JP2017146704A - Information processing device, information processing method and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce the labor required for monitoring a moving body reflected in an captured image based on light transmitted through a fisheye lens. SOLUTION: A normal traveling mobile vector calculation unit 111 that calculates a normal traveling mobile vector by learning based on a past captured image obtained by an imaging device that performs imaging based on light transmitted through a fisheye lens, and the above. The difference between the target moving body vector detection unit 112 that detects the target moving body vector based on the captured image of the target moving body obtained by the imaging device, the normal traveling moving body vector, and the target moving body vector sets a threshold value. A determination unit 113 for determining whether or not to exceed the limit is provided. [Selection diagram] Fig. 2

Description

  The present invention relates to an information processing apparatus, an information processing method, and a program.

  Conventionally, a monitoring device for monitoring a moving body has been disclosed (for example, see Patent Document 1). Such a monitoring device calculates the movement vector of the moving body by associating the moving bodies cut out from the captured consecutive frames. Then, the monitoring device sets a traveling direction vector of a moving body that performs normal traveling set in advance (hereinafter also referred to as “normally traveling moving body vector”) and a moving direction vector of the extracted moving body (hereinafter referred to as “target movement”). Abnormality is detected when the angle formed by "body vector") exceeds a threshold.

JP-A-6-325287

  However, the task of setting the traveling direction vector in advance is complicated for the user. Further, when construction is performed on the monitoring target area, it is necessary to correct the traveling direction vector once set, which is also complicated for the user. In particular, when an image is picked up based on light that has passed through a fisheye lens, the picked-up image is distorted, and the work of setting the traveling direction vector becomes more complicated.

  Therefore, the present invention has been made in view of the above problems, and an object of the present invention is to reduce the effort required to monitor a moving object reflected in a captured image based on light transmitted through a fisheye lens. It is to provide a technology that can.

  In order to solve the above-described problem, according to an aspect of the present invention, based on a past captured image obtained by an imaging device that performs imaging based on light transmitted through a fisheye lens, a normal traveling moving body vector is obtained by learning. A normal moving body vector calculating unit for calculating, a target moving body vector detecting unit for detecting a target moving body vector based on a captured image showing the target moving body obtained by the imaging device, and the normal moving body vector An information processing apparatus comprising: a determination unit that determines whether or not a difference from the target moving body vector exceeds a threshold value.

  The information processing apparatus may include a display control unit that controls a predetermined display when the determination unit determines that the difference exceeds the threshold value.

  When the determination unit determines that the difference exceeds the threshold, the display control unit cuts out an area corresponding to the position of the target moving body as a moving body area from a captured image in which the target moving body is reflected, The mobile object region may be converted into a mobile object region like a central projection method, and display of the mobile object region like the central projection method may be controlled.

  The information processing apparatus cuts out an area corresponding to a selection operation by a user from a captured image showing the target moving body as a selection area, converts the selection area into a selection area like a central projection system, and You may provide the display control part which controls the display of a selection area | region.

  The information processing apparatus may include a normal progress mobile body vector update unit that updates the normal progress mobile body vector based on the target mobile body vector.

  The imaging apparatus may be an omnidirectional camera in which a horizontal angle of view of the fisheye lens is 360 degrees.

  Further, according to another aspect of the present invention, based on a past captured image obtained by an imaging device that performs imaging based on light transmitted through a fisheye lens, a normal traveling moving body vector is calculated by learning; Detecting a target moving body vector based on a captured image showing the target moving body obtained by the imaging device, and whether or not a difference between the normal progressing moving body vector and the target moving body vector exceeds a threshold value. An information processing method is provided.

  Further, according to another aspect of the present invention, the computer calculates a normal traveling moving body vector by learning based on a past captured image obtained by an imaging device that performs imaging based on light transmitted through the fisheye lens. A normal moving body vector calculation unit; a target moving body vector detection unit that detects a target moving body vector based on a captured image in which the target moving body obtained by the imaging device is reflected; the normal traveling body vector and the target There is provided a program for causing an information processing device to function as an information processing device including a determination unit that determines whether or not a difference from a moving body vector exceeds a threshold value.

  As described above, according to the present invention, it is possible to reduce the time and effort required for monitoring a moving body that appears in a captured image based on light transmitted through a fisheye lens.

It is a figure for demonstrating the outline | summary of the information processing apparatus which concerns on one Embodiment of this invention. It is a block diagram which shows the function structure of the information processing apparatus which concerns on the embodiment. It is a figure which shows the relationship between the image | video imaged with an imaging device, and the image | video imaged by a center projection system. It is a figure which shows the example of a screen display-controlled by a display control part. It is a figure which shows the example of the normal progress mobile body vector computed by learning. It is a figure which shows the example of a screen newly controlled by the display control part.

  Exemplary embodiments of the present invention will be described below in detail with reference to the accompanying drawings. In addition, in this specification and drawing, about the component which has the substantially same function structure, duplication description is abbreviate | omitted by attaching | subjecting the same code | symbol.

  In the present specification and drawings, a plurality of constituent elements having substantially the same functional configuration may be distinguished by attaching different alphabets after the same reference numeral. However, when it is not necessary to particularly distinguish each of a plurality of constituent elements having substantially the same functional configuration, only the same reference numerals are given.

[Outline of information processing equipment]
FIG. 1 is a diagram for explaining the outline of the information processing apparatus. An overview of the information processing apparatus will be described with reference to FIG. As illustrated in FIG. 1, the information processing system 1 includes an information processing device 10 and an imaging device 20. Moreover, referring to FIG. 1, the vehicle M-1 exists on the road plane. In addition, in this embodiment, although it demonstrates taking a vehicle as an example as a moving body, a moving body is not limited to a vehicle. That is, this embodiment can be applied to other mobile bodies (for example, trains) other than vehicles.

  The imaging device 20 includes a fisheye lens 210 and performs imaging based on light transmitted through the fisheye lens 210. Thus, when imaging based on light transmitted through the fisheye lens 210 is performed, a wider range of images is captured in the vertical direction as the vertical angle of view of the fisheye lens 210 increases. When imaging based on light transmitted through the fisheye lens 210 is performed, a wider range of images is captured in the horizontal direction as the horizontal angle of view of the fisheye lens 210 increases.

  Here, the horizontal angle of view of the fisheye lens 210 is not particularly limited, but in the present embodiment, a case where the horizontal angle of view of the fisheye lens 210 is 360 degrees (when the imaging device 20 is an omnidirectional camera) will be described. In addition, the vertical angle of view of the fisheye lens 210 is not particularly limited. For example, if the vertical angle of view is 180 degrees or more, the vehicle M-1 traveling on the road plane is more surely included in the imaging region of the imaging device 20. In the example illustrated in FIG. 1, the imaging device 20 is installed downward, but the orientation in which the imaging device 20 is installed is not particularly limited.

  In FIG. 1, an imaging device 20 exists outside the information processing device 10, the information processing device 10 and the imaging device 20 are connected by wire, and the information processing device 10 is captured by the imaging device 20. An example is shown in which a captured image is acquired by receiving. However, the imaging device 20 may be incorporated in the information processing device 10. For example, the information processing apparatus 10 may acquire a captured image by reading a captured video recorded on a recording medium by the imaging apparatus 20.

[Details of this embodiment]
First, details of the present embodiment will be described. FIG. 2 is a block diagram illustrating a functional configuration of the information processing apparatus 10 according to the present embodiment. As illustrated in FIG. 2, the information processing apparatus 10 according to the present embodiment includes a control unit 110, an operation unit 120, a communication unit 130, a storage unit 140, and a display unit 150.

  The operation unit 120 receives an operation input from the operator. The operation unit 120 can provide the control unit 110 with an operation input from the operator. In this embodiment, the operation unit 120 is mainly assumed to be a mouse (although mainly assumed to be a click operation using a mouse), but the operation unit 120 is an input device other than a mouse (for example, Touch panel). When a touch panel is used as the operation unit 120, a tap operation on the touch panel can be used instead of a click operation using a mouse.

  The communication unit 130 is a communication interface for performing communication with the imaging device 20. The storage unit 140 can store a program and data for operating the control unit 110. In addition, the storage unit 140 can temporarily store various data necessary for the operation of the control unit 110. The display unit 150 can display various information on the display screen according to control by the control unit 110.

  In the example illustrated in FIG. 2, the operation unit 120, the communication unit 130, the storage unit 140, and the display unit 150 are provided inside the information processing apparatus 10, but the operation unit 120, the communication unit 130, and the storage unit 140 and the display unit 150 may be provided outside the information processing apparatus 10. The control unit 110 includes a normal progress moving body vector calculation unit 111, a target moving body vector detection unit 112, a determination unit 113, a normal progress moving body vector update unit 114, a display control unit 115, and an operation acquisition unit 116. Hereinafter, the details of each of these functional units included in the control unit 110 will be described.

  FIG. 3 is a diagram illustrating a relationship between a video imaged by the imaging device 20 (hereinafter also referred to as “omnidirectional video”) and a video imaged by the central projection method (hereinafter also referred to as “planar video”). It is. As shown in FIG. 3, light incident on the inside of the fisheye lens from the spherical surface S of the fisheye lens is projected from the spherical surface S of the fisheye lens onto the omnidirectional video imaging surface T, and the projected position r (X , Y) appears in the coordinates XY of the omnidirectional video Img-10. The omnidirectional video Img-10 shows the vehicle M-1 and the vehicle M-2. In addition, an arbitrary area in the omnidirectional video Img-10 can be easily converted into a planar image Img-20 like the central projection method.

  FIG. 4 is a diagram illustrating an example of a screen whose display is controlled by the display control unit 115. As shown in FIG. 4, the display control unit 115 controls display of the omnidirectional video Img-1 by the display unit 150. Here, it is assumed that the user wants to monitor the vehicle M-2 in detail. In such a case, the user performs a selection operation on the position of the vehicle M-2 shown in the omnidirectional video Img-1 (for example, a click operation after setting the pointer Pt to the position of the vehicle M-2).

  When the operation acquisition unit 116 acquires a selection operation input to the operation unit 120, the display control unit 115 cuts out an area corresponding to the selection operation as a selection area Re-1. At this time, information indicating the selection area Re-1 (for example, a frame surrounding the selection area Re-1 as shown in FIG. 4) may be displayed. Here, the area according to the selection operation is not limited. For example, when the omnidirectional video Img-1 is divided into a plurality of regions in advance, a region including the position where the selection operation is performed among the plurality of regions may be cut out as the selection region Re-1. Alternatively, a predetermined area based on the position where the selection operation is performed (for example, a predetermined area centered on the position where the selection operation is performed) may be cut out as the selection area Re-1.

  When the display control unit 115 cuts out the selection area Re-1, the display control section 115 converts the selection area Re-1 into a central projection method-like selection area (planar image Img-2), and the central projection method-like selection area (planar image Img). -2) display on the display unit 150 is controlled. In this way, by displaying both the omnidirectional video Img-1 and the flat video Img-2, the user performs overall monitoring with the omnidirectional video Img-1, and the flat video Img with less distortion. -2, it is possible to perform detailed monitoring of a part of the omnidirectional video Img-1.

  Here, when an abnormality occurs in a vehicle (for example, the vehicle M-1 and the vehicle M-2) shown in the omnidirectional video Img-1, the information processing apparatus 10 can detect the abnormality. At this time, as described above, the operation of setting the normal traveling moving body vector in advance is complicated for the user. In addition, when road construction is performed, it is necessary to correct the normal traveling vehicle vector that has been set once, which is also complicated for the user.

  In particular, when an image is picked up by the image pickup device 20 based on the light transmitted through the fisheye lens 210, the picked-up image (omnidirectional image Img-1) is distorted. Becomes more complicated. Therefore, in the present embodiment, when imaging is performed based on the light transmitted through the fisheye lens 210, a technique for reducing the labor required for monitoring the vehicle shown in the omnidirectional video Img-1 is proposed. .

  First, the normal traveling mobile body vector calculation unit 111 calculates a normal traveling mobile body vector by learning based on the past omnidirectional video obtained by the imaging device 20. FIG. 5 is a diagram illustrating an example of a normal traveling moving body vector calculated by learning. As illustrated in the omnidirectional video Img-11 in FIG. 5, the normal traveling mobile body vector calculation unit 111 performs a plurality of normal traveling mobile body vectors (for example, normal traveling mobile body vectors, for example) by learning based on the past omnidirectional video. Vn-1, Vn-2, etc.) can be calculated.

  In FIG. 5, for the sake of simplicity, the calculated density of the normally traveling moving body vector is shown to be smaller, but the calculated density of the normally traveling moving body vector is not particularly limited. For example, the normal traveling mobile body vector calculation unit 111 can also calculate a normal traveling mobile body vector for each pixel.

  Moreover, you may provide a restriction | limiting in the omnidirectional video utilized for learning. For example, an omnidirectional video showing a vehicle in which an abnormality has occurred may be excluded from the learning target. At this time, the omnidirectional video showing the vehicle in which the abnormality has occurred may be excluded from the learning target. For example, when an omnidirectional video in which a vehicle in which an abnormality has occurred is detected, the normal traveling mobile body vector calculation unit 111 may learn again from the beginning, or the vehicle in which an abnormality has occurred is reflected. Only the omnidirectional video may be excluded.

  Further, the learning method of the normal traveling mobile vector is not particularly limited. For example, the normal traveling vehicle vector calculation unit 111 calculates a movement vector over the entire road area of the omnidirectional video, and integrates the calculated movement vectors to normalize the entire road area (especially the road area where the vehicle travels). A progressive moving body vector may be calculated. Alternatively, the normal traveling mobile body vector calculation unit 111 may calculate the normal traveling mobile body vector by detecting the vehicle area from the omnidirectional video and integrating the detected movement vectors of the vehicle area.

  As described above, the movement vector integration by the normal traveling body vector calculation unit 111 is preferably performed over the entire predetermined area (for example, a road area, a vehicle area, etc.). Then, even if the movement vector is not constant in the region, the normal traveling mobile vector averaged in the region is calculated by integrating the movement vector over the entire region.

  When learning by the normal traveling body vector calculation unit 111 is completed and an omnidirectional video is newly obtained by the imaging device 20, the target mobile body vector detection unit 112 performs the target based on the omnidirectional video obtained by the imaging device 20. A moving body vector is detected. Here, the detection method of the target moving body vector is not particularly limited. For example, the target moving body vector detection unit 112 detects the vehicle area from the omnidirectional video by the background subtraction method, and detects the target moving body vector by the optical flow of each pixel of the detected vehicle area (or by template matching). . At this time, the target moving body vector detection unit 112 may reduce the variation in the direction of the target moving body vector for each pixel by a correction process such as averaging with respect to the direction of the target moving body vector.

  Subsequently, the determination unit 113 determines whether or not the difference between the normal progress moving body vector and the target moving body vector exceeds a threshold value. When the difference exceeds the threshold value, it is determined that an abnormality has occurred in the vehicle. At this time, the threshold value may be set by the user for each type of target moving body or may be determined in advance. The difference between the normal traveling mobile vector and the target mobile vector may include only one of the direction difference and the size difference between the normal traveling mobile vector and the target mobile vector, or both. May be included.

  In addition, since the omnidirectional video is continuously captured, the determination unit 113 adds time to determine whether or not the difference between the normal traveling moving body vector and the target moving body vector exceeds the threshold. It may be determined whether or not a general condition is satisfied. For example, the determination unit 113 may determine whether the difference for N vehicles has continued (N is an arbitrary natural number equal to or greater than 2) and has exceeded a threshold value.

  Examples of abnormalities occurring in the vehicle include “reverse running”, “stop”, “low speed”, “evacuation (running away from an object)”, and the like. The “reverse running” can be detected when the normal traveling moving body vector and the target moving body vector are in opposite directions. “Stop” can be detected when the target moving body vector is “0”. “Low speed” can be detected when the size of the target moving body vector is smaller than a predetermined amount than the size of the normal traveling moving body vector. “Escape” can be detected when the direction of the normal moving moving body vector and the target moving body vector differ by more than a predetermined angle. However, the abnormality that occurs in the vehicle is not limited to these.

  As a specific example, FIG. 5 shows a target moving body vector Vt-1 of the vehicle M-1. In this example, the determination unit 113 obtains a normal traveling moving body vector Vn-1 whose starting points coincide with the target moving body vector Vt-1 of the vehicle M-1, and obtains the target moving body vector Vt-1 and It is determined that the difference from the normal traveling mobile vector Vn-1 exceeds the threshold (determining that the target moving mobile vector Vt-1 and the normal traveling mobile vector Vn-1 are in opposite directions).

  FIG. 5 shows a target moving body vector Vt-2 of the vehicle M-2. In this example, the determination unit 113 acquires a normal traveling mobile vector Vn-2 whose start points coincide with the target mobile vector Vt-2 of the vehicle M-2, and the target mobile vector Vt-2 It is determined that the difference from the normal traveling mobile vector Vn-2 does not exceed the threshold (determining that the target moving mobile vector Vt-1 and the normal traveling mobile vector Vn-1 are in the same direction).

  When the determination by the determination unit 113 is completed, the normal traveling mobile body vector update unit 114 updates the normal traveling mobile body vector based on the target mobile body vector. Specifically, the target moving body vector Vt-1 is added to the normal traveling moving body vector Vn-1, and the target moving body vector Vt-2 is added to the normal moving moving body vector Vn-2. Then, if there is only one abnormal vehicle, it is determined that only that vehicle is abnormal, and if an abnormal vehicle that moves in the same way continues, the normal traveling vehicle vector Since the vehicle vector approaches the vehicle vector, it is possible to automatically follow changes in the situation of the vehicle traveling on the road.

  At this time, the normal traveling mobile vector update unit 114 assigns a weight to the target moving body vector Vt-1, and adds the weighted target moving body vector Vt-1 to the normal traveling mobile body vector Vn-1. Good (the target moving body vector Vt-2 may be weighted, and the weighted target moving body vector Vt-2 may be added to the normal traveling moving body vector Vn-2).

  As described above, when the difference between the normal traveling moving body vector and the target moving body vector exceeds the threshold, it is determined that an abnormality has occurred in the vehicle. In such a case, a predetermined operation may be performed. For example, the display control unit 115 may control a predetermined display by the display unit 150 when the difference between the normal traveling mobile vector and the target mobile vector exceeds a threshold value. FIG. 6 is a diagram illustrating an example of a screen that is newly controlled by the display control unit 115.

  As shown in FIG. 6, the display control unit 115 controls the display of the omnidirectional video Img-1 by the display unit 150. Here, as described above, it is assumed that the determination unit 113 determines that the difference between the normal traveling mobile body vector Vn-1 and the target mobile body vector Vt-1 of the vehicle M-1 exceeds the threshold value. In such a case, the display control unit 115 cuts out an area corresponding to the position of the vehicle M-1 from the omnidirectional video Img-1 as the moving body area Re-2. At this time, information indicating the moving body region Re-2 (for example, a frame surrounding the moving body region Re-2 as shown in FIG. 6) may be displayed.

  Here, the area | region according to the position of the vehicle M-1 is not limited. For example, when the omnidirectional video Img-1 is divided into a plurality of regions in advance, a region including the position of the vehicle M-1 among the plurality of regions may be cut out as the moving body region Re-2. Or the predetermined area | region (For example, the predetermined area | region centering on the position of the vehicle M-1) on the basis of the position of the vehicle M-1 may be cut out as the mobile body area | region Re-2.

  When the display control unit 115 cuts out the moving object region Re-2, the display control unit 115 converts the moving object region Re-2 into a moving object region (planar image Img-2) like the central projection method, and the moving object region like the central projecting method. The display by the display unit 150 of (planar image Img-2) is controlled. Thus, by displaying both the omnidirectional video Img-1 and the planar video Img-2 in which the abnormal vehicle M-1 is displayed, the user performs overall monitoring by the omnidirectional video Img-1. Further, it is possible to perform detailed monitoring of the abnormal vehicle M-1 by the planar image Img-2 with less distortion.

  The display control unit 115 controls the display by the display unit 150 of the center projection method-like moving body region (planar image Img-2), and an abnormal vehicle M-1 is present in the center projection method-like moving body region. You may control the display to the effect. For example, as shown in FIG. 6, the display control unit 115 may display the mark Fr in a region where the abnormal vehicle M-1 is reflected in the central projection type moving object region (planar image Img-2). Alternatively, a warning message indicating that an abnormal vehicle has been detected may be displayed.

[Effect of this embodiment]
As described above, according to the present embodiment, the information processing apparatus 10 including the normal moving body vector calculation unit 111, the target moving body vector detection unit 112, and the determination unit 113 is provided. Here, the normal traveling moving body vector calculation unit 111 calculates the normal traveling moving body vector by learning based on the past captured video obtained by the imaging device 20 that performs imaging based on the light transmitted through the fisheye lens 210. . In addition, the target moving body vector detection unit 112 detects the target moving body vector based on the captured video that shows the target moving body obtained by the imaging device 20. The determination unit 113 determines whether or not the difference between the normal traveling mobile vector and the target mobile vector exceeds a threshold value.

  According to such a configuration, specifically, the normal traveling mobile body vector is set by learning. In addition, correction of the normal traveling mobile vector once set is also performed by learning. Therefore, it is possible to reduce the effort required to monitor the moving body shown in the captured image based on the light transmitted through the fisheye lens 210.

  In addition, when detecting a vehicle abnormality by a vehicle tracking process based on a distorted image such as an omnidirectional image, it is difficult to track the vehicle directly from the distorted image. It is common to detect vehicle anomalies. At this time, the processing cost may increase because it is necessary to convert the omnidirectional video into a plurality of planar videos. On the other hand, according to the present embodiment, in order to detect a vehicle abnormality from a distorted image such as an omnidirectional image without depending on the vehicle tracking process, the omnidirectional image is converted into a plane image in order to detect the vehicle abnormality. There is no need and processing costs are reduced.

[Description of modification]
The preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, but the present invention is not limited to such examples. It is obvious that a person having ordinary knowledge in the technical field to which the present invention pertains can come up with various changes or modifications within the scope of the technical idea described in the claims. Of course, it is understood that these also belong to the technical scope of the present invention.

  For example, in the above description, an example in which only one central projection method-like selection area (planar image Img-2 in FIG. 3) is displayed has been described. However, a plurality of selection areas for the central projection method may be displayed. At this time, for example, when a region in which the difference between the normal traveling moving body vector and the target moving body vector exceeds a threshold is detected, any of the plurality of central projection-like selection areas is a central-projection-like moving body. It may be switched to a region. Then, a predetermined display (for example, blinking display or the like) may be attached to the moving object region like the central projection method.

  In the above description, an example in which a fisheye lens is used has been described. When using a fish-eye lens, as described above, imaging is performed by projecting from a spherical surface to a plane, while when using a normal lens, the imaging is performed by projecting from a plane to a plane. . The image pickup method using a normal lens is called a center projection method, and is characterized in that there is no distortion in the result of image pickup by the center projection method. On the other hand, an imaging method using a fisheye lens corresponds to a projection method other than the central projection method, and specifically corresponds to a distance projection method, a solid angle projection method, an orthogonal projection method, and the like.

  Further, for example, each block configuring the control unit 110 of the information processing apparatus 10 includes, for example, a CPU (Central Processing Unit), a RAM (Random Access Memory), and the like, and a program stored in the storage unit 140 is stored in the CPU. The function can be realized by being expanded in the RAM and executed. At this time, a computer-readable recording medium that records the program can also be provided. Or each block which comprises the control part 110 may be comprised by the hardware for exclusive use, and may be comprised by the combination of several hardware.

DESCRIPTION OF SYMBOLS 1 Information processing system 10 Information processing apparatus 20 Imaging apparatus 210 Fisheye lens 110 Control part 111 Normal progress mobile body vector calculation part 112 Target mobile body vector detection part 113 Judgment part 114 Normal progress mobile body vector update part 115 Display control part 116 Operation acquisition part 120 Operation unit 130 Communication unit 140 Storage unit 150 Display unit

Claims (8)

A normal traveling moving body vector calculation unit that calculates a normal traveling moving body vector by learning based on past captured images obtained by an imaging device that performs imaging based on light transmitted through the fisheye lens;
A target moving body vector detection unit that detects a target moving body vector based on a captured image in which the target moving body obtained by the imaging device is reflected;
A determination unit that determines whether or not a difference between the normal traveling mobile vector and the target mobile vector exceeds a threshold;
An information processing apparatus comprising: The information processing apparatus includes:
A display control unit that controls a predetermined display when the determination unit determines that the difference exceeds the threshold;
The information processing apparatus according to claim 1. When the determination unit determines that the difference exceeds the threshold, the display control unit cuts out an area corresponding to the position of the target moving body as a moving body area from a captured image in which the target moving body is reflected, Converting the mobile object region into a mobile object region like a central projection method, and controlling display of the mobile object region like the central projection method;
The information processing apparatus according to claim 2. The information processing apparatus includes:
A region corresponding to the selection operation by the user is extracted from the captured image showing the target moving body as a selection region, the selection region is converted into a central projection method-like selection region, and the display of the central projection method-like selection region is controlled. Including a display control unit,
The information processing apparatus according to claim 1. The information processing apparatus includes:
A normal progress mobile vector update unit that updates the normal progress mobile vector based on the target mobile vector;
The information processing apparatus according to claim 1. The imaging device is an omnidirectional camera in which a horizontal angle of view of the fisheye lens is 360 degrees.
The information processing apparatus according to claim 1. Calculating a normal traveling body vector by learning based on a past captured image obtained by an imaging device that performs imaging based on light transmitted through the fisheye lens;
Detecting a target moving body vector based on a captured image showing the target moving body obtained by the imaging device;
Determining whether a difference between the normal traveling mobile vector and the target mobile vector exceeds a threshold;
Including an information processing method. Computer
A normal traveling moving body vector calculation unit that calculates a normal traveling moving body vector by learning based on past captured images obtained by an imaging device that performs imaging based on light transmitted through the fisheye lens;
A target moving body vector detection unit that detects a target moving body vector based on a captured image in which the target moving body obtained by the imaging device is reflected;
A determination unit that determines whether or not a difference between the normal traveling mobile vector and the target mobile vector exceeds a threshold;
A program for causing an information processing apparatus to function.

Images