Imaging apparatus and control method for the same

Abstract

To provide a technique for estimating an object's fall region on the basis of the movements of persons in an image and for performing imaging on the basis of the fall region.SOLUTION: An imaging apparatus is configured to estimate the motion information of each person on the basis of a captured video, determine the shooting area on the basis of the estimated motion information of each person. Then, the imaging apparatus is configured to identify the motion information of each person on the basis of the video shot within that shooting area and estimate the object's fall area on the basis of the identified motion information and control the apparatus to perform shooting on the basis of that fall area.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to imaging techniques. [Background technology]

[0002] In recent years, with the advancement of automation and labor-saving in filming in sports video production, many technologies have been proposed to solve the problems of automatic filming of sports. For example, the technology disclosed in Patent Document 1 controls at least one of the exposure adjustment and focus adjustment of the camera based on the position information of the person or object to be filmed. In this way, by automatically focusing on the player to be filmed, the cameraman can save the trouble of searching for the player he wants to film. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent No. 7233886 Summary of the Invention [Problem to be solved by the invention]

[0004] When filming sports such as ball games in which flying objects are involved, it is necessary to change the camera's angle of view so as to film the play occurring at the point where the object lands, rather than the flying object, and to do so, it is necessary to estimate the area where the object will land. However, in conventional technology, the camera is controlled based on the position information of the object or person, so it is difficult to estimate the area where the ball will land if the ball is not within the angle of view being filmed. This disclosure provides a technology for estimating the area where the object will land based on the movement of a person in the video and filming based on the area where the object will land. [Means for solving the problem]

[0005] One aspect of the present disclosure is characterized by comprising an estimation means for estimating movement information of each person based on captured video, a determination means for determining a shooting area based on the movement information of each person estimated by the estimation means, and a control means for identifying movement information of each person based on video captured of the shooting area, estimating a falling area of ​​an object based on the identified movement information, and controlling to perform shooting based on the falling area. [Effects of the Invention]

[0006] According to the present disclosure, it is possible to estimate the area where an object will fall based on the movement of a person in a video, and to perform shooting based on the area where the object will fall. [Brief explanation of the drawings]

[0007] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an imaging system. [Figure 2] FIG. 2 is a block diagram showing an example of the hardware configuration of each of a camera 101 and a camera 102. [Figure 3] FIG. 2 is a block diagram showing an example of the functional configuration of a camera 101 and a camera 102. [Figure 4] 10 is a flowchart of the operation of the camera 101. [Figure 5] FIG. 10 is a diagram showing a specific example of the process in step S404. [Figure 6] FIG. 10A is a diagram showing an example of vector components, and FIG. 10B is a diagram showing an example of region information. [Figure 7] 4 is a flowchart of the operation of the camera 102. [Figure 8] FIG. 10 is a diagram showing a specific example of the process in step S703. [Figure 9] FIG. 10 is a diagram showing a specific example of the process in step S704. [Figure 10] FIG. 10 is a diagram showing a specific example of the process in step S705. DETAILED DESCRIPTION OF THE INVENTION

[0008] Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. Note that the following embodiments do not limit the scope of the invention claimed. Although multiple features are described in the embodiments, not all of these multiple features are necessarily essential to the invention, and multiple features may be combined arbitrarily. Furthermore, in the accompanying drawings, the same reference numerals are used to designate the same or similar components, and redundant explanations will be omitted.

[0009] [First embodiment] In this embodiment, the operation of the imaging system when imaging a baseball game will be described. However, the scene to be imaged by the imaging system is not limited to a baseball game, and may be any scene of a sport in which an object such as a ball is flying and people such as players move in accordance with the object's fall.

[0010] First, an example of the configuration of an imaging system according to this embodiment will be described with reference to Fig. 1. As shown in Fig. 1, the imaging system includes a camera 101, a camera 102, and an input device 103, and each of the cameras 101, 102, and the input device 103 is connected to a network 104 such as a LAN or the Internet.

[0011] A baseball game is being played on a field 105 between a pitcher 106, a catcher 107, and a batter 108, and cameras 101 and 102 are installed in positions that allow them to capture the baseball game scene.

[0012] Camera 101 captures the sequence from when pitcher 106 throws the ball to when batter 108 hits it. Camera 101 then determines a capture area, which is the range (area) that camera 102 will capture, based on the orientation of the faces of multiple people, such as pitcher 106, catcher 107, and batter 108, who are gazing at the ball (hit ball) hit by batter 108. Camera 101 then generates area information that defines the capture area and transmits the area information to camera 102 via network 104.

[0013] Here, a global coordinate system is set in advance for the field 105, and the area information is information for defining the shooting area in the global coordinate system. The global coordinate system is, for example, a coordinate system with a point on the field 105 as its origin and three axes that are orthogonal to each other at the origin as the x-axis, y-axis, and z-axis. Here, the direction perpendicular to the field 105 is defined as the z-axis.

[0014] Camera 102 captures an image of the image capture area defined by the area information received from camera 101. Camera 102 then estimates the area where the ball will fall (drop area) based on the direction of movement of each person included in the video after the ball has been hit back, and controls pan, tilt, and zoom so as to capture an image of the surrounding area including the drop area.

[0015] The input device 103 is a computer device such as a PC, a tablet terminal device, a smartphone, etc. The input device 103 transmits various types of information to the camera 101 or 102 in response to a user operation, and controls the operation of the camera 101 or 102 in response to the user operation.

[0016] For example, before the cameras 101 and 102 start capturing images, the input device 103 displays a map with an overhead view of the field 105 on a monitor. Then, the input device 103 converts a position on the map designated by a user operation as the position of the camera 101 into a position in a global coordinate system, and transmits the converted position to the camera 101. The user operation is realized by the user operating a user interface such as a keyboard, a mouse, or a touch panel.

[0017] Next, an example of the hardware configuration of each of the cameras 101 and 102 will be described using the block diagram in Fig. 2. First, an example of the hardware configuration of the camera 101 will be described. The CPU 201 executes various processes using computer programs and data stored in the RAM 203. In this way, the CPU 201 controls the overall operation of the camera 101, and also executes or controls various processes that will be described as processes performed by the camera 101.

[0018] The ROM 202 stores setting data for the camera 101, computer programs and data related to the startup of the camera 101, and computer programs and data related to the basic operations of the camera 101. The ROM 202 also stores computer programs and data for causing the CPU 201 to execute or control various processes described as processes performed by the camera 101.

[0019] The RAM 203 has an area for storing computer programs and data loaded from the ROM 202, and an area for storing video captured by the image capturing unit 290. The RAM 203 also has an area for storing information received from the input device 103 or the camera 102 via the communication I / F 204, and a work area used by the CPU 201 when executing various processes. In this way, the RAM 203 can provide various areas as needed.

[0020] The communication I / F 204 functions as an interface for performing data communication with the camera 102 and the input device 103 via the network 104. The image capturing unit 290 captures video. The CPU 201, ROM 202, RAM 203, communication I / F 204, and image capturing unit 290 are all connected to a system bus 205.

[0021] Next, we will explain an example of the hardware configuration of the camera 102. The CPU 206 executes various processes using computer programs and data stored in the RAM 208. As a result, the CPU 206 controls the overall operation of the camera 102, and also executes or controls various processes that will be explained as processes performed by the camera 102.

[0022] The ROM 207 stores setting data for the camera 102, computer programs and data related to the startup of the camera 102, and computer programs and data related to the basic operations of the camera 102. The ROM 207 also stores computer programs and data for causing the CPU 206 to execute or control various processes described as processes performed by the camera 102.

[0023] The RAM 208 has an area for storing computer programs and data loaded from the ROM 207, and an area for storing video captured by the image capturing unit 291. The RAM 208 also has an area for storing information received from the input device 103 or the camera 101 via the communication I / F 210, and a work area used when the CPU 206 executes various processes. In this way, the RAM 208 can provide various areas as needed.

[0024] The motor 209 controls one or more of pan, tilt, and zoom of the camera 102 under the control of the CPU 206, thereby controlling the angle of view of the camera 102. The communication I / F 210 functions as an interface for performing data communication with the camera 101 and the input device 103 via the network 104. The image capturing unit 291 captures video. The CPU 206, ROM 207, RAM 208, motor 209, communication I / F 210, and image capturing unit 291 are all connected to a system bus 211. Note that the hardware configuration of the camera 101 and camera 102 shown in FIG. 2 is an example, and can be modified or changed as appropriate.

[0025] An example of the functional configuration of camera 101 and camera 102 is shown in the block diagram of FIG. 3. In this embodiment, a case will be described in which each functional unit shown in FIG. 3 is implemented by software (computer program). In this embodiment, the functional units shown in FIG. 3 will be described as the subject of processing. However, in reality, the functions of these functional units are realized by CPU 201 executing computer programs corresponding to storage unit 301, acquisition unit 302, acquisition unit 303, estimation unit 304, calculation unit 305, and transmission unit 306. Similarly, the functions of these functional units are realized by CPU 206 executing computer programs corresponding to reception unit 307, acquisition unit 308, acquisition unit 309, estimation unit 310, and angle-of-view control unit 311. Note that one or more of the functional units shown in FIG. 3 may be implemented by hardware.

[0026] The operation of the camera 101 will be described with reference to the flowchart in Fig. 4. In step S401, the storage unit 301 receives the "position of the camera 101 in the global coordinate system" transmitted from the input device 103 via the network 104, and stores the received "position of the camera 101 in the global coordinate system" in the RAM 203. After step S401, the shooting unit 290 shoots scenes of the baseball game, and the acquisition unit 302 acquires the video (moving images) shot by the shooting unit 290.

[0027] In step S402, the acquisition unit 303 analyzes the video acquired by the acquisition unit 302 to determine whether or not the batter 108 has hit the ball. Various methods can be applied to make this determination.

[0028] For example, the acquisition unit 303 may use a learning model that has learned the motion of a batter hitting a ball to determine whether the batter 108 in the video has hit the ball. Alternatively, the acquisition unit 303 may recognize surrounding sounds collected by a sound collection device such as a microphone to determine whether the batter 108 has hit the ball.

[0029] If it is determined that the batter 108 has hit the ball, the process proceeds to step S403; if it is determined that the batter 108 has not hit the ball, the process proceeds to step S402.

[0030] In step S403, the acquisition unit 303 calculates vector components that indicate the facial orientations (the orientations of the faces facing the ball) of people such as the pitcher 106, catcher 107, batter 108, spectators, and umpire included in the video (video after the batter 108 hits the ball) acquired by the acquisition unit 302. Here, the "video after the batter 108 hits the ball" refers to, for example, a group of frames of video for a certain period of time starting from the frame in which it is detected that the batter 108 has hit the ball.

[0031] The method for calculating the vector components indicating the orientation of a person's face in the video is not limited to a specific method. For example, the acquisition unit 303 may calculate the vector components indicating the orientation of the face using a known technique such as a method using feature points of the person's face in the video and Euler angles. The acquisition unit 303 calculates the vector components in a local coordinate system based on the video.

[0032] A local coordinate system based on an image is a coordinate system in which, for example, one point in the image is the origin and three axes that intersect at right angles at the origin are the x-axis, y-axis, and z-axis. For example, the horizontal direction in the image is the x-axis (the left side in the image is the positive direction), the direction perpendicular to the image is the y-axis (the depth direction in the image is the positive direction), and the vertical direction in the image is the z-axis (the upper side in the image is the positive direction).

[0033] In step S404, the estimation unit 304 performs three-dimensional measurement based on the "vector components in the local coordinate system" that indicate the direction of each person's face calculated in step S403, and determines the area in the field 105 to be photographed by the camera 102 (photography area).

[0034] The method for determining the shooting area by performing 3D measurement based on the "vector components in the local coordinate system" indicating the facial orientation of each person calculated in step S403 is not limited to a specific method. For example, the estimation unit 304 converts the vector components in the local coordinate system into vector components in the global coordinate system based on the above-mentioned "position of the camera 101 in the global coordinate system." FIG. 6(a) shows the vector components (xa, ya, za) in the global coordinate system obtained by converting the "vector components in the local coordinate system" indicating the facial orientation of the pitcher 106. The estimation unit 304 then determines the position of the intersection of the vectors (line segments) having the vector components converted into the global coordinate system as the position of the ball in the global coordinate system, and determines the direction from the previously determined position of the ball to the currently determined position of the ball as the direction of the ball. When the field 105 is divided into a plurality of defensive areas (for example, the left field area, right field area, center field area, and infield area of ​​the outfield), the estimation unit 304 identifies which of the plurality of defensive areas the ball is heading towards, and determines the identified defensive area as the shooting area.

[0035] Then, in step S405, the calculation unit 305 generates, as area information, information that defines the shooting area determined in step S404 in the global coordinate system. For example, the calculation unit 305 converts the two-dimensional position of the defensive area determined as the shooting area, among the two-dimensional positions of each defensive area on the field 105, into a three-dimensional position in the global coordinate system based on the "position of the camera 101 in the global coordinate system." The "two-dimensional position of the defensive area on the field 105" is, for example, the two-dimensional coordinates of each vertex that defines the defensive area. In this case, the calculation unit 305 converts the two-dimensional coordinates of each vertex of the defensive area identified as the shooting area into a three-dimensional position in the global coordinate system based on the "position of the camera 101 in the global coordinate system." This allows the calculation unit 305 to generate, as area information, information that indicates the three-dimensional position of each vertex of the shooting area in the global coordinate system.

[0036] FIG. 6(b) shows a case where (x1, y2, 0) (x2, y2, 0) (x2, y1, 0) (x1, y1, 0) are obtained as the three-dimensional positions in the global coordinate system of each vertex of the rectangular shooting area.

[0037] Camera 101 may store in advance the three-dimensional positions of each defensive area (the three-dimensional positions of each vertex of the defensive area in the global coordinate system). In this case, calculation unit 305 may identify, from the three-dimensional positions stored in advance, the three-dimensional position of the defensive area that corresponds to the shooting area determined in step S404, and output the identified three-dimensional position as area information. Then, in step S406, transmission unit 306 transmits the area information generated in step S405 to camera 102 via network 104.

[0038] The processing of step S404 above will be described using a specific example shown in Fig. 5. Fig. 5 shows one frame of a video captured by camera 101 after batter 108 hits a ball pitched by pitcher 106.

[0039] 5(a), the arrows indicate vectors that indicate the facial orientations of pitcher 106 and batter 108 estimated in step S403. In the case of such facial orientations, the left field area is determined as the photographing area in step S404.

[0040] In Figure 5(b), arrow 106a indicates a vector indicating the direction of the face of pitcher 106, and arrow 108a indicates a vector indicating the direction of the face of batter 108. In the case of Figure 5(b), the face of pitcher 106 faces in a direction different from the faces of batter 108 and catcher 107. When only one person faces in a different direction like this, the photographing area is determined using the face direction of batter 108 and the face direction of catcher 107.

[0041] Next, the operation of camera 102 will be described with reference to the flowchart in Fig. 7. When the process according to the flowchart in Fig. 7 starts, shooting unit 291 shoots scenes of a baseball game, and acquisition unit 308 acquires the video (moving images) shot by shooting unit 291.

[0042] In step S701, the receiving unit 307 receives the area information transmitted from the camera 101 via the network 104. Then, the angle-of-view control unit 311 controls the motor 209 to control one or more of the pan, tilt, and zoom of the camera 102 so that the shooting area defined by the area information is appropriately within the angle of view of the camera 102.

[0043] In step S702, the acquisition unit 309 detects players from the video acquired by the acquisition unit 308 (video captured after the angle of view was controlled in step S701, i.e., video of the shooting area), and estimates whether the detected players are moving and their direction of movement. The method for detecting players from the video and the method for estimating whether the detected players are moving and their direction of movement are not limited to a specific method.

[0044] In step S703, the estimation unit 310 estimates the landing area of ​​the batted ball based on the movement direction of the player estimated in step S702. For example, for each movement direction of the player estimated in step S702, the estimation unit 310 obtains a line segment extending from the position of the player in the movement direction, and estimates the position of the intersection of the obtained line segment as the position of the batted ball. The estimation unit 310 then estimates the area including the estimated intersection (e.g., an area centered on the estimated intersection) as the landing area of ​​the batted ball. Note that if only one player is estimated to be stationary in step S702, the estimation unit 310 may estimate the area including the position of that player (e.g., an area centered on the position of that player) as the landing area of ​​the batted ball. The size of the landing area may be determined in advance, or may be changed depending on the position of the intersection or the position of one player.

[0045] The processing of step S703 will be described using a specific example shown in Fig. 8. As shown in Fig. 8(a), when movement direction 801a is estimated as the movement direction of player 801 and movement direction 802a is estimated as the movement direction of player 802, area 803 centered on the position of the intersection of lines extending from the positions of the respective players in the movement directions of the respective players is estimated as the landing area of ​​the batted ball.

[0046] 8(b), if a player 804 is already at the point where the ball will land and is about to catch the ball, the player 804 will have stood still for a certain period of time, and therefore the player 804 will be estimated to be stationary. In such a case, an area 806 including the position of the player 804 (for example, an area centered on the position of the player 804) may be estimated as the area where the ball will land.

[0047] In step S704, the angle of view control unit 311 controls one or more of the pan and tilt of the camera 102 so that the drop area estimated in step S703 falls within the angle of view of the camera 102 (for example, so that the center of the drop area is the center of the angle of view of the camera 102).

[0048] The processing of step S704 will be described with reference to a specific example shown in Fig. 9. When area 803 in Fig. 8(a) is estimated as the drop area, the angle-of-view control unit 311 controls the pan and tilt of the camera 102 so that the current angle of view 901 of the camera 102 becomes angle of view 902 in which the area 803 is at the center of the angle of view of the camera 102, as shown in Fig. 9(a).

[0049] If the area 806 in Figure 8(b) is estimated as the drop area, the angle of view control unit 311 controls the pan and tilt of the camera 102 so that the current angle of view 903 of the camera 102 becomes angle of view 904, in which the area 806 is at the center of the angle of view of the camera 102, as shown in Figure 9(b).

[0050] In step S705, the angle of view control unit 311 controls the zoom of the camera 102 so that the falling area estimated in step S703 and the players included in the video after the angle of view control in step S704 are within the angle of view of the camera 102 (changing the zoom magnification around the falling area).

[0051] The processing of step S705 will be described with reference to a specific example shown in Fig. 10. After controlling the pan and tilt to obtain the angle of view 902 shown in Fig. 9(a), the zoom of the camera 102 is controlled so that the two players and area 803 within the angle of view 902 are included as much as possible within the angle of view of the camera 102, as shown in Fig. 10(a). As a result, as the two players approach the landing area, the camera 102 increases the zoom magnification so that the two players fit within the angle of view, with area 803 at the center, and finally obtains an angle of view 1001.

[0052] 9(b), the zoom of the camera 102 is controlled so that the area 806 fits as large as possible within the angle of view of the camera 102, as shown in FIG. 10(b). As a result, the zoom magnification of the camera 102 is increased around the area 806, and the angle of view finally becomes 1002.

[0053] In this way, according to this embodiment, it is possible to capture video at the desired timing when filming a scene in which a player catches the ball, and this can contribute to automating a filming system that films desired scenes.

[0054] [Second embodiment] In the first embodiment, the angle of view is controlled by controlling pan, tilt, and zoom. However, the method for controlling the angle of view is not limited to a specific method, and for example, the angle of view may be controlled by using electronic zoom on an overhead view image.

[0055] For example, steps S401 to S405 may be executed, and the area information thus obtained may be used to execute the processing of steps S701 to S703, after which an area in the video image may be identified such that the falling area is at the center of the angle of view, and a photographing device may be used that digitally zooms into that area.

[0056] [Third embodiment] In the first embodiment, the direction of the face and the direction of movement were used as examples of a person's movement information, but this is not limited to this. For example, whether the foot / hand that is put forward is the right foot / hand or the left foot / hand, the direction in which the person jumped, etc. can also be used as a person's movement information.

[0057] [Fourth embodiment] In the above embodiment, the process for generating area information (processing according to the flowchart in Figure 4) was described as being performed by the camera 101, but this is not limited to this, and it may also be performed, for example, by a controller that controls the operation of the camera 101.

[0058] Furthermore, in the above embodiment, the processing for estimating the drop area (processing in steps S702 and S703) was described as being performed by the camera 102, but this is not limited to this, and it may also be performed, for example, by a controller that controls the operation of the camera 102.

[0059] The numerical values, processing timing, processing order, processing subject, data (information) configuration / acquisition method / sending destination / sending source / storage location, etc. used in the above embodiment are given as examples to provide a concrete explanation, and are not intended to be limited to these examples.

[0060] In addition, some or all of the above-described embodiments may be used in appropriate combination, and some or all of the above-described embodiments may be selectively used.

[0061] (Other embodiments) The present disclosure can also be realized by providing a program that realizes one or more functions of the above-described embodiments to a system or device via a network or a storage medium, and having one or more processors in the computer of the system or device read and execute the program. It can also be realized by a circuit (e.g., ASIC) that realizes one or more functions.

[0062] The disclosure of this specification includes the following imaging device and imaging device control method. (Item 1) an estimation means for estimating motion information of each person based on the captured video; a determination means for determining a photographing area based on the motion information of each person estimated by the estimation means; a control means for specifying motion information of each person based on the video of the shooting area, estimating a falling area of ​​the object based on the specified motion information, and controlling to perform shooting based on the falling area; An imaging device comprising: (Item 2) 2. The photographing device according to item 1, wherein the estimation means estimates the facial orientation of each person based on the photographed video. (Item 3) 3. The photographing device according to item 2, wherein the estimation means estimates the direction of each person's face based on video footage taken over a certain period of time after the ball is hit. (Item 4) 4. The photographing device according to item 2 or 3, wherein the determining means determines the photographing area based on the face direction of each person estimated by the estimating means. (Item 5) 5. The photographing device according to item 4, wherein the determining means performs three-dimensional measurement based on vector components indicating the face direction of each person estimated by the estimating means, and determines an area in the direction of the object as the photographing area. (Item 6) The control means estimates the movement direction of each person based on the image captured in the shooting area, and estimates the falling area of ​​the object based on the estimated movement direction. (Item 7) 6. The photographing device according to any one of items 1 to 5, wherein the control means, when there is only one person not moving, estimates the area where the object will fall based on the position of the person. (Item 8) 8. The photographing device according to any one of items 1 to 7, wherein the control means controls one or more of panning, tilting, and zooming to perform photographing based on the drop area. (Item 9) 8. The photographing device according to any one of items 1 to 7, wherein the control means performs digital zoom so as to photograph based on the drop area. (Item 10) The imaging device includes a first imaging device and a second imaging device, the first image capturing device is provided with the estimation means and the determination means, The second imaging device is equipped with the control means. 10. The photographing device according to any one of items 1 to 9, (Item 11) A method for controlling an imaging device, comprising: an estimation step in which the estimation means of the image capturing device estimates motion information of each person based on the captured video; a determination step in which a determination means of the photographing device determines a photographing area based on the motion information of each person estimated in the estimation step; a control step in which a control means of the photographing device specifies motion information of each person based on a video of the photographing area, estimates a falling area of ​​an object based on the specified motion information, and controls the photographing device to perform photographing based on the falling area; 11. A control method for an imaging device, comprising:

[0063] The invention is not limited to the above-described embodiments, and various changes and modifications can be made without departing from the spirit and scope of the invention. Accordingly, the following claims are appended to apprise the public of the scope of the invention. [Explanation of symbols]

[0064] 101: Camera 102: Camera 103: Input device 104: Network 301: Storage unit 302: Acquisition unit 303: Acquisition unit 304: Estimation unit 305: Calculation unit 306: Transmission unit 307: Reception unit 308: Acquisition unit 309: Acquisition unit 310: Estimation unit 311: View angle control unit

Claims

1. an estimation means for estimating motion information of each person based on the captured video; a determination means for determining a photographing area based on the motion information of each person estimated by the estimation means; a control means for specifying motion information of each person based on the video of the shooting area, estimating a falling area of ​​the object based on the specified motion information, and controlling to perform shooting based on the falling area; An imaging device comprising:

2. 2. The photographing device according to claim 1, wherein the estimation means estimates the face direction of each person based on the photographed video.

3. 3. The photographing device according to claim 2, wherein the estimation means estimates the direction of each person's face based on video captured over a certain period of time after the ball is hit.

4. 3. The photographing apparatus according to claim 2, wherein the determining means determines the photographing area based on the face orientation of each person estimated by the estimating means.

5. The photographing device according to claim 4, characterized in that the determination means performs three-dimensional measurement based on vector components indicating the face direction of each person estimated by the estimation means, and determines an area in the direction of the object as the photographing area.

6. 2. The photographing device according to claim 1, wherein the control means estimates the direction of movement of each person based on the image captured of the photographing area, and estimates the area where the object will fall based on the estimated direction of movement.

7. 2. The photographing device according to claim 1, wherein, when there is only one person who is not moving, the control means estimates the area where the object will fall based on the position of the person.

8. 2. The photographing device according to claim 1, wherein the control means controls one or more of panning, tilting, and zooming to perform photographing based on the fall area.

9. 2. The photographing device according to claim 1, wherein the control means performs digital zooming so as to photograph based on the falling area.

10. the imaging device includes a first imaging device and a second imaging device; the first image capture device is provided with the estimation means and the determination means, The second imaging device is equipped with the control means.

2. The imaging device according to claim 1.

11. A method for controlling an imaging device, comprising: an estimation step in which the estimation means of the image capturing device estimates motion information of each person based on the captured video; a determination step in which a determination means of the photographing device determines a photographing area based on the motion information of each person estimated in the estimation step; a control step in which a control means of the photographing device specifies motion information of each person based on a video of the photographing area, estimates a falling area of ​​an object based on the specified motion information, and controls the photographing device to perform photographing based on the falling area; 11. A control method for an imaging device, comprising:

Images