) at predetermined time intervals by moving body difference using the recorded video acquired in step S301. Then, the display image generation unit 247 generates an image in which the frame 512 is superimposed on the background image.

  FIG. 6B is a diagram illustrating a state in which the frames 512 are acquired at predetermined time intervals and all the frames 512 are superimposed and displayed as the frame group 513. A plurality of frames is superimposed on one image in order to enhance the visibility on the user side when a moving object frame of the same size is set as one detection area at the time of setting the detection area. Finally, the display control unit 248 causes the display device 140 to display the superimposed image generated by the display image generation unit 247. The display device 140 displays a moving object frame 512 as a minimum rectangle including the moving object. In addition, here, each frame is superimposed and displayed in chronological order as shown in FIG. Therefore, when a moving body moves from the back to the hand, the new frame is displayed in front of the old frame. Each frame is a PNG (Portable Network Graphics) image in order to take account of the change in transmittance described later.

  In S303, the input information acquisition unit 241 acquires detection area information set by the user. That is, the user manually sets a detection area while viewing the superimposed image acquired in S302, and the input information acquisition unit 241 receives the setting content.

  FIG. 6C shows the state in which the user has set the detection area 601. The method of setting the detection area is as described above. Although only one detection area is specified here, a plurality of detection areas may be specified. In other words, a plurality of detection areas can be set and analyzed for each detection area. Furthermore, each detection area can be further divided into a plurality of small areas. In this case, even if a plurality of small regions are scattered, if the same detection area, the analysis processing is performed with the setting applied to the detection area.

  In S304, the display image generation unit extracts a frame image in which a moving body (human body) is included in the detection area set by the user in S303. The extraction is performed, for example, by determining whether the upper half of the frame is included in the range of the detection area. FIG. 6D is a diagram illustrating a state in which frame images included in the detection area 601 are extracted. Here, the frames 611, 612 and 613 present in the detection area 601 are extracted. As a result, the frame image outside the detection area is not subject to subsequent processing.

  In S305, the display image generation unit 247 extracts the maximum and minimum size frames from the detection area. Specifically, since each frame in the detection area is already cut out as a rectangle, the largest rectangular frame is extracted as the largest size, and the smallest rectangular frame is extracted as the smallest size. Here, the frame 611 is extracted as the maximum size frame, and the frame 613 is extracted as the minimum size frame.

  In S306, the display image generation unit 247 generates an image in which the enhanced frame is superimposed on the background image. Then, the display control unit 248 displays the image created by the display image generation unit 247 on the display device 140.

  FIG. 7 is a diagram for explaining acquisition of the maximum and minimum sizes. Of the frame images belonging to the detection area 601, an image in which the maximum size frame 701 and the minimum size frame 702 are highlighted is shown.

  Here, in order to highlight a frame, the transmittance of the frame 701 which is the maximum size and the frame 702 which is the minimum size is reduced, and the transmittance of the other frames is increased. Regarding the transmittance, the user can set an arbitrary value for the maximum size / minimum size frame and other frames. For example, when it is desired to pay attention only to the maximum size / minimum size frames, the maximum / minimum size transmittance may be set to “0”, and the transmittance of other frames may be set to “100”.

  In addition, methods other than the control of the above-mentioned transmittance | permeability can also be used for the method of highlighting a flame | frame. For example, emphasis can be achieved by thickening the outline of the frame 701 having the maximum size and the frame 702 having the minimum size. Further, as described above, since the frames are superimposed in time-sequential order, it is also possible to emphasize by controlling to display the frames of maximum and minimum sizes in the foreground.

  In S307, the display image generation unit 247 generates a human body size setting screen in which the human body model for setting the human body size is displayed superimposed on the background image. This process is executed, for example, when the user presses a human body size setting button (not shown).

  FIG. 8 is a diagram for explaining setting of the human body size. That is, it is a diagram exemplarily showing a human body size setting screen generated by the display image generation unit 247. The human body models 801 and 802 are models imitating the upper body of the human body. As described above, the user can set the human body size by scaling the human body models 801 and 802 by operating the mouse. The method of setting the human body size is not limited to this, and for example, the human body model may be selected, and the size may be adjusted by using the up button and the down button on the keyboard. It is also possible to automatically determine the human body size from the maximum and minimum frames acquired in S305 and to superimpose it in the vicinity of the detection area. When the user sets the human body size, the input information acquisition unit 241 acquires the maximum size and the minimum size of the human body size set by the user.

  In S308, the input information acquisition unit 241 determines whether there is another detection area. If there is no other detection area setting, the process ends. If there is another detection area setting, the process returns to S303 to repeat the process.

  As described above, according to the first embodiment, it is possible to increase the efficiency of setting the detection area by using the superimposed video of the moving object frame output to the display device 140. In addition, the human body size can be set more efficiently by highlighting the maximum size frame and the minimum size frame included in the detection area in the superimposed image. That is, it is possible to greatly reduce the labor and time required for setting the human body size.

Second Embodiment
In the second embodiment, acquisition processing (S305) of a frame of maximum size and minimum size will be described in more detail. Specifically, a process when an object other than a human body is included in a video and an object other than a human body is acquired as a frame having a maximum size or a minimum size will be described. The configuration of the system and each device is the same as that of the first embodiment (FIGS. 1 to 3), and thus the description thereof is omitted.

<System operation>
Since the overall operation of the system is the same as that of the first embodiment (FIG. 5), detailed description thereof is omitted. As described above, in the second embodiment, acquisition processing (S305) of a frame of maximum size / minimum size is different from that of the first embodiment.

  When the imaging device 110 captures a moving human and an object other than the human body and stores the image as a recorded video image in the memory 223 in the client device 120, processing similar to that of the first embodiment is started. S301 to S304 are the same as those in the first embodiment. However, in S304, the point from which objects other than a human body are extracted differs from 1st Embodiment.

  FIG. 10 is a diagram exemplarily showing various GUIs for displaying candidate frames. FIG. 10A is a diagram illustrating an example of the superimposed video of the frame extracted in S304 in the second embodiment. The video includes human bodies 611 to 613 and an image of a bird that is a subject 901 other than the human body.

  FIG. 9 is a flowchart showing acquisition processing of a frame of maximum size and minimum size in the second embodiment.

  In S401, the display image generation unit 247 acquires the minimum size frame as a minimum human body size candidate, and generates the maximum / minimum size confirmation screen 920. Then, the display control unit 248 displays the maximum / minimum size confirmation screen 920 on the display device 140. Here, the maximum / minimum size confirmation screen 920 is a UI for allowing the user to determine whether or not the frame includes a human body. The maximum / minimum size confirmation screen 920 is displayed adjacent to the superimposed video of the frame extracted in S304, for example.

  FIG. 10B is a diagram illustrating an example of a UI on which the superimposed video of the frame extracted in S304 and the maximum / minimum size confirmation screen 920 are displayed. The maximum / minimum size confirmation screen 920 includes a minimum human body size candidate frame 921 and a maximum human body size candidate frame 922.

  The minimum human body size candidate frame 921 displays the acquired minimum size frame, and the maximum human body size candidate frame 922 displays the acquired maximum size frame. Here, the subject 901 is displayed as the object 923 in the minimum human body size candidate frame 921 as the minimum frame candidate.

  In S402, the display image generation unit 247 acquires the determination result of the user as to whether or not the frame includes the human body. Specifically, the user visually confirms the image displayed in the minimum human body size candidate frame 921. Then, when it is determined that the image displayed in the minimum human body size candidate frame 921 includes the human body, the user presses the enter button (not shown). On the other hand, when it is determined that the image displayed in the minimum human body size candidate frame 921 does not include a human body, the user presses the arrow button 924.

  In S403, the display image generation unit 247 analyzes the determination result of the user in S402. Here, if it is analyzed that the arrow button 924 has been pressed by the user, it is determined that an erroneous detection of the object has occurred, and the process proceeds to S404. On the other hand, if it is determined that the confirm button has been pressed, it is determined that no erroneous detection of the object has occurred, and the process proceeds to S405.

  In S <b> 404, the display image generation unit 247 displays the next next candidate subject (here, the subject 931) next to the currently selected subject 911. FIG. 10C is a diagram showing a state where the next candidate subject is displayed. Here, a minimum human body size candidate 943 is newly displayed in the minimum human body size candidate frame 921. Then, the process returns to S402, and the user determines whether the frame includes a human body. By this process, the frame which does not include the human body is excluded from the minimum human body size.

  In S405, the display image generation unit 247 acquires the maximum size frame as a maximum human body size candidate, and generates the maximum / minimum size confirmation screen 920. The acquisition process of the maximum size frame shown in S405 to S408 is the same as the acquisition process of the minimum size frame (S401 to S404), and thus description thereof is omitted.

  FIG. 10D is a diagram illustrating an example of a UI on which the superimposed video of the frame extracted in S304 and the maximum / minimum size confirmation screen 920 are displayed. Here, the subject 611 is displayed as the object 964 in the maximum human body size candidate frame 922 as the maximum frame candidate.

  With the above-described processing, even when an object other than the human body is included in the video, the maximum size and the minimum size of the human body can be appropriately acquired. Thereafter, the processing proceeds to step S306. That is, the display image generation unit 247 generates an image in which the emphasized frame is superimposed on the background image. Then, the display control unit 248 displays the superimposed image on the display device 140.

  As described above, according to the second embodiment, it is possible to make the setting of the detection area and the setting of the human body size more efficient even when the image includes an object other than the human body.

(Modification)
In the above description, the moving object acquisition unit 246 superimposedly displays a plurality of frames at a predetermined time interval in S302, but other display methods may be used. For example, a display method in which the frame time interval can be changed may be used.

  FIG. 11 is a diagram for explaining the adjustment of the number of superimposed frames (the number of superimposed frames). Specifically, it is a diagram showing the relationship between the amount of movement of a moving object (here, a human body) per unit time and the frame group displayed accordingly. The movement amount per unit time is calculated from the pixel movement amount per fixed time.

  The frame display video 1001 is an example of frame superimposition when the moving amount of the moving object per unit time is small. In this case, since the number of superimposed images is too large, the user is bothered when setting the detection area and setting the human body size. The frame display unit 1021 is an example of frame superimposition when the moving amount of the moving object per unit time is large. In this case, it is difficult to grasp the detection area where people are to be counted, and it is difficult to set the detection area and the human body size. For this reason, as shown in the frame display video 1011, it is desirable that the amount of movement per unit time is appropriate, and that each frame be displayed as a video that is easily visible.

  Therefore, the moving object acquisition unit 246 adjusts the number of frames to be displayed according to the moving speed of the moving object. Here, the moving speed of the moving body is calculated by the amount of movement in pixel conversion per fixed time. For example, in the situation shown in the frame display video 1001, since the number of frames is large, the number of frames is adjusted to be thinned out. On the other hand, in the situation shown in the frame display video 1021, since the number of frames is small and the frame interval is widened, adjustment is made to increase the number of frames. By these adjustments, it is possible to provide a more suitable superimposed display in consideration of user visibility.

  The moving body acquisition unit 246 may automatically perform the adjustment described above, or may be configured to receive an adjustment instruction from the user. For example, the display image generation unit 247 may display a display interval setting screen (not shown) so that the user can manually set the frame display interval.

(Other embodiments)
The present invention supplies a program that implements one or more functions of the above-described embodiments to a system or apparatus via a network or storage medium, and one or more processors in a computer of the system or apparatus read and execute the program. Can also be realized. It can also be realized by a circuit (for example, ASIC) that realizes one or more functions.

  110 imaging device; 120 client device; 130 input device; 140 display device; 150 network

Claims (11)

An image processing device for setting a detection area for detecting a predetermined moving object in a captured image by an imaging device and a moving object size of the predetermined moving object in the detection area,
Acquisition means for acquiring a moving image from the imaging device;
First extraction means for extracting a moving body image from each of a plurality of images included in the moving image;
Generation means for generating a superimposed image in which a plurality of moving body images extracted by the first extraction means are superimposed and displayed;
First setting means for setting the detection area based on the superimposed image;
Second extracting means for extracting a moving body image included in the detection area among the plurality of moving body images extracted by the first extracting means;
A determining unit that determines a moving object image of maximum size and minimum size among moving object images extracted by the second extracting unit;
Second setting means for setting the moving object size in the detection area based on the moving object image of the maximum size and the minimum size determined by the determining means;
An image processing apparatus comprising: The first setting unit includes a first display unit that displays the superimposed image and displays a user interface (UI) that receives a setting of the detection area from a user. Image processing device. The second setting means displays a user interface (UI) for displaying the moving body image of the maximum size and the minimum size determined by the determining means and receiving the setting of the moving body size from the user. The image processing apparatus according to claim 1, further comprising: The image processing apparatus according to claim 3, wherein the second display unit highlights the moving body images having the maximum size and the minimum size determined by the determination unit. The second display means performs the highlighting by making the transmittance of the moving image of the maximum size and the minimum size determined by the determining means relatively lower than the transmittance of the other moving image. The image processing apparatus according to claim 4, wherein Determining means for determining whether or not the maximum size and minimum size moving body images determined by the determining means include a predetermined moving body;
Excluding means for excluding the moving body image determined not to include the predetermined moving body from the maximum size and the minimum size moving body image by the determining means;
The image processing apparatus according to any one of claims 1 to 5, further comprising: The image processing apparatus according to claim 1, further comprising a control unit that controls the number of superimposed moving body images in the superimposed image. The image processing apparatus according to claim 7, wherein the control unit controls the number of superimpositions based on a moving amount of a moving object per unit time in the moving image. The image processing apparatus according to any one of claims 1 to 8, wherein the predetermined moving body is a human body. A control area of an image processing apparatus for setting a detection area for detecting a predetermined moving object in an image captured by an imaging apparatus and a moving object size of the predetermined moving object in the detection area,
An acquisition step of acquiring a moving image from the imaging device;
A first extraction step of extracting a moving object image from each of a plurality of images included in the moving image;
A generation step of generating a superimposed image in which a plurality of moving body images extracted by the first extraction step are superimposed and displayed;
A first setting step of setting the detection area based on the superimposed image;
A second extraction step of extracting a moving body image included in the detection area among a plurality of moving body images extracted by the first extraction step;
A determining step of determining a maximum size and a minimum size moving image among the moving images extracted by the second extraction step;
A second setting step of setting the moving body size in the detection area based on the moving body images of the maximum size and the minimum size determined by the determining step;
And controlling the image processing apparatus.   The program for functioning a computer as each means of the image processing apparatus in any one of Claims 1-9.

Images