Information processing apparatus

Abstract

To improve estimation accuracy of a moving track and a target point of movement of a pedestrian.SOLUTION: The information processing apparatus 10 includes an acquisition unit 14 and a control unit 15. The acquisition unit 14 acquires an image. The control unit 15 calculates the position of the animal included as a partial image in the image acquired by the acquisition unit 14. The control unit 15 predicts the movement trajectory and the target point of the animal based on the difference in time associated with each of the plurality of images including the animal as a partial image and the difference in position of the animal calculated for each of the plurality of images.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device. [Background technology]

[0002] With the development of autonomous driving technology, mobile objects with low-speed autonomous driving functions that travel on sidewalks are beginning to be put into practical use. For such mobile objects, there is a need to predict the routes that pedestrians will take. For example, a route prediction device that predicts the routes that pedestrians will take has been proposed (see Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2023-171455 Summary of the Invention [Problem to be solved by the invention]

[0004] To predict pedestrian paths, it is desirable to estimate the destination point of the pedestrian's movement. However, there is room for improvement in estimating the destination point.

[0005] An object of the present disclosure is to improve the accuracy of estimating the movement trajectory and destination points of pedestrian movement. [Means for solving the problem]

[0006] An information processing device according to a first aspect comprises: an acquisition unit that acquires an image; The system is equipped with a control unit that calculates the position of an animal included as a partial image in an image acquired by the acquisition unit, and predicts the movement trajectory and target point of the animal based on the difference in time associated with each of multiple images that include the animal as a partial image and the difference in the position of the animal calculated for each of the multiple images. [Effects of the Invention]

[0007] According to the present disclosure, the accuracy of estimating the movement trajectory and destination point of a pedestrian's movement is improved. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a functional block diagram showing a schematic configuration of a mobile object including an information processing device according to an embodiment of the present invention. [Figure 2] 1. FIG. 4 is a diagram showing a change in a person's position over time, illustrating a method for calculating a movement trajectory using a second prediction method in the information processing device of FIG. [Figure 3] 1. FIG. 4 is a diagram showing a change in a person's position over time, illustrating a method for calculating a movement trajectory using a third prediction method in the information processing device of FIG. [Figure 4] 10 is a diagram showing the change in the position of a person and the position of a specific object over time to explain the correction of the movement trajectory during execution of the third prediction method of FIG. 3. FIG. [Figure 5] 1. FIG. 4 is a diagram showing the positions of a person, a target point, and an obstacle as viewed from above, for explaining a method for calculating a secondary target point by the information processing device of FIG. 1 when an obstacle is present. [Figure 6] 6 is a top view of the positions of a person, a target point, and an obstacle, illustrating which edge is selected when the obstacle in FIG. 5 has multiple edges in one direction. FIG. [Figure 7] 6 is a top view of the positions of a person, a target point, and an obstacle, illustrating a state in which the inclination angle of the end that is the maximum inclination angle among multiple ends in one direction of the obstacle in FIG. 5 is 90 degrees. FIG. [Figure 8] 2 is a flowchart illustrating a prediction process executed by the control unit of FIG. 1. [Figure 9] 2 is a flowchart for explaining a detouring process executed by the control unit of FIG. 1. [Figure 10] 2 is a flowchart for explaining a restart process executed by the control unit of FIG. 1. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. In the following drawings, the same components are denoted by the same reference numerals.

[0010] The information processing device of the present disclosure may provide a moving body having a low-speed automatic driving function with a travel trajectory and a destination point, which will be described later, as information. For example, as shown in FIG. 1, an information processing device 10 may be provided in a moving body 11 having a low-speed automatic driving function.

[0011] The mobile object 11 having a low-speed automatic driving function is, for example, a vehicle for transporting luggage, whose upper speed limit is approximately the same as that of a pedestrian. The mobile object 11 may have a camera 12, an information processing device 10, and a control device 13. In other words, the camera 12 and the information processing device 10 may be manufactured as separate devices and mounted on the mobile object 11. Alternatively, the information processing device 10 may be manufactured as a device built into the camera 12 and mounted on the mobile object 11.

[0012] The camera 12 may be, for example, a monocular camera or a stereo camera. The camera 12 may be installed so as to be able to capture an image of the external view of the mobile body 11. The camera 12 may be mounted at a predetermined position and orientation relative to the mobile body 11. The mounting position and mounting orientation of the camera 12 relative to the mobile body 11 may be recognized as information by the camera 12 or the information processing device 10.

[0013] The camera 12 may capture an image and generate it as information. The camera 12 may have a timer. The camera 12 may add the time measured by the timer to the image as information. In a configuration in which the mounting position and mounting attitude are stored in a built-in memory, the camera 12 may add the mounting position and mounting attitude to the image as information. The camera 12 may transmit the image together with the added information to the information processing device 10.

[0014] As will be described later, the information processing device 10 may estimate the movement trajectory and destination point of a surrounding animal based on an image acquired from the camera 12. The animal is, for example, a person. However, the animal is not limited to a person and may be a dog, deer, monkey, bear, cat, etc. Hereinafter, in this specification, the animal will be described as a person. The information processing device 10 may transmit the estimated movement trajectory and destination point as information to the control device 13.

[0015] The control device 13 may control the operation of the mobile object 11. For example, the control device 13 may control the mobile object 11 to drive automatically based on the detection results of a position sensor such as a GNSS, a gyro sensor, a speed sensor, etc., that the mobile object 11 has, as well as a set destination, a surrounding map, etc. Specifically, the control device 13 may control the motor, brakes, steering angle, etc., based on the control results.

[0016] Furthermore, the control device 13 may avoid people and correct the movement route of the moving object 11 based on the movement trajectory and the target point received as information from the information processing device 10.

[0017] The following describes in detail the configuration of the information processing device 10. The information processing device 10 includes an acquisition unit 14 and a control unit 15.

[0018] The acquisition unit 14 acquires images. The acquisition unit 14 may acquire images from, for example, the camera 12. The acquisition unit 14 is not limited to acquiring images from the camera 12 mounted on the mobile object 11, but may acquire images as information from a camera provided on a roadside device or the like around the mobile object 11. The images acquired from the camera provided on a roadside device or the like around the mobile object 11 may include information about the position and orientation of the camera in the world coordinate system.

[0019] The acquisition unit 14 may acquire information from a sensor other than a camera. For example, the acquisition unit 14 may acquire the positions of surrounding objects as information from a distance measuring device such as Lidar.

[0020] The acquisition unit 14 may further have a function of outputting information. Specifically, the acquisition unit 14 may transmit the movement trajectory and the destination point predicted by the control unit 15 as information to the control device 13, as will be described later.

[0021] The acquisition unit 14 may be, for example, a physical connector or a wireless communication device. Physical connectors include electrical connectors compatible with transmission of electrical signals, optical connectors compatible with transmission of optical signals, and electromagnetic connectors compatible with transmission of electromagnetic waves. Electrical connectors include connectors conforming to IEC 60603, connectors conforming to the USB standard, connectors compatible with RCA terminals, connectors compatible with S terminals specified in EIAJ CP-1211A, connectors compatible with D terminals specified in EIAJ RC-5237, connectors conforming to the HDMI (registered trademark) standard, and connectors compatible with coaxial cables, including BNC. Optical connectors include various connectors conforming to IEC 61754. Wireless communication devices include wireless communication devices conforming to various standards, including Bluetooth (registered trademark) and IEEE 802.11.

[0022] The control unit 15 is configured to include at least one processor, at least one dedicated circuit, or a combination thereof. The processor is a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor specialized for specific processing. The dedicated circuit may be, for example, an FPGA (Field-Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), or the like. The control unit 15 may control the operation of the information processing device 10.

[0023] The control unit 15 may further include a storage unit. The storage unit may include any storage device, such as a RAM (Random Access Memory) or a ROM (Read Only Memory). The storage unit may store various programs that cause the control unit 15 to function and various information used by the control unit 15.

[0024] For example, the storage unit may store as information the mounting position and mounting attitude of the camera 12 on the moving body 11. Furthermore, for example, the storage unit may store a conversion formula or conversion table for converting the coordinates of a pixel in a two-dimensional coordinate system into the world coordinate system when the pixel constituting an image acquired from the camera 12 indicates an object on the road surface or floor surface. Furthermore, for example, the storage unit may store as information a map. The map may include as information the position of a specific object, which will be described later.

[0025] The control unit 15 may add the time of acquisition as information to the image acquired by the acquisition unit 14. The control unit 15 may add the time of acquisition in a configuration in which the time is not added to the image transmitted by the camera 12.

[0026] The control unit 15 may determine the presence or absence of a person around the moving object 11 based on the information acquired by the acquisition unit 14. Specifically, the control unit 15 determines whether or not a partial image of a person is included in the image acquired by the acquisition unit 14. The control unit 15 may determine the presence or absence of a person, for example, by image analysis or by using a discrimination model constructed by machine learning. Furthermore, the control unit 15 may generate a distance image based on the distance measurement results acquired by the distance measurement sensor, and determine the presence or absence of a person based on the distance image. Specifically, the control unit 15 may determine the presence or absence of a person based on the shape of a point cloud that can be considered to be in the same distance range in the distance image.

[0027] When the control unit 15 recognizes the presence of a person around the moving object 11, it calculates the position of the person. The position of the person may be indicated by a position in real space, in other words, coordinates in a world coordinate system. Hereinafter, in the description of this specification, unless otherwise specified, the position of a person means a position in real space. The control unit 15 may calculate the position of the person based on an image using any method.

[0028] For example, in a configuration in which camera 12 is a stereo camera and acquires stereo images, control unit 15 may calculate the position of the person using triangulation technology based on the positions of partial images of the person in each of the two images. Furthermore, in a configuration in which camera 12 is a monocular camera, control unit 15 may perform distance measurement using image aberration, distance measurement using AI technology based on the relationship between the image and the distance, etc. Furthermore, for images acquired from a camera installed on a roadside unit or the like around mobile object 11, control unit 15 may also calculate the position of the person using the position and orientation of the camera in the world coordinate system. Furthermore, in a configuration in which ranging images are generated, control unit 15 may calculate the position of the person based on the distance corresponding to the point cloud forming the person whose presence is recognized in the ranging image.

[0029] The control unit 15 may store a partial image of a person whose presence has been recognized in the image of each frame and the position of the person in a buffer memory that is part of the storage unit.

[0030] The control unit 15 may determine whether a partial image of a person identical to a person present in the image of the most recent frame is included in the image of the frame immediately preceding the current frame. The control unit 15 may perform the above determination using any method. For example, the control unit 15 may perform the determination using pattern matching, a discrimination model based on machine learning, or the like. When the image of the most recent frame contains partial images of multiple people, the control unit 15 may perform the above determination for each person. The control unit 15 may recognize the position of the person included as a partial image in each of the images of the multiple frames based on the above determination.

[0031] The control unit 15 calculates the time difference associated with each of a plurality of frame images that include the same person as a partial image. The control unit 15 also calculates the position difference of the person calculated for each of the plurality of frame images. The control unit 15 predicts the movement trajectory and target point of the person based on the time difference and the position difference.

[0032] Specifically, the control unit 15 predicts the movement trajectory based on the time difference and the position difference. The control unit 15 may calculate a position on the movement trajectory that corresponds to the position of the person calculated for the image of the latest frame. The control unit 15 may calculate the movement speed of the person in the image. The control unit 15 may predict, as a destination point, a position obtained by moving the person from the corresponding position as a starting point along the movement trajectory at the movement speed for a predetermined movement time. The predetermined movement time is set to any time that does not result in an extremely low prediction accuracy. For example, the predetermined movement time may be set to 20 seconds, 15 seconds, 10 seconds, 5 seconds, 3 seconds, etc.

[0033] Various methods for predicting travel trajectories and destinations are described in more detail below.

[0034] In the first prediction method, the control unit 15 may calculate a first position and a second position of a person for each of a first image and a second image as a plurality of images. The first image may be the most recent image among the images stored in the storage unit, or may be an image with a time within a range that can be considered as the current time for prediction. The second image may be older than the first image, for example, may be an image of the immediately preceding frame. The control unit 15 may predict a first straight line passing through the first position and the second position as a movement trajectory.

[0035] The control unit 15 may calculate the moving speed by dividing the difference between the first position and the second position by the difference between the time of the first image and the time of the second image. The control unit 15 may predict, as a destination point, a position reached by moving from the first position along the moving trajectory in a predetermined moving time.

[0036] In the second prediction method, the control unit 15 may use three or more frames of images as the multiple images. The control unit 15 may calculate the position of the person for each of the multiple images. The three or more frames of images may include the most recent image stored in the storage unit or an image within a first time range from the most recent image. The first time range is a range in which the predicted value can be kept within the error range even if the most recent image is replaced in predicting the actual movement trajectory. As shown in FIG. 2, the control unit 15 may calculate an approximate line aL based on the calculated positions of three or more people ps. The drawing position of the person ps indicates the position of the person ps at each time. Furthermore, t(n) following the symbol ps indicates the time at which the person is located at that position. n=0 is the most recent time. The smaller the value of n, the further back in time it goes. The approximate line aL may be calculated, for example, using the least squares method. The control unit 15 may predict the approximate line aL as the movement trajectory.

[0037] The control unit 15 may calculate, as the first position p1, a position on the approximate line aL that corresponds to the position of the person ps calculated for the most recent image among the multiple images. The position that corresponds to the approximate line aL is, for example, the intersection of the approximate line aL and a perpendicular line that is dropped from the original position to the approximate line aL.

[0038] Furthermore, the control unit 15 may calculate a position on the approximate line aL that corresponds to the position of the person calculated for any two images. One of the two images may be the most recent image among the multiple images. The control unit 15 may calculate the distance between the two corresponding positions on the approximate line.

[0039] The control unit 15 may calculate the time difference between the two images. The control unit 15 may calculate the moving speed of the person ps by dividing the distance between two corresponding positions on the approximate line aL by the time difference. The control unit 15 may predict, as a destination point, a position that is reached by moving from the first position p1 as a starting point along the moving trajectory by a moving distance for a predetermined moving time.

[0040] In the third prediction method, the control unit 15 may use three or more frames of images as the multiple images, as in the second prediction method. The control unit 15 may calculate the position of the person ps for each of the multiple images. The control unit 15 may calculate a judgment value based on the multiple calculated positions. If the judgment value satisfies a predetermined condition, the control unit 15 may predict the movement trajectory and the destination point using the third prediction method. If the judgment value does not satisfy the predetermined condition, the control unit 15 may predict the movement trajectory and the destination point using the first prediction method or the second prediction method.

[0041] The judgment value is, for example, as described above, the first distance between the position of person ps calculated for the latest image and an approximate line aL based on the position of person calculated for each of the multiple images. The first distance may be the length of a perpendicular line drawn from the position of person ps calculated for the latest image to the approximate line aL based on the position of person calculated for each of the multiple images. In a configuration in which the judgment value is the first distance, the predetermined condition may be that the first distance is equal to or greater than a distance threshold.

[0042] The distance threshold may be set to a statistically determined value that exceeds the sway experienced by a typical person when walking straight. The distance threshold may be set based on the variation in the distances to the approximate line aL of the person's position calculated for each of the multiple images. For example, 3σ may be applied to the distance threshold with respect to the standard deviation σ of the distances to the approximate line aL calculated for the multiple images.

[0043] Alternatively, the judgment value is, for example, a first acceleration of the person based on three or more positions of the person ps calculated for each of the multiple images and three or more times for each of the multiple images.

[0044] To calculate the first acceleration, the velocity of the person ps may be calculated for each image. The velocity of the person in any image may be calculated by dividing the distance traveled by the person's position from the image in the immediately preceding frame by the time difference between any one image and the image in the immediately preceding frame. The second acceleration may be calculated by dividing the difference in velocity calculated for two consecutive frames by the time difference between the two images. The second acceleration calculated for the most recent image may be determined as the first acceleration. Alternatively, the second acceleration calculated for an image whose time falls within a second time range from the most recent time may be determined as the first acceleration. The second time range is a range in which the prediction accuracy can be kept within an error range even when the most recent image is replaced in predicting the actual direction change of the person.

[0045] In a configuration in which the judgment value is a first acceleration, the predetermined condition may be that the first acceleration is equal to or greater than an acceleration threshold. The acceleration threshold may be set to a value that determines that a typical person is deviating from a straight line and changing direction. Specifically, the first acceleration may be a vector, and the product of the sine of the angle between the direction of the person's velocity in the most recent image and the direction of the first acceleration and the acceleration threshold may be compared with the acceleration threshold. The acceleration threshold may be variable depending on the velocity. For example, the acceleration threshold may be changed so that it increases as the velocity of the person in the most recent image increases and decreases as the velocity of the person decreases.

[0046] When the above-described predetermined condition is satisfied, the control unit 15 may calculate a third acceleration based on the position of the person ps calculated for each of the multiple images and the time associated with each of the multiple images. The third acceleration may be calculated for each of the multiple images. A specific method for calculating the third acceleration may be a method similar to the above-described method for calculating the first acceleration.

[0047] The control unit 15 may predict the movement trajectory and the target point based on the position and velocity of the person ps calculated for the most recent image and the third acceleration. Specifically, the control unit 15 may calculate the movement velocity based at least on the position and velocity of the person ps calculated for the most recent image and the third acceleration. The calculated movement velocity may change with time as a variable.

[0048] For example, as shown in Figure 3, when person ps changes direction along a curve, the direction of each position, or in other words, the acceleration a(n) at each time, changes. n is an integer and indicates the frame number. n=0 corresponds to the image of the frame at the most recent time. The smaller n is, the earlier it corresponds to the image of the frame. The larger n is beyond 0, the more it corresponds to the image of a frame expected in the future. In Figure 3, the drawing position of person ps indicates the position of person ps at each time. The number inside person ps represents time t(n).

[0049] For example, when turning along a curve, the acceleration changes so that it moves toward the center like a circular motion (see a(t(-2))~a(t(3))). Also, as the acceleration changes, the direction of the velocity also changes (v(t(-1))~v(t(3)).

[0050] Therefore, the control unit 15 may calculate the moving speed until the turn as a function of time based on the position and speed of the person Ps from the start time to the end time of the turn, by adding the position and speed of the person Ps calculated for the image with the most recent associated time among the multiple images. The end time of the turn is, for example, the time when a statistically determined time has elapsed as the time the turn will continue. The time the turn will continue may be changed depending on the speed of the person Ps. For example, the time may be determined so that the faster the speed of the person Ps is, the shorter the time, and so that the slower the speed of the person Ps is, the longer the time.

[0051] The control unit 15 may include a constant speed along a straight line after a direction change in the function of the moving speed. The control unit 15 may predict the moving trajectory and the destination point based on the calculated moving speed and a predetermined moving time. Specifically, the control unit 15 may predict, as the moving trajectory, a trajectory obtained by moving along a curve while changing the speed from the time (t(-2)) when the direction change started until the predetermined time (t(-2) to t(3)) has elapsed, and thereafter moving in a straight line at the speed (v(4)) at the position where the curved movement occurred until the latest time (t(g)) when the predetermined moving time (t(0) to t(g)) has elapsed.

[0052] If the judgment value satisfies a predetermined condition, the control unit 15 may calculate a second line based on the time difference between each of the multiple images and the position difference between the person ps calculated for each of the multiple images. The second line may be the first line calculated by the first prediction method. Alternatively, the second line may be an approximate line aL calculated by the second prediction method.

[0053] 4, the control unit 15 may further determine whether a specific object so is located between the second straight line L2 and the movement trajectory tj predicted by the third prediction method. The specific object so may be a signboard, a toilet, a store, a side road, etc. The control unit 15 may detect the specific object so based on an image acquired by the acquisition unit 14. Alternatively, the control unit 15 may detect the specific object so based on the specific object so in a map stored in the storage unit and the position and orientation of the moving object 11 in real space detected by a position sensor and an orientation sensor mounted on the moving object 11, respectively.

[0054] When the control unit 15 recognizes the presence of the specific object so, it may set the position of the specific object so as a target point. Furthermore, the control unit 15 may correct the movement trajectory predicted by the third prediction method so that the movement trajectory heads toward the target point.

[0055] The control unit 15 may change the second straight line L2 depending on the magnitude of the acceleration, etc. For example, the control unit 15 may change the starting point of the second straight line L2 depending on the acceleration. Specifically, as the acceleration decreases, the starting point may be set to a position further along the trajectory of the curved movement in the third prediction method from the position of the person ps in the most recent image. Furthermore, a straight line extended in the direction of the speed at that position may be recognized as the second straight line L2.

[0056] The control unit 15 may determine whether or not an obstacle exists between the position of the person ps and the predicted target point. The position of the person ps used for the determination may be calculated for the most recent image. The control unit 15 may determine whether or not an obstacle exists by, for example, image analysis of the image or distance image acquired by the acquisition unit 14.

[0057] When the control unit 15 recognizes the presence of an obstacle, it may calculate the area occupied by the obstacle. The area occupied by the obstacle may be an area viewed vertically from above. The area of ​​the obstacle is, for example, an area defined in real space. Specifically, the control unit 15 determines whether an obstacle exists between the position of the person and the predicted destination point based on a determination of whether the area of ​​the obstacle is located on the movement trajectory.

[0058] When the control unit 15 determines that there is an obstacle on the movement trajectory, it may calculate a secondary target point to avoid the obstacle. The control unit 15 may correct the movement trajectory so that the movement trajectory passes through the secondary target point. When the control unit 15 determines that there is an obstacle on the movement trajectory, it may store the most recently predicted target point tp in the memory unit and temporarily suspend prediction of the movement trajectory and the target point. Correction of the movement trajectory based on the secondary target point will be described in detail below.

[0059] As shown in FIG. 5, if an obstacle obs exists on the movement trajectory tj, the control unit 15 may detect an edge edg of the obstacle obs that is visible to a person ps heading in the direction of travel. The control unit 15 may calculate a normal nL of a first line segment sL that passes through the edge edg and connects the position of the person ps to the target point tp. The control unit 15 may calculate a position that is a predetermined distance away from the edge edg of the obstacle obs along the normal nL as a secondary target point stp. The predetermined distance is a typical distance from the obstacle obs when a person avoids the obstacle obs, and may be determined in advance based on statistics. The predetermined distance may also be variable depending on various other conditions.

[0060] In this specification, the edge edg of the obstacle obs is a single straight line, in other words, both ends of a line segment that continues in the same direction, or both ends of a curve with a continuous slope. Furthermore, the outline of the obstacle obs when viewed from above may be composed of a combination of multiple straight lines and multiple curves. Therefore, there may be multiple edges edg of the obstacle obs visible to the person ps heading in the direction of travel. The control unit 15 may calculate the secondary target point stp using one of the multiple edges edg. The control unit 15 may store the calculated secondary target point stp in the memory unit. Below, a method for calculating the secondary target point stp for multiple edges edg is described.

[0061] As shown in FIG. 6, the control unit 15 may classify the detected multiple edges edg as edges edg located clockwise or counterclockwise from the first line segment sL based on the position of the person ps. The control unit 15 may determine whether the multiple edges edg are classified on one side separated by the first line segment sL, in other words, on the clockwise side or counterclockwise side. When multiple edges edg are classified, in other words, when multiple edges edg are located on the one side, the control unit 15 may select one edge edg from the multiple edges edg as described below.

[0062] The control unit 15 may calculate multiple second line segments sL2 connecting the position of the person ps to each of the multiple edges edg. The control unit 15 may calculate the inclination angle of each of the multiple second line segments sL2 with respect to the first line segment sL1. The control unit 15 may temporarily select the edge edg with the largest inclination angle for calculating the secondary target point stp. When a single edge edg is located on one side, the control unit 15 may temporarily select that edge edg for calculating the secondary target point stp.

[0063] For example, when the first end edg1, the second end edg2, and the third end edg3 are located on the counterclockwise side, the first end edg1 with the largest inclination angle may be temporarily selected as the end edg on the counterclockwise side. Also, when only the fourth end edg4 is located on the clockwise side, the fourth end edg4 may be temporarily selected as the end edg on the clockwise side.

[0064] The control unit 15 may exclude from the temporary selection all edges located in a direction including an edge edg where the inclination angle of the second line segment sL2 with respect to the first line segment sL1 is 90 degrees or more, among both directions separated by the first line segment sL1. In other words, the control unit 15 may select an edge edg located in the direction opposite to the first line segment sL1. For example, as shown in FIG. 7, if the fifth edge edg5 and the sixth edge edg6 are located on the counterclockwise side and the inclination angle corresponding to the fifth edge edg5 exceeds 90 degrees, the fifth edge edg5 and the sixth edge edg6 located on the counterclockwise side may be excluded.

[0065] The control unit 15 may calculate the secondary target point using the end edg with the smaller inclination angle among the ends edg temporarily selected in each of the two directions separated by the first line segment sL1. In other words, the control unit 15 does not need to calculate a secondary target point for the end edg with the larger inclination angle. Specifically, as described above, the control unit 15 may calculate a normal nL of the first line segment sL that passes through the end edg with the smaller inclination angle. The control unit 15 may calculate a position a predetermined distance away from the end edg along the normal nL as the secondary target point stp.

[0066] The control unit 15 may consider the calculated secondary target point stp to be the position of the person ps and calculate a first line segment sL1 connecting the calculated secondary target point stp to the target point tp. The control unit 15 may determine whether or not an obstacle obs exists on the first line segment sL1. Thereafter, the control unit 15 may repeat the process of detecting the edge edg of the obstacle obs, selecting a single edge edg from the detected multiple obstacles obs, and calculating the secondary target point stp until no obstacle obs exists on the newly calculated first line segment sL1. Note that the presence or absence of an obstacle obs may be determined only within a detection range based on an image acquired by the control unit 15. Furthermore, the detection of the edge edg of the obstacle obs may be performed within a range from the latest calculated secondary target point stp in a direction from the position of the immediately previous person ps toward the latest calculated secondary target point stp. Note that the position of the immediately previous person ps is the position of the person ps when the first secondary target point stp is calculated, or the immediately previous secondary target point stp.

[0067] After the person sp passes through the calculated secondary target point stp, the control unit 15 may delete the passed secondary target point from the storage unit. After the person sp passes through the last calculated secondary target point stp, the control unit 15 may cancel the temporary suspension of prediction of the movement trajectory tj. Specifically, after the person sp arrives at the last calculated secondary target point stp, the control unit 15 may again predict the movement trajectory tj heading toward the target point tp stored in the storage unit.

[0068] Next, the prediction process executed by the control unit 15 in this embodiment will be described with reference to the flowchart of Fig. 8. The prediction process starts, for example, every time an image is acquired.

[0069] In step S100, the control unit 15 determines whether the prediction process is paused. If the prediction process is paused, the prediction process ends. If the prediction process is not paused, the process proceeds to step S101.

[0070] In step S101, the control unit 15 determines whether or not a partial image of the person ps is included in the newly acquired image. If not, the prediction process ends. If included, the process proceeds to step S102.

[0071] In step S102, the control unit 15 calculates the position of the person ps based on the acquired image. After the calculation, the process proceeds to step S103.

[0072] In step S103, the control unit 15 stores the positions of the people ps calculated in step S102 as information for each person ps. After storing, the process proceeds to step S104.

[0073] In step S104, the control unit 15 reads out from the storage unit the stored positions of the persons ps for each person ps included as a partial image in an image going back a predetermined number of frames. After reading, the process proceeds to step S105.

[0074] In step S105, the control unit 15 selects a person ps that matches the person ps in the newly acquired image from among the people ps read out in step S104. After the selection, the process proceeds to step S106.

[0075] In step S106, the control unit 15 calculates an approximate straight line for each person ps in the newly acquired image that matches the person in the past image in step S105, based on the position read out in step S104. After the calculation, the process proceeds to step S107.

[0076] In step S107, the control unit 15 calculates a judgment value based on the position calculated in step S102. After the calculation, the process proceeds to step S108.

[0077] In step S108, the control unit 15 determines whether the judgment value calculated in step S107 satisfies a predetermined condition. If the predetermined condition is not satisfied, the process proceeds to step S109. If the predetermined condition is satisfied, the process proceeds to step S111.

[0078] In step S109, the control unit 15 calculates the velocity corresponding to the newly acquired image. After the calculation, the process proceeds to step S110.

[0079] In step S110, the control unit 15 calculates the movement trajectory tj and the target point tp based on the position of the person ps calculated in step S102 and the speed calculated in step S109. After the calculation, the process proceeds to step S116.

[0080] In step S111, the control unit 15 calculates the acceleration of the person ps based on the position of the person ps calculated in step S102 and the position of the person ps read out in step S104. After the calculation, the process proceeds to step S112.

[0081] In step S112, the control unit 15 calculates the movement trajectory tj and the target point tp based on the acceleration calculated in step S111. After the calculation, the process proceeds to step S113.

[0082] In step S113, the control unit 15 calculates a second straight line L2 based on the position of the person ps calculated in step S102 and the acceleration calculated in step S111. After the calculation, the process proceeds to step S114.

[0083] In step S114, the control unit 15 determines whether or not a specific object so is located in the area between the movement trajectory tj calculated in step S112 and the second straight line L2 calculated in step S113. If a specific object so is located, the process proceeds to step S115. If a specific object so is not located, the process proceeds to step S116.

[0084] In step S115, the control unit 15 changes the target point tp to the position of the specific object so. Also, the control unit 15 corrects the movement trajectory tj so that the movement trajectory tj heads toward the position of the specific object so. After the correction, the process proceeds to step S116.

[0085] In step S116, the control unit 15 transmits the calculated target point tp and movement trajectory tj as information to the control device 13. After transmission, the prediction process ends.

[0086] Next, the detouring process executed by the control unit 15 in this embodiment will be described with reference to the flowchart of Fig. 9. The detouring process starts, for example, every time an image is acquired.

[0087] In step S200, the control unit 15 determines whether the secondary destination point stp calculated in the previous detour process is stored in the storage unit. If it is not stored, the process proceeds to step S202. If it is stored, the process proceeds to step S201.

[0088] In step S201, the control unit 15 determines, based on the most recently acquired image, whether or not there is a new edge edg of the obstacle obs that is the same as the edge edg that caused the calculation of the secondary target point stp that was confirmed to be stored in step S200. If there is no new edge edg, the process proceeds to step S202. If there is a new edge edg, the process proceeds to step S205.

[0089] In step S202, the control unit 15 determines whether or not an obstacle obs exists on the movement trajectory tj. If no obstacle obs exists, the detouring process ends. If an obstacle obs exists, the process proceeds to step S203.

[0090] In step S203, the control unit 15 stores the most recently calculated destination point as information in the storage unit. The control unit 15 also temporarily suspends the prediction process. After the temporary suspension, the process proceeds to step S204.

[0091] In step S204, the control unit 15 detects the edge edg of the obstacle obs whose presence has been confirmed in step S202. After detection, the process proceeds to step S205.

[0092] In step S205, the control unit 15 classifies the edge edg detected in step S204 into either a clockwise direction or a counterclockwise direction. After the classification, the process proceeds to step S206.

[0093] In step S206, the control unit 15 calculates a first straight line sL1 connecting the position of the person ps and the target point tp. The control unit 15 also calculates, for each edge edg, a second line segment sL2 connecting the position of the person ps and each edge edg. The control unit 15 also calculates the inclination angle of each second line segment sL2 with respect to the first straight line sL1. After the calculation, the process proceeds to step S207.

[0094] In step S207, the control unit 15 determines whether or not there is an inclination angle of 90 degrees or more among the inclination angles calculated in step S206 corresponding to the edge edg separated in one direction. If there is an inclination angle of 90 degrees or more in one direction, the process proceeds to step S208. If there is no inclination angle of 90 degrees or more, the process proceeds to step S209.

[0095] In step S208, the control unit 15 selects, from the clockwise direction and the counterclockwise direction, a direction other than the direction to which the edge edg corresponding to the tilt angle of 90 degrees or more belongs. Furthermore, the control unit 15 selects the edge edg corresponding to the largest tilt angle among the selected directions. After the selection, the process proceeds to step S211.

[0096] In step S209, the control unit 15 selects two edges edg corresponding to the maximum tilt angles in both directions, respectively. After the selection, the process proceeds to step S210.

[0097] In step S210, the control unit 15 selects the edge edg corresponding to the narrower tilt angle from the two edges edg selected in step S209. After the selection, the process proceeds to step S211.

[0098] In step S211, the control unit 15 calculates the secondary target point stp based on the selected single edge edg. The control unit 15 also stores the calculated secondary target point stp in the storage unit. After storing the secondary target point stp, the process proceeds to step S212.

[0099] In step S212, the control unit 15 determines whether or not an obstacle obs identical to the obstacle obs whose presence was confirmed in step S202 exists between the secondary target point stp calculated in the latest step S211 and the target point tp. If an obstacle obs exists, the process proceeds to step S204. Note that when returning to step S204, the control unit 15 regards the secondary target point stp as the secondary target point calculated in the latest step S211. If an obstacle obs does not exist, the detour process ends.

[0100] Next, the restart process executed by the control unit 15 in this embodiment will be described with reference to the flowchart of Fig. 10. The restart process is started, for example, every time an image is acquired.

[0101] In step S300, the control unit 15 determines whether the person ps has passed the secondary target point stp based on the most recently acquired image. If the person ps has not passed the secondary target point stp, the restart process ends. If the person ps has passed the secondary target point stp, the process proceeds to step S301.

[0102] In step S301, the control unit 15 erases from the storage unit the information about the secondary destination point stp, the passage of which has been confirmed in step S301. After erasure, the process proceeds to step S302.

[0103] In step S302, the control unit 15 determines whether the previous secondary destination stp stored in the storage unit has been deleted. If the previous secondary destination stp has not been deleted, the restart process ends. If the previous secondary destination stp has been deleted, the process proceeds to step S303.

[0104] In step S303, the control unit 15 releases the pause of the prediction process, and after the pause is released, the restart process ends.

[0105] The information processing device 10 of this embodiment configured as described above includes an acquisition unit 14 that acquires images, and a control unit 15 that calculates the position of a person ps included as a partial image in the images acquired by the acquisition unit 14, and predicts a movement trajectory tj and a target point tp of the person ps based on the time difference associated with each of multiple images including the person ps as a partial image and the position difference of the person ps calculated for each of the multiple images. With this configuration, the information processing device 10 predicts the target point by referring to the position of the person ps according to time, and therefore can improve the estimation accuracy of the target point tp with limited information.

[0106] Furthermore, the information processing device 10 calculates a first position and a second position of the person ps for each of the first image and the second image as a plurality of images, calculates a moving speed of the person ps based on the distance between the first position and the second position and the difference in time associated with each of the first image and the second image, and predicts a moving trajectory tj and a target point tp based on the first position, the second position, and the moving speed. With this configuration, the information processing device 10 can predict the target point tp with a minimum amount of information.

[0107] Furthermore, the information processing device 10 calculates an approximate line based on the position of the person ps calculated for each of three or more frames of images as a plurality of images, calculates the movement speed of the person based on the difference in time associated with any two of the plurality of images and the distance between the positions on the approximate line corresponding to the positions of the person ps calculated for each of the two images, and predicts the movement trajectory tj and the target point tp based on the approximate line and the movement speed. With this configuration, the information processing device 10 can reduce a decrease in the prediction accuracy of the movement trajectory tj due to momentary shaking of the person ps, and can further improve the estimation accuracy of the target point tp.

[0108] Furthermore, when a judgment value based on the position of the person ps calculated for each of three or more frames of images as a plurality of images satisfies a predetermined condition, the information processing device 10 calculates the acceleration of the person ps based on the position of the person ps calculated for each of the images and the times associated with each of the plurality of images, and predicts the movement trajectory tj and the target point tp based on the position, speed, and acceleration of the person ps calculated for the image with the most recent associated time among the plurality of images. With this configuration, the information processing device 10 can improve the estimation accuracy of the target point tp when the person ps changes direction.

[0109] Furthermore, in the information processing device 10, the judgment value is a first distance of the position of the person ps calculated for the image with the most recent associated time among the multiple images relative to an approximate line based on the position of the person ps calculated for each of the multiple images, or a first acceleration of the person ps based on the position of the person ps calculated for each of the multiple images and the times associated with each of the multiple images, and the predetermined condition includes that the first distance is equal to or greater than a distance threshold or that the first acceleration is equal to or greater than an acceleration threshold. With this configuration, the information processing device 10 can realize an estimation that the person ps will change direction.

[0110] Furthermore, when the information processing device 10 determines that a specific object is located between the movement trajectory tj predicted when the judgment value satisfies a predetermined condition and a line based on the difference between the time associated with each of the multiple images and the difference between the positions of the person ps calculated for each of the multiple images, it determines the position of the specific object so as the target point tp and corrects the movement trajectory tj in a direction toward the target point tp. With this configuration, the information processing device 10 can improve the estimation accuracy compared to a configuration in which the movement trajectory tj and the target point tp are predicted only from the position of the person ps according to time.

[0111] Furthermore, when the information processing device 10 determines that an obstacle obs is located between the position of the person ps and the target point tp, it calculates a secondary target point stp for avoiding the obstacle obs and corrects the movement trajectory tj so that it passes through the secondary target point stp. With this configuration, the information processing device 10 can improve the estimation accuracy of the movement trajectory tj when an obstacle obs is present.

[0112] Furthermore, the information processing device 10 calculates, as the secondary target point stp, a position that is a predetermined distance away from the edge edg of the obstacle obs in the normal direction of the first line segment sL1 that connects the position of the person ps based on the image and the target point tp. With this configuration, the information processing device 10 can calculate, as the secondary target point stp, a point that an actual person is expected to pass through when avoiding the obstacle obs when there is the obstacle obs. Therefore, the information processing device 10 can further improve the estimation accuracy of the movement trajectory tj for avoiding the obstacle obs.

[0113] Furthermore, when multiple edges edg of the obstacle obs are located on one side separated by the first line segment sL1, the information processing device 10 selects, from the multiple edges edg, the edge edg where the second line segment sL2 connecting the position of the person ps with the first line segment sL1 has the largest inclination angle, in order to calculate the secondary target point stp. With this configuration, the information processing device 10 can calculate the secondary target point stp for each of the multiple edges edg in one direction, and can calculate only the secondary target point stp that is most likely to be passed through, without determining whether or not to pass through. Therefore, the information processing device 10 can reduce the processing load.

[0114] Furthermore, the information processing device 10 excludes, from selection for calculating the secondary target point stp, all edges edg located in a direction including an edge edg where the second line segment sL2 has an inclination angle of 90 degrees or more with respect to the first line segment sL1, among both directions separated by the first line segment sL1. With this configuration, the information processing device 10 excludes from prediction movement of the person ps in a direction returning from the original traveling direction, which is unlikely to be passed through, and therefore can further improve the estimation accuracy of the movement trajectory tj for avoiding the obstacle obs.

[0115] Furthermore, the information processing device 10 calculates the secondary target point stp using the end edg with the smaller inclination angle out of the two ends edg selected in each of the two directions separated by the first line segment sL1. The end edg with the smaller inclination angle is generally the end in the direction that is likely to result in the shortest avoidance distance. Based on such a general assumption, the information processing device 10 having the above-described configuration can further improve the estimation accuracy of the movement trajectory tj for avoiding the obstacle obs.

[0116] Furthermore, the information processing device 10 again predicts the movement trajectory tj of the person ps toward the target point tp after the person ps passes through the secondary target point stp. With this configuration, the information processing device 10 predicts the movement trajectory tj by excluding the position of the person ps according to the passage of time while avoiding the obstacle obs, and therefore, it is possible to reduce a decrease in the estimation accuracy of the target point tp.

[0117] In one embodiment, (1) an information processing device includes: an acquisition unit that acquires an image; The system is equipped with a control unit that calculates the position of an animal included as a partial image in an image acquired by the acquisition unit, and predicts the movement trajectory and target point of the animal based on the difference in time associated with each of multiple images that include the animal as a partial image and the difference in the position of the animal calculated for each of the multiple images.

[0118] (2) In the information processing device of (1) above, The control unit calculating a first position and a second position of the animal for each of a first image and a second image as the plurality of images; calculating a moving speed of the animal based on the distance between the first position and the second position and the difference in time associated with the first image and the second image; The movement trajectory and the target point are predicted based on the first position, the second position, and the movement speed.

[0119] (3) In the information processing device of (1) above, The control unit calculating an approximate straight line based on the position of the animal calculated for each of three or more frames of images as the plurality of images; calculating a moving speed of the animal based on the difference between the times associated with any two of the plurality of images and the distance between the positions on the approximation line corresponding to the positions of the animal calculated for each of the two images; The movement trajectory and the target point are predicted based on the approximate line and the movement speed.

[0120] (4) In any of the information processing devices (1) to (3), The control unit If a judgment value based on the position of the animal calculated for each of three or more frames of the plurality of images satisfies a predetermined condition, calculating an acceleration of the animal based on the position of the animal calculated for each of the images and the time associated with each of the plurality of images; The movement trajectory and the target point are predicted based on the position and velocity of the animal and the acceleration calculated for the most recently associated image among the plurality of images.

[0121] (5) In the information processing device of (4) above, the determination value is a first distance of the position of the animal calculated for the image having the latest associated time among the plurality of images, relative to an approximation line based on the position of the animal calculated for each of the plurality of images, or a first acceleration of the animal based on the position of the animal calculated for each of the plurality of images and the time associated with each of the plurality of images; The predetermined condition includes the first distance being equal to or greater than a distance threshold, or the first acceleration being equal to or greater than an acceleration threshold.

[0122] (6) In the information processing device of (4) or (5) above, When the control unit determines that a specific object is located between the movement trajectory predicted when the judgment value satisfies a predetermined condition and a line based on the difference in time associated with each of the multiple images and the difference in the position of the animal calculated for each of the multiple images, it determines the position of the specific object as a target point and corrects the movement trajectory in a direction toward the target point.

[0123] (7) In any of the information processing devices described in (1) to (6), When the control unit determines that an obstacle is located between the animal's position and the target point, it calculates a secondary target point to avoid the obstacle and corrects the movement trajectory so that it passes through the secondary target point.

[0124] (8) In the information processing device of (7) above, The control unit calculates, as the secondary target point, a position that is a predetermined distance away from the edge of the obstacle in a normal direction of a first line segment that connects the position of the animal based on the image and the target point.

[0125] (9) In the information processing device of (8), When multiple ends of the obstacle are located on one side separated by the first line segment, the control unit selects the end among the multiple ends where the second line segment connecting to the animal's position has the largest inclination angle relative to the first line segment for calculating the secondary target point.

[0126] (10) In the information processing device of (9), The control unit excludes all ends located in directions separated by the first line segment, including ends at which the second line segment has an inclination angle of 90 degrees or more relative to the first line segment, from selection for calculating the secondary target point.

[0127] (11) In the information processing device of (9) or (10), The control unit calculates the secondary target point using the end with the smaller inclination angle out of the two ends selected in each of the two directions separated by the first line segment.

[0128] (12) In any of the information processing devices described in (7) to (11), After the animal passes the sub-goal point, the control unit again predicts the movement trajectory toward the goal point.

[0129] The above has described an embodiment of the information processing device 10, but the embodiment of the present disclosure can also be implemented as a method or program for implementing the device, or as a storage medium on which a program is recorded (for example, an optical disk, a magneto-optical disk, a CD-ROM, a CD-R, a CD-RW, a magnetic tape, a hard disk, or a memory card, etc.).

[0130] Furthermore, the implementation form of the program is not limited to application programs such as object code compiled by a compiler or program code executed by an interpreter, but may also be in the form of a program module incorporated into an operating system. Furthermore, the program may or may not be configured so that all processing is performed solely by the CPU on the control board. The program may also be configured so that part or all of it is executed by another processing unit mounted on an expansion board or expansion unit added to the board as needed.

[0131] The drawings illustrating the embodiments of the present disclosure are schematic, and the dimensional ratios and the like in the drawings do not necessarily correspond to the actual ones.

[0132] Although the embodiments of the present disclosure have been described based on the drawings and examples, it should be noted that those skilled in the art could make various modifications or alterations based on the present disclosure. Therefore, it should be noted that these modifications or alterations are included in the scope of the present disclosure. For example, the functions included in each component can be rearranged so as not to be logically inconsistent, and multiple components can be combined or divided into one.

[0133] For example, the information processing device 10 of this embodiment is mounted on the moving object 11, but may be embodied as, for example, a server device that communicates with the moving object 11. The information processing device embodied as a server device may acquire images from the moving object 11 and roadside devices around the moving object 11, and may provide the moving object 11 with a predicted movement trajectory tj and a target point tp as information.

[0134] All of the features described in this disclosure and / or all steps of all disclosed methods or processes may be combined in any combination except combinations in which these features are mutually exclusive. Furthermore, each feature described in this disclosure may be replaced by an alternative feature serving the same, equivalent, or similar purpose, unless expressly denied. Thus, unless expressly denied, each disclosed feature is only one example of a generic series of identical or equivalent features.

[0135] Furthermore, embodiments of the present disclosure are not limited to the specific configurations of any of the above-described embodiments, but rather extend to any novel feature or combination thereof described herein, or any novel method or process step or combination thereof described herein.

[0136] In this disclosure, descriptions such as "first" and "second" are identifiers for distinguishing the configuration. In this disclosure, the configurations distinguished by descriptions such as "first" and "second" can have their numbers exchanged. For example, the first line segment can exchange the identifiers "first" and "second" with the second line segment. The exchange of identifiers is performed simultaneously. The configurations remain distinguished even after the identifier exchange. Identifiers may be deleted. A configuration from which an identifier has been deleted is distinguished by a symbol. The descriptions of identifiers such as "first" and "second" in this disclosure should not be used solely to interpret the order of the configurations or to justify the existence of an identifier with a smaller number. [Explanation of symbols]

[0137] 10. Information processing equipment 11 Mobile 12 Camera 13 Control device 14 Acquisition Department 15 Control Unit aL Approximate straight line edg edge L2 Second line nL Normal to the first line segment obs obstacles ps person p1 first position sL1 First line segment sL2 Second line segment so specific object stp sub-target point tj moving trajectory tp target point

Claims

1. an acquisition unit that acquires an image; a control unit that calculates the position of an animal included as a partial image in an image acquired by the acquisition unit, and predicts a movement trajectory and a target point of the animal based on the difference in time associated with each of a plurality of images including the animal as a partial image and the difference in the position of the animal calculated for each of the plurality of images. Information processing device.

2. 2. The information processing device according to claim 1, The control unit calculating a first position and a second position of the animal for each of a first image and a second image as the plurality of images; calculating a moving speed of the animal based on a distance between the first position and the second position and a difference in time associated with the first image and the second image; The movement trajectory and the target point are predicted based on the first position, the second position, and the movement speed. Information processing device.

3. 2. The information processing device according to claim 1, The control unit calculating an approximate straight line based on the position of the animal calculated for each of three or more frames of images as the plurality of images; calculating a moving speed of the animal based on the difference between the times associated with any two of the plurality of images and the distance between the positions on the approximation line corresponding to the positions of the animal calculated for each of the two images; The movement trajectory and the destination point are predicted based on the approximate line and the movement speed. Information processing device.

4. 4. The information processing device according to claim 1, The control unit If a judgment value based on the position of the animal calculated for each of three or more frames of the plurality of images satisfies a predetermined condition, calculating an acceleration of the animal based on the position of the animal calculated for each of the images and a time associated with each of the plurality of images; The movement trajectory and the target point are predicted based on the position and velocity of the animal and the acceleration calculated for the image associated with the most recent time among the plurality of images. Information processing device.

5. 5. The information processing device according to claim 4, the determination value is a first distance of the position of the animal calculated for the image having the latest associated time among the plurality of images to an approximation line based on the position of the animal calculated for each of the plurality of images, or a first acceleration of the animal based on the position of the animal calculated for each of the plurality of images and the time associated with each of the plurality of images; The predetermined condition includes the first distance being equal to or greater than a distance threshold, or the first acceleration being equal to or greater than an acceleration threshold. Information processing device.

6. 5. The information processing device according to claim 4, When the control unit determines that a specific object is located between the predicted movement trajectory when the judgment value satisfies a predetermined condition and a line based on the difference in time associated with each of the plurality of images and the difference in the position of the animal calculated for each of the plurality of images, the control unit determines the position of the specific object as a target point and corrects the movement trajectory in a direction toward the target point. Information processing device.

7. 4. The information processing device according to claim 1, When the control unit determines that an obstacle is located between the position of the animal and the target point, the control unit calculates a secondary target point for avoiding the obstacle and corrects the movement trajectory so that the movement trajectory passes through the secondary target point. Information processing device.

8. 8. The information processing device according to claim 7, The control unit calculates, as the secondary target point, a position that is a predetermined distance away from an edge of the obstacle and in a normal direction of a first line segment that connects the position of the animal based on the image and the target point. Information processing device.

9. 9. The information processing device according to claim 8, When a plurality of ends of the obstacle are located on one side separated by the first line segment, the control unit selects, among the plurality of ends, an end at which a second line segment connecting the obstacle to the position of the animal has a maximum inclination angle with respect to the first line segment, for calculating the secondary target point. Information processing device.

10. 10. The information processing device according to claim 9, The control unit excludes, from selection for calculation of the secondary target point, all ends located in a direction including an end of the second line segment at an inclination angle of 90 degrees or more with respect to the first line segment, among both directions separated by the first line segment. Information processing device.

11. 10. The information processing device according to claim 9, The control unit calculates the secondary target point using the end with the smaller inclination angle out of the two ends selected in each of the two directions separated by the first line segment. Information processing device.

12. 8. The information processing device according to claim 7, The control unit predicts again a movement trajectory of the animal toward the target point after the animal passes the sub-target point. Information processing device.

Images