Information Processing Apparatus, Information Processing Method, and Information Processing Program

Abstract

To improve the detection accuracy of an object.SOLUTION: An information processing device 100 of the present invention comprises: a change unit 122 which changes the number of images per unit time used to detect an object included in an image captured by an imaging device 200 according to an angle of view of the imaging device 200; and a detection unit 123 which detects the object using each image of the number of images per changed unit time among the images captured by the imaging device 200.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program.

Background Art

[0002] Conventionally, various technologies related to security cameras and surveillance cameras have been proposed. For example, technologies related to store-installed security camera devices, and technologies related to surveillance camera devices and programs used in surveillance camera devices have been proposed.

Prior Art Document

Patent Document

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, for example, due to the small viewing angle of the imaging device, there are cases where an object passing within the viewing angle cannot be detected, and thus the detection accuracy of the object may decrease.

[0005] The present invention has been made in view of the above, and an object thereof is to provide an information processing apparatus, an information processing method, and an information processing program capable of improving the detection accuracy of an object.

Means for Solving the Problems

[0006] In order to solve the above-described problems and achieve the object, an information processing apparatus includes: a changing unit that changes the number of images per unit time used for detecting an object included in an image captured by the imaging device according to the viewing angle of the imaging device; and a detecting unit that executes the detection of the object using each image having the changed number of images per unit time among the images captured by the imaging device.

Effects of the Invention

[0007] According to the present invention, the detection accuracy of an object can be improved.

Brief Description of Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiments for Carrying Out the Invention

[0009] Hereinafter, with reference to the drawings, embodiments of an information processing apparatus, an information processing program, and an information processing method according to the present application will be described in detail. Note that the present invention is not limited by this embodiment. In the description of the drawings, the same parts are denoted by the same reference numerals, and redundant explanations are omitted.

[0010] [Configuration of the Information Processing System] First, the configuration of the information processing system 1 will be described with reference to FIG. 1. FIG. 1 is a diagram showing an example of the configuration of the information processing system 1 according to the embodiment. As shown in FIG. 1, the information processing system 1 includes an information processing apparatus 100 and an imaging apparatus 200. The information processing apparatus 100 and the imaging apparatus 200 are connected by wire or wirelessly. In FIG. 1, one information processing apparatus 100 and three imaging apparatuses 200 are shown, but in the information processing system 1, the numbers of the information processing apparatus 100 and the imaging apparatus 200 are not limited. That is, the information processing system 1 is composed of an arbitrary number of information processing apparatuses 100 and an arbitrary number of imaging apparatuses 200. Each of these apparatuses will be described below.

[0011] The imaging apparatus 200 is an example such as a security camera or a surveillance camera, and is a camera that captures images. The imaging apparatus 200 captures images according to the set resolution, format, frame rate, etc. Note that the images include still images and moving images.

[0012] The information processing apparatus 100 is an example of a computer that analyzes the images captured by the imaging apparatus 200 and detects objects in the images. For example, the information processing apparatus 100 determines whether each image of the number of images per unit time captured by the imaging apparatus 200 contains an object to be detected. Here, the number of images per unit time means the detection frame rate when performing object detection.

[0013] Also, the detection frame rate is the frame rate used by the information processing apparatus 100 for object detection, and is different from the frame rate of the moving image. That is, the imaging apparatus 200 captures a moving image at the set frame rate, outputs the captured moving image to the information processing apparatus 100, and the information processing apparatus 100 performs object detection on the moving image acquired from the imaging apparatus 200 at the set detection frame rate.

[0014] For example, when the frame rate of a video is set to 40 fps (frames per second) and the detection frame rate is set to 5 fps, the imaging device 200 captures the video at the speed of 40 fps set as the frame rate and transmits a video composed of 40 images per second to the information processing device 100. Then, since the detection frame rate is set to 5 fps in the information processing device 100, for the video composed of 40 images per second, it determines whether an object is included in each image using 5 images per second and performs object detection.

[0015] Note that in this specification, the angle of view refers not only to the range that the imaging device 200 can capture, but also to the range within the range that the imaging device 200 can capture where an object can be detected. Further, the object includes not only moving objects such as people, animals, plants, and machines, but also any detection target such as objects other than moving objects such as shelves, carts, and products.

[0016] [Problems of the Related Art] As a related art for performing such object detection, there is known a technique of determining whether a detection target object is included in each image of the number of images per unit time, and detecting the object when it is determined that the object is included more than a threshold number of times. However, in this related art, due to the small angle of view of the imaging device, the detection accuracy of the object may decrease, such as when an object passing within the angle of view cannot be detected.

[0017] Here, the problems of the above-described related art will be described. FIG. 2 is a diagram for explaining the problems of the related art. In the related art, an image captured by an imaging device such as a camera is transmitted to an external system such as an AI application, and various processes such as detecting an object included in the image are performed in the external system.

[0018] In such prior art, on the external system side such as an AI application, an object is detected when the image contains the object more than a threshold number of times per unit time. For example, when the detection frame rate of an imaging device is 10 fps, the threshold number of times is 4, and in the condition of detecting a person when the person to be detected appears in 4 frames, as shown in Fig. 2(1), when the angle of view is large, since the person appears in 5 frames before passing through the angle of view, the person can be detected.

[0019] On the other hand, even if the detection frame rate of the imaging device is 10 fps as in Fig. 2(1), when the angle of view is small, as shown in Fig. 2(2), since the person passes through the angle of view before appearing in 4 frames, the person cannot be detected. That is, even in a situation where an object must be detected, due to the slow processing speed of object detection (the detection frame rate to be processed), detection omission of the object may occur.

[0020] Note that the problem of detection accuracy due to the angle of view of the imaging device occurs not only depending on the angle at which the imaging device captures an image, but also depending on the environment in which the imaging device is installed. For example, even if it is a wide-angle camera, when there is an obstacle in front of the installed camera, when a wall surface continues to be captured, or when there is a range through which the object to be detected cannot pass, it is conceivable that the range where the target object can actually be detected is smaller than that of a narrow-angle camera.

[0021] Furthermore, in the prior art, resources may not be effectively utilized. For example, even though the angle of view of the imaging device is large, an unnecessarily high detection frame rate may be set. For example, in the case of a wide-angle camera, even though an accuracy sufficient to detect an object can be achieved with a setting of 10 fps, a setting of 20 fps, which is twice the value, may be made. In this case, by performing unnecessary image processing, another problem such as resource depletion may occur.

[0022] Therefore, the information processing apparatus 100 according to the embodiment includes a changing unit that changes the number of images per unit time used for detecting an object included in an image captured by the imaging apparatus 200 according to the angle of view of the imaging apparatus 200, and a detecting unit that executes object detection using each of the images having the changed number of images per unit time among the images captured by the imaging apparatus 200.

[0023] That is, the information processing apparatus 100 according to the embodiment automatically adjusts the detection frame rate when executing object detection to a value corresponding to the angle of view of the imaging apparatus 200 estimated from information such as an image and information about the imaging apparatus 200. Thereby, the information processing apparatus 100 can flexibly adjust the detection frame rate without depending on a specific detection frame rate, and improve the object detection accuracy.

[0024] [Configuration of Information Processing Apparatus] Next, the configuration of the information processing apparatus 100 will be described with reference to FIG. 3. As shown in FIG. 3, the information processing apparatus 100 includes a communication unit 110, a control unit 120, and a storage unit 130. Note that these units may be held by a plurality of devices in a distributed manner. The processing of each of these units will be described below.

[0025] The communication unit 110 is implemented by a NIC (Network Interface Card) or the like, and enables communication between the control unit 120 and an external device via a telecommunication line such as a LAN (Local Area Network) or the Internet. For example, the communication unit 110 enables communication between the external device and the control unit 120.

[0026] The storage unit 130 is implemented by a semiconductor memory device such as a RAM (Random Access Memory) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 130 stores information related to the imaging device 200, information related to the imaging device 200, the frame rate, and other information necessary for changing the number of images per unit time. Note that the information related to the imaging device 200 includes information such as the model, identification number, angle of view, specifications (sensitivity, focal length, etc.), settings (resolution, storage format, etc.), captured images, coordinates where an object was detected, distance to the object, and the number of images per unit time (detection frame rate). Also, the information stored in the storage unit 130 is not limited to the examples described above.

[0027] The control unit 120 is implemented using a CPU (Central Processing Unit), an NP (Network Processor), an FPGA (Field Programmable Gate Array), etc., and executes a processing program stored in a memory. As shown in FIG. 3, the control unit 120 includes an estimation unit 121, a change unit 122, and a detection unit 123. Hereinafter, each unit included in the control unit 120 will be described.

[0028] The estimation unit 121 estimates the angle of view of the imaging device 200 and outputs the estimation result to the change unit 122. For example, the estimation unit 121 estimates the angle of view of the imaging device 200 based on an image of a checkerboard captured by the imaging device 200. Note that the details of the estimation method using the checkerboard will be described later.

[0029] Also, the estimation unit 121 can input an image captured by the imaging device 200 to a learned model that has been trained to output the angle of view in response to the input of an image, and estimate the output angle of view as the angle of view of the imaging device 200.

[0030] In addition, the estimation unit 121 can also estimate the angle of view of the imaging device 200 based on information regarding the imaging device 200. For example, the estimation unit 121 estimates, as the angle of view of the imaging device 200, a range including coordinates at which an object was detected in the past by the imaging device 200, as information regarding the imaging device 200. As another example, the estimation unit 121 can also estimate the angle of view of the target imaging device 200 by referring to the angle of view of another imaging device 200 having the same model number as the target imaging device 200 or sharing the same specifications or settings. Note that the estimation unit 121 can also estimate, as the angle of view of the target imaging device 200, an average value or a median value of the angles of view of other imaging devices 200 having the same model number as the target imaging device 200 or sharing the same specifications or settings, or an angle of view commonly set among such other imaging devices 200.

[0031] In addition, the estimation unit 121 can also estimate the angle of view of the imaging device 200 using information on the distance to an object. For example, the estimation unit 121 estimates, as the angle of view of the imaging device 200, a value obtained by multiplying the angle of view of the imaging device 200 estimated using the coordinates at which the object was detected by the imaging device 200 by a predetermined magnification corresponding to the distance to the object. As another example, the estimation unit 121 can also estimate, as the angle of view of the imaging device 200, a value obtained by multiplying the angle of view of the imaging device 200 estimated from an image of a checkerboard captured by the imaging device 200 by a predetermined magnification corresponding to the distance to the object. Note that as the predetermined magnification, any value according to the purpose can be used, such as a value that becomes smaller as the distance to the object is shorter than a predetermined distance and larger as the distance is longer.

[0032] The change unit 122 changes the number of images per unit time. Specifically, the change unit 122 changes the number of images per unit time used for detecting an object included in an image captured by the imaging device 200 according to the angle of view of the imaging device 200. For example, when the angle of view of the imaging device 200 is smaller than a predetermined angle of view, the change unit 122 increases the number of images per unit time, and when the angle of view of the imaging device 200 is larger than the predetermined angle of view, the change unit 122 decreases the number of images per unit time used for detecting the object.

[0033] More specifically, when the angle of view of the imaging device 200 is smaller than a predetermined angle of view (for example, 100 degrees), the change unit 122 changes the number of images per unit time used for object detection to a double value. On the other hand, when the angle of view of the imaging device 200 is larger than a predetermined angle of view (for example, 100 degrees), the change unit 122 changes the number of images per unit time used for object detection to a half value.

[0034] Note that in the above, an example where the change unit 122 changes the number of images per unit time used for object detection to a double or half value has been shown. However, it is not particularly limited as long as it changes the number of images per unit time used for object detection, such as a value obtained by adding a predetermined value to or subtracting a predetermined value from the value before the change, or a value obtained by multiplying or dividing the value before the change by a predetermined value. Also, any value according to the purpose can be used for the predetermined angle of view and the predetermined value.

[0035] As another example, the change unit 122 inputs the angle of view of the imaging device 200 to a learned model that has been learned to output the number of images per unit time according to the input of the angle of view, and changes the output number of images per unit time to the number of images per unit time used for detecting an object included in the image captured by the target imaging device 200.

[0036] The detection unit 123 performs object detection using each of the images with the changed number of images per unit time among the images captured by the imaging device 200. For example, the detection unit 123 determines for each image whether the object to be detected is included in each of the images with the number of images per unit time changed by the change unit 122 among the images captured by the imaging device 200, and detects the object when it is determined that the object is included more than a threshold number of times.

[0037] Next, a specific example will be given and described for the estimation process of estimating the angle of view by the above-described estimation unit 121 and the change process of changing the number of images per unit time by the change unit 122.

[0038] [Estimation Process] Using FIGS. 4 and 5, the estimation process of the information processing apparatus 100 according to the embodiment will be described. FIGS. 4 and 5 are diagrams showing an example of the estimation process of the information processing apparatus 100 according to the embodiment.

[0039] As an example, the estimation unit 121 estimates the angle of view of the camera from the rows, columns, number, etc. of the squares shown in the image, using, for example, an image obtained by imaging a checkerboard with black squares drawn from a predetermined position. For example, as shown in FIG. 4, if four columns of black squares are shown in the image obtained by imaging a checkerboard with black squares drawn from a predetermined position, the angle of view of the camera is estimated to be 90 degrees, and if six columns are shown, it is estimated to be 120 degrees. That is, the angle of view of the camera is estimated from the range in which the black squares of the checkerboard are shown. In the above description, an example in which an image of a checkerboard with black squares is used for estimating the angle of view has been described, but the image is not limited to this as long as it can be used for estimating the angle of view.

[0040] As another example, the estimation unit 121 estimates the angle of view of the imaging device 200 from past detection results as information regarding the imaging device 200. For example, as shown in FIG. 5, when an obstacle exists in front of the imaging device 200, an object cannot be detected in a part within the range (for example, 120 degrees) that the imaging device 200 can image. In such a case, the estimation unit 121 estimates the range (for example, 90 degrees) in which the point group of the coordinates where the object was detected in the past is included as the angle of view.

[0041] Note that, in the above description, an example in which an obstacle exists has been described, but even when no obstacle exists, the estimation unit 121 can perform the same angle-of-view estimation process. As a result, when there are obstacles such as pillars and shelves, when the wall surface continues to be imaged, or when there is a range where a physical object to be detected cannot pass, the area where the object cannot be detected is excluded from the range that the imaging device 200 can image, and only the range where the object can be detected can be estimated as the angle of view.

[0042] As another example, the estimation unit 121 estimates, as the viewing angle of the imaging device 200, a value obtained by multiplying the viewing angle of the imaging device 200 estimated by the method described with reference to FIGS. 4 and 5 by a magnification factor corresponding to the distance. Here, for the predetermined magnification factor, a value is used such that the shorter the distance to the object is than a predetermined distance, the smaller the magnification factor is, and the longer the distance to the object is than the predetermined distance, the larger the magnification factor is. For example, when the distance to the object is 1.5 m and the predetermined distance is 3 m, 0.5 times is used as the predetermined magnification factor. For example, when the distance to the object is 6 m and the predetermined distance is 3 m, 1.5 times is used as the predetermined magnification factor.

[0043] More specifically, the estimation unit 121 estimates that 60 degrees, which is a value obtained by multiplying the viewing angle 120 degrees of the imaging device 200 estimated based on the image by a magnification factor 0.5 corresponding to the distance, is the viewing angle of the imaging device 200. Thereby, it can be estimated that the closer the distance to the object to be detected is, the smaller the viewing angle of the imaging device 200 is, and the farther the distance to the object to be detected is, the larger the viewing angle of the imaging device 200 is.

[0044] [Change processing] With reference to FIGS. 6 to 8, the change processing of the information processing apparatus 100 according to the embodiment will be described. FIGS. 6 to 8 are diagrams showing an example of the change processing of the information processing apparatus 100 according to the embodiment. In this example, an example will be described in which an AI application, which is an application that functions as the information processing apparatus 100 according to the viewing angle of the imaging device 200, changes the number of images per unit time.

[0045] For example, as shown in FIG. 6(1), when the number of images per unit time (detection frame rate) used by the imaging device 200 for object detection is 10 fps and the viewing angle of the imaging device 200 is small, when a person crosses the area captured by the imaging device 200, only 3 frames of the person can be captured within the viewing angle, and since the person passes by before being captured the required number of times (for example, 4 frames), the person cannot be detected.

[0046] Even when a person to be detected passes by, it is difficult to detect the person. Therefore, the changing unit 122 changes to increase the number of images per unit time used for object detection. For example, as shown in FIG. 6(2), when the viewing angle of the imaging device 200 is smaller than a predetermined viewing angle (for example, 100 degrees), the changing unit 122 changes the number of images per unit time to a double value. That is, the detection frame rate when performing object detection is changed from 10 fps to 20 fps.

[0047] As a result, as shown in FIG. 6(2), even when the viewing angle of the imaging device 200 is small, when a person passes through the area where the person is imaged by the imaging device 200, the person is imaged in 6 frames within the viewing angle, and the person can be detected. In this way, the information processing apparatus 100 can prevent a decrease in detection accuracy even when the viewing angle of the imaging device 200 is small by increasing the number of images per unit time used for object detection according to the viewing angle.

[0048] Subsequently, an example will be described in which an obstacle exists in front of the imaging device 200, and there is a range where an object cannot be detected within the range that the imaging device 200 can image. For example, as shown in FIG. 7(1), when the number of images per unit time used by the imaging device 200 for object detection is 10 fps and the viewing angle is small due to the existence of a range where an object cannot be detected, when a person crosses in front of the imaging device 200, the person passes by before being imaged the required number of times (for example, 4 frames) for detection, so the person cannot be detected.

[0049] Even when a person to be detected passes by, it is difficult to detect the person. Therefore, the changing unit 122 changes to increase the number of images per unit time used for object detection. For example, as shown in FIG. 7(2), when the viewing angle of the imaging device 200 is smaller than a predetermined viewing angle (for example, 100 degrees), the changing unit 122 changes the number of images per unit time used for object detection to a double value. That is, the detection frame rate when performing object detection is changed from 10 fps to 20 fps.

[0050] As a result, as shown in FIG. 7(2), even when the angle of view of the imaging device 200 is small, when a person passes through the area captured by the imaging device 200, the person can be captured in the angle of view for 6 frames, and the person can be detected. In this way, the information processing device 100 can prevent a decrease in detection accuracy even when the angle of view of the imaging device 200 is small by increasing the number of images per unit time used for object detection according to the angle of view.

[0051] Subsequently, an example in which an unnecessarily high detection frame rate is set will be described. In FIG. 8, even though the angle of view of the imaging device 200 is large, 20 fps is set as the number of images per unit time used for object detection. For example, as shown in FIG. 8(1), before the number of images per unit time used for object detection is changed by the changing unit 122, when a person crosses in front of the camera, 10 frames are captured, which is more than twice the number of times (for example, 4 frames) required for detection.

[0052] In such a case where resources are wasted, the changing unit 122 changes to reduce the number of images per unit time. For example, as shown in FIG. 8(2), the changing unit 122 changes the number of images per unit time to half the value. That is, the detection frame rate when performing object detection is changed from 20 fps to 10 fps.

[0053] As a result, as shown in FIG. 8(1), from a state where the angle of view of the imaging device 200 is large and the number of images per unit time is large, as shown in FIG. 8(2), the number of images per unit time can be reduced to reduce resources. In this way, the information processing device 100 can improve the efficiency of resources for an AI application in which resources are allocated more than necessary for object detection by decreasing the number of images per unit time according to the angle of view.

[0054] [Flowchart] Next, the processing flow by the information processing apparatus 100 will be described with reference to FIG. 9. Note that the following steps S101 to S104 can also be executed in a different order. Also, some of the following steps S101 to S104 may be omitted.

[0055] First, the estimation unit 121 estimates the angle of view of the imaging device 200 (step S101). For example, the estimation unit 121 estimates the angle of view of the imaging device 200 based on an image. Also, for example, the estimation unit 121 estimates the angle of view of the imaging device 200 based on information regarding the imaging device 200.

[0056] Subsequently, the change unit 122 changes the number of images per unit time used for detecting an object included in the image captured by the imaging device 200 according to the angle of view of the imaging device 200 (step S102). For example, when the angle of view of the imaging device 200 is smaller than a predetermined angle of view, the change unit 122 changes to increase the number of images per unit time.

[0057] Subsequently, the detection unit 123 determines whether each image of the number of images per unit time includes an object equal to or more than a threshold number of times (step S103). Here, when it is determined by the detection unit 123 that each image of the number of images per unit time does not include an object equal to or more than the threshold number of times (step S103 “NO”), the information processing apparatus 100 performs the processing of step S103 again.

[0058] On the other hand, when it is determined by the detection unit 123 that each image of the number of images per unit time includes an object equal to or more than the threshold number of times (step S103 “YES”), the detection unit 123 detects the object (step S104).

[0059] [Effect] The information processing apparatus 100 according to the embodiment includes a changing unit 122 that changes the number of images per unit time used for detecting an object included in an image captured by the imaging apparatus 200 according to the angle of view of the imaging apparatus 200, and a detecting unit 123 that executes object detection using each of the images having the changed number of images per unit time among the images captured by the imaging apparatus 200. Thereby, the information processing apparatus 100 can change the detection frame rate, which is the number of images per unit time used for object detection, according to the angle of view of the imaging apparatus 200, and improve the object detection accuracy.

[0060] The information processing apparatus 100 according to the embodiment includes an estimating unit 121 that estimates the angle of view of the imaging apparatus 200 based on an image captured by the imaging apparatus 200. Thereby, the information processing apparatus 100 estimates the angle of view of the imaging apparatus 200 based on the image captured by the imaging apparatus 200, and changes the detection frame rate, which is the number of images per unit time used for object detection, according to the estimated angle of view of the imaging apparatus 200, so that the object detection accuracy can be further improved.

[0061] The information processing apparatus 100 according to the embodiment includes an estimating unit 121 that estimates the angle of view of the imaging apparatus 200 based on information about the imaging apparatus 200. Thereby, the information processing apparatus 100 excludes a range where an object cannot be detected or adjusts according to the distance or the like based on the information about the imaging apparatus 200, estimates the angle of view of the imaging apparatus 200, and changes the detection frame rate, which is the number of images per unit time used for object detection, according to the estimated angle of view of the imaging apparatus 200, so that the object detection accuracy can be further improved.

[0062] When the angle of view of the imaging apparatus 200 is smaller than a predetermined angle of view, the changing unit 122 of the information processing apparatus 100 according to the embodiment increases the number of images per unit time. Thereby, when the angle of view of the imaging apparatus 200 is small, the information processing apparatus 100 can greatly change the detection frame rate, which is the number of images per unit time used for object detection, and further improve the object detection accuracy.

[0063] When the angle of view of the imaging device 200 is larger than a predetermined angle of view, the changing unit 122 of the information processing apparatus 100 according to the embodiment decreases the number of images per unit time. Thereby, when the angle of view of the imaging device 200 is large, the information processing apparatus 100 changes the detection frame rate, which is the number of images per unit time used for object detection, to be small, enabling effective utilization of resources.

[0064] The changing unit 122 of the information processing apparatus 100 according to the embodiment inputs the angle of view of the imaging device 200 to a learned model that has been learned to output the number of images per unit time in response to the input of the angle of view, and changes the output number of images per unit time to be the number of images per unit time used for detecting an object included in the image captured by the imaging device 200.

[0065] Thereby, the information processing apparatus 100 appropriately changes the detection frame rate, which is the number of images per unit time used for object detection, according to the angle of view of the imaging device 200 by using a model that has learned the relationship between the angle of view and the number of images per unit time, and can further improve the object detection accuracy.

[0066] [Program] Also, it is possible to create a program that describes the processing executed by the information processing apparatus 100 described in the above embodiment in a computer-executable language. In this case, by the computer executing the program, the same effects as the above embodiment can be obtained. Further, such a program may be recorded on a computer-readable recording medium, and the same processing as the above embodiment may be realized by causing the computer to read and execute the program recorded on this recording medium.

[0067] The information processing apparatus 100 is realized by, for example, a computer system 1000 as shown in FIG. 10. The computer system 1000 includes a CPU 1100, a RAM 1200, a ROM 1300, an HDD 1400, a communication interface (I / F) 1500, an input / output interface (I / F) 1600, and a media interface (I / F) 1700.

[0068] The CPU 1100 operates based on programs stored in the ROM 1300 or the HDD 1400, and controls each part. The ROM 1300 stores a boot program executed by the CPU 1100 when the computer system 1000 starts up, programs dependent on the hardware of the computer system 1000, and the like.

[0069] The HDD 1400 stores programs executed by the CPU 1100, data used by such programs, and the like. The communication interface 1500 receives data from other devices via the communication network NW and sends it to the CPU 1100, and sends data generated by the CPU 1100 to other devices via the communication network NW.

[0070] The CPU 1100 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse via the input / output interface 1600. The CPU 1100 acquires data from the input devices via the input / output interface 1600. Also, the CPU 1100 outputs the generated data to the output devices via the input / output interface 1600.

[0071] The media interface 1700 reads a program or data stored in the recording medium 1800 and provides it to the CPU 1100 via the RAM 1200. The CPU 1100 loads such a program from the recording medium 1800 onto the RAM 1200 via the media interface 1700 and executes the loaded program. The recording medium 1800 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc), a PD (Phase change rewritable Disk), etc., a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory, etc.

[0072] For example, when the computer system 1000 functions as the information processing apparatus 100 of the present disclosure, the CPU 1100 of the computer system 1000 realizes the functions of the information processing apparatus 100 by executing the program loaded onto the RAM 1200. The data in the storage unit 130 is stored in the HDD 1400. The CPU 1100 of the computer system 1000 reads and executes these programs from the recording medium 1800, but as another example, these programs may be acquired from other apparatuses via the communication network NW.

[0073] [Others] Although various embodiments have been described in detail in this specification with reference to the drawings, these multiple embodiments are examples and are not intended to limit the present invention to these multiple embodiments. The features described in this specification can be realized in various ways including various modifications and improvements based on the knowledge of those skilled in the art.

[0074] Also, the above-mentioned "part (module, -er suffix, -or suffix)" can be read as a unit, means, circuit, step, etc. For example, the communication part (communication module), the control part (control module), and the storage part (storage module) can be read as a communication unit, a control unit, and a storage unit, respectively.

Explanation of Reference Numerals

[0075] 100 Information processing device 110 Communication unit 120 Control unit 121 Estimation unit 122 Change unit 123 Detection unit 130 Memory unit 200 Imaging device

Claims

1. An estimation unit that estimates a range including coordinates where an object was detected in the past as the field of view angle of an imaging device, a change unit that changes the number of images per unit time used for detecting an object included in an image captured by the imaging device according to the field of view angle of the imaging device estimated by the estimation unit, and a detection unit that performs detection of the object using each of the images with the changed number of images per unit time among the images captured by the imaging device. An information processing apparatus, characterized by comprising the above.

2. The information processing apparatus according to claim 1, further comprising an estimation unit that estimates the field of view angle of the imaging device based on an image captured by the imaging device.

3. The information processing apparatus according to claim 1, wherein the change unit increases the number of images per unit time when the field of view angle of the imaging device is smaller than a predetermined field of view angle.

4. The information processing apparatus according to claim 1, wherein the change unit decreases the number of images per unit time when the field of view angle of the imaging device is larger than a predetermined field of view angle.

5. Input the field of view angle of the imaging device into a learned model trained to output the number of images per unit time according to the input of the field of view angle of the imaging device, and change the output number of images per unit time as the number of images per unit time used for detecting an object included in an image captured by the imaging device. The information processing apparatus according to claim 1, characterized by the above.

6. A method executed by an information processing apparatus, comprising: an estimation step of estimating a range including coordinates where an object was detected in the past as the field of view angle of the imaging device; a change step of changing the number of images per unit time used for detecting an object included in an image captured by the imaging device according to the field of view angle of the imaging device estimated in the estimation step; and a detection step of performing detection of the object using each of the images with the changed number of images per unit time among the images captured by the imaging device. An information processing method, characterized by including the above.

7. An estimation step of estimating a range including coordinates where an object was detected in the past as the field of view angle of the imaging device; a change step of changing the number of images per unit time used for detecting an object included in an image captured by the imaging device according to the field of view angle of the imaging device estimated in the estimation step; A detection step of performing detection of the object using each of the images of which the number of images per unit time has been changed among the images captured by the imaging device An information processing program characterized by causing a computer to execute the program

Images