Information processing device, control method and program for information processing device

Abstract

To provide a technique to acquire appropriate images even when the position of a subject changes.SOLUTION: An information processing apparatus (101) comprises: receiving means (413) that receives an instruction to change an area photographed by first photographing means (103) from a first photographic area to a second photographic area; acquisition means (403) that, for a subject associated in advance with the second photographic area when the instruction is received, acquires information on the current position of the subject; difference acquisition means (404) that, based on the position information, acquires the difference between a predetermined position and the position of the subject in the second photographic area; and correction means (405) that changes the angle of view of the first photographing means based on the difference to change the second photographic area.SELECTED DRAWING: Figure 7

Description

[Technical Field]

[0001] The present invention relates to an information processing device, a control method for an information processing device, and a program. [Background technology]

[0002] In recent years, the demand for live streaming and video production has increased with the increase in online events. Examples include video recording for entertainment events such as music events and plays, e-learning systems for lectures, and business applications such as online presentations and online meetings. Furthermore, lectures are often recorded and live streamed by installing cameras in existing classrooms that lack streaming or filming equipment, with as few cameras as possible being used for filming. As mentioned above, filming takes place in a variety of locations, and space for equipment, cameramen, and operators is often limited, so filming is often done with a small number of people.

[0003] When capturing video in these situations, the preset function of a PTZ (pan-tilt-zoom) camera is used, which allows a single camera to capture multiple angles of view. Pan and tilt are functions that rotate the lens or the entire camera horizontally and vertically, respectively, relative to the surface on which the camera is installed. Zoom is a function that enlarges or reduces the image output by the camera's image sensor. The camera's preset function allows the operator to specify PTZ values ​​in advance to determine the capture area, and includes functions such as preset patrol, which automatically patrols through multiple capture areas, and preset movement, which allows the operator to specify a specific preset to change the capture area.

[0004] Patent Document 1 discloses a technology for automatically capturing high-quality images by assigning a composition score to image data input from an imaging sensor during preset patrol of a PTZ camera, etc. Composition in photographs and video capture refers to the subjects that make up the image, the position of the subjects on the screen, and the size of the subjects that occupy the screen. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Patent No. 6729572 Summary of the Invention [Problem to be solved by the invention]

[0006] However, with conventional technology, when the shooting area is moved by specifying a preset, if the subject moves in the new shooting area, the operator cannot continue shooting with the intended composition. If the intended composition is not achieved, the operator must manually operate the camera to correct the angle of view after moving the preset, and manual PTZ causes image blurring, making it difficult to capture continuous, smooth images. Thus, there is a problem in that it is difficult to capture appropriate images when the position of the subject changes.

[0007] The present invention has been made in view of the above-mentioned problems, and has an object to provide a technique for acquiring an appropriate image even when the position of the subject changes. [Means for solving the problem]

[0008] To achieve the above object, an information processing device according to one aspect of the present invention comprises: a receiving means for receiving an instruction to change an area photographed by the first photographing means from the first photographing area to the second photographing area; When the instruction is received by the receiving means 、 Position information of the subject previously associated with the second photographing area based on an image acquired by a second image capturing means having a wider angle than the first image capturing means. Acquisition means for acquiring; a difference acquisition means for acquiring a difference between a predetermined position in the second photographing area and a position of the subject based on the position information; a change unit that changes the angle of view of the first imaging unit based on the difference to change the second imaging area; Equipped with 、 When there are a plurality of subjects associated in advance with the second photographing area and the area sizes of the plurality of subjects change due to movement of the plurality of subjects, the change means changes the angle of view after the change in accordance with the area sizes of the plurality of subjects before the change. It is characterized by the following. [Effects of the Invention]

[0009] According to the present invention, it is possible to acquire an appropriate image even if the position of the subject changes. [Brief explanation of the drawings]

[0010] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of an information processing system according to an embodiment. [Figure 2] FIG. 10 is a conceptual diagram illustrating an example of a situation change over time according to an embodiment. [Figure 3] FIG. 1 is a diagram showing an example of the hardware configuration of an information processing apparatus according to an embodiment. [Figure 4] FIG. 2 is a diagram showing an example of a software logical configuration (functional configuration) of an information processing apparatus according to an embodiment. [Figure 5] 10 is a flowchart showing a procedure of a process performed by an information processing apparatus according to an embodiment when registering a preset. [Figure 6] FIG. 10 is an explanatory diagram of information stored by an information processing apparatus according to an embodiment at the time of preset registration. [Figure 7] 10 is a flowchart showing a procedure of a process performed by an information processing device according to an embodiment when capturing video. [Figure 8] 10A and 10B are diagrams illustrating an example of correction when a composition in which a subject is at the center of the screen is not established according to an embodiment. [Figure 9] 10A and 10B are diagrams illustrating an example of correction when the number of subjects to be photographed changes according to an embodiment. [Figure 10] 10A to 10C are diagrams showing examples of correction when the size of a subject being photographed changes according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0011] 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 claimed invention. 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.

[0012] <System configuration> An example of the configuration of an information processing system including multiple cameras according to this embodiment will be described with reference to FIG.

[0013] The system according to this embodiment includes an information processing device 101, a PTZ camera 103, and an overhead camera 104, which are connected via a network 102. A plurality of presets can be registered in the PTZ camera 103. A preset is information in which an operator operating the PTZ camera 103 specifies PTZ values ​​in advance to define a shooting area. When registering a preset, a subject included in the shooting area is associated with the shooting area. For example, when registering a preset in a situation where a subject is located at a predetermined position in the shooting area, the shooting area is registered in association with the position (initial position) of the subject within the shooting area.

[0014] The operator specifies a preset via the information processing device 101, thereby outputting an instruction to change the shooting area to the PTZ camera 103. The above-described shooting areas and presets have a one-to-one relationship. In this configuration example, the PTZ camera 103 is a camera that captures images of a subject in various compositions and is capable of controlling at least one of pan, tilt, and zoom. The overhead camera 104 is a wide-angle camera that can capture all of the shooting areas set by the multiple presets set in the PTZ camera 103. In other words, the overhead camera 104 is a camera that captures an image overlooking the shooting area captured by the PTZ camera 103. Based on the image captured by this overhead camera 104, subject position information is acquired. Video captured by the PTZ camera 103 or the overhead camera 104 may be recorded in each camera or in a storage device connected via the network 102.

[0015] The information processing device 101 is a computer device that performs the above-described operations, and may be configured as a personal computer, a smartphone, a tablet terminal device, or the like. The preset switching may be performed automatically by programming a preset tour in the information processing device 101 or the PTZ camera 103, rather than manually by an operator. Note that FIG. 1 shows the main components of the system of this embodiment that will be referred to in the following description, and the system may include additional devices in addition to the illustrated components. For example, there may be multiple PTZ cameras and overhead cameras. The system may also include other devices, such as a server device that operates the cameras and controls image transmission, and a device that relays data communication.

[0016] <Photography conditions and photographic area> The movement of the shooting conditions and shooting area (preset) according to this embodiment will be described using Fig. 2. In Fig. 2, situations that change over time are represented by time t1 shown in situation 21, time t2 shown in situation 22, time t3 shown in situation 23, and time t4 shown in situation 24. In this embodiment, preset A, in which shooting area 205 for shooting subject 201 is set, and preset B, in which shooting area 203 for shooting subject 202 is set, are registered in PTZ camera 103.

[0017] First, at time t1, preset B is specified by the operator for PTZ camera 103, and PTZ camera 103 is capturing an image of subject 202 in capturing area 203. At time t2, capturing an image of preset A is specified by the operator. PTZ camera 103, which has received the specification of preset A, captures an image of subject 201 in capturing area 205. At time t3, subject 202, which is the subject of capture of preset B, moves. At this time, information processing device 101 detects from the image of overhead camera 104 that subject 202 captured within capturing area 204 acquired from overhead camera 104 has moved, and can acquire position information of subject 202.

[0018] At time t4, when the operator again specifies preset B, the information processing device 101 issues a PTZ instruction to the PTZ camera 103 to change the shooting area 203 set in preset B, which captures the subject 202 before movement, to the shooting area 207, which captures the subject 202 after movement, based on the position information of the subject 202 acquired from the image of the overhead camera 104.

[0019] <Hardware configuration> Fig. 3 is a diagram showing an example of the hardware configuration of an information processing device 101 according to this embodiment. The information processing device 101 according to this embodiment will be described using Fig. 3. The information processing device 101 has a CPU 301, a RAM 302, a ROM 303, an operation unit 304, an output control unit 305, and a communication I / F 306. Note that in the example of Fig. 3, the information processing device 101, the PTZ camera 103, and the overhead camera 104 are all connected to a network 102 such as a LAN, but the form of the network connecting each device can take various forms and is not limited to a specific form.

[0020] The CPU 301 is one or more CPUs that operate based on programs stored in the ROM 303 and control the entire information processing device 101. The ROM 303 stores a boot program executed by the CPU 301 when the information processing device 101 is started up, an instruction program for executing the processing of the information processing device 101, data used by these programs, and the like.

[0021] The CPU 301 controls an output device such as a display and an input device such as a keyboard, a mouse, a camera controller, and a camera switcher via an operation unit 304 and an output control unit 305. The CPU 301 acquires data via the operation unit 304. The CPU 301 also outputs generated data to the output device via the output control unit 305. For example, when the hardware configuration of FIG. 3 functions as the information processing device 101 according to the embodiment, the CPU 301 of the information processing device 101 executes a program loaded on the RAM 302 to realize the functions of the information processing device 101.

[0022] The communication I / F 306 receives data from other devices via the network 102 and sends it to the CPU 301, and transmits data generated by the CPU 301 to other devices such as the PTZ camera 103 and the overhead camera 104 via the network 102. Furthermore, the devices connected to these networks communicate with the information processing device 101 via the communication I / F 306. The ROM 303 also stores image data acquired by the PTZ camera 103 and the overhead camera 104 from the network 102 via the communication I / F 306. The CPU 301 of the information processing device 101 loads these programs from the ROM 303 into the RAM 302 and executes them, but as another example, the CPU 301 may acquire these programs from other devices via the communication I / F 306.

[0023] <Software configuration (functional configuration)> Fig. 4 is a diagram showing an example of the software logical configuration (functional configuration) of the information processing device 101 according to this embodiment. The information processing device 101 includes an image acquisition unit 401, a subject extraction unit 402, a position information acquisition unit 403, a position change amount acquisition unit 404, a correction unit 405, an imaging control unit 406, a preset instruction receiving unit 413, and a preset registration unit 414. In Fig. 4, 410 denotes image data, 411 denotes subject information data, 412 denotes position information data, and 415 denotes preset information.

[0024] The image acquisition unit 401 acquires image data 410 from the PTZ camera 103 and / or the overhead camera 104. The object extraction unit 402 extracts an object from the image acquired by the image acquisition unit 401 and acquires object information data 411. The position information acquisition unit 403 acquires position information data 412 of the object extracted from the image of the overhead camera 104.

[0025] The position change amount acquisition unit 404 acquires the position change amount of the subject based on the difference between the extracted position information of the subject and the initial position of the subject in the shooting area in the preset information (difference acquisition). If the position change amount is equal to or greater than a threshold, the correction unit 405 corrects the shooting area corresponding to the preset instruction received by the preset instruction receiving unit 413 based on the position change amount. The shooting control unit 406 controls the PTZ camera 103 to shoot the shooting area corrected by the correction unit 405, or to shoot the shooting area corresponding to the preset instruction if the correction by the correction unit 405 is not performed.

[0026] The preset instruction receiving unit 413 receives an instruction to change the shooting composition of the PTZ camera 103 by specifying one of multiple presets. The preset registration unit 414 generates and registers preset information that can identify the subject that existed at the time of preset registration and the subject's position information, based on the subject information data 411 and the position information data 412.

[0027] Hereinafter, processing performed by the information processing device 101 having the logical configuration shown in Fig. 4 will be described with reference to the flowcharts in Fig. 5 and Fig. 7. Note that the following description will be made assuming that each unit shown in Fig. 4 or each functional unit constituting a unit is the subject of processing. However, in reality, the functions of the functional units of the information processing device 101 are realized by the CPU 301 executing a computer program that causes the CPU 301 to realize the functions of the functional units. Note that the functional units shown in Fig. 4 may be implemented in hardware.

[0028] <Processing when registering presets> 5 is a flowchart showing the procedure of a process performed by the information processing device according to this embodiment when registering a preset. The following preset registration process is performed when registering one preset for a photographing composition. When registering multiple presets, the processes from step S501 to step S504 shown in FIG. 5 are repeated.

[0029] In step S501, when the operator instructs preset registration, the image acquisition unit 401 acquires image data 410 from the PTZ camera 103 and the overhead camera 104, and stores the image data in the RAM 302. The image data may be a still image, or one frame of a series of frames of a moving image.

[0030] In step S502, the subject extraction unit 402 extracts subjects such as subject 201 and subject 202 shown in FIG. 2 from the acquired image data. The extracted subject information data 411 is output to the position information acquisition unit 403. While general object recognition is widely known as an object recognition method using an image, in this embodiment as well, the subject to be extracted is not limited to a person, and any subject that can be recognized from an image may be extracted. However, it is also possible to determine the subject to be extracted in advance, or to exclude subjects that are unnecessary for reproducing the composition from the subjects to be extracted.

[0031] In step S503, the position information acquisition unit 403 acquires position information (position at the time of preset registration) of the subject extracted from the image data of the overhead camera 104 in accordance with the subject information data 411, and outputs position information data 412. At this time, the position information acquisition unit 403 associates the image acquired from the PTZ camera 103 with the subject included in the image acquired from the overhead camera 104, and acquires only the position information of the subject included in the image from the PTZ camera 103. Feature matching and the like are widely known as techniques for associating the same subject captured in different images. Also known methods for acquiring a position from an image include a method of acquiring the actual coordinates of the subject by setting a reference marker in advance, and a method of calculating from the blurred shape of the image, and the method for acquiring the position information is not particularly limited.

[0032] The subject position may be the coordinates of the center position (e.g., center of gravity position) of the subject area of ​​a person or the like recognized from the image, or if a specific part of the subject is photographed using a preset, the center coordinates (e.g., center of gravity coordinates) of the part area may be the subject position.

[0033] In step S504, the preset registration unit 414 outputs preset information 415 that can identify the subject and the subject's position information based on the subject information data 411 and the position information data 412. The position of the subject registered here becomes the initial position.

[0034] <Example of preset information> An example of the preset information 415 according to this embodiment will now be described with reference to Fig. 6. The saved preset information is information associated with a PTZ value that specifies the shooting area of ​​the PTZ camera 103, and includes a preset ID, a subject ID, subject identification information, and information on the initial position, and can also store information on the current position.

[0035] Each preset and subject is assigned a preset ID and subject ID that allow them to be uniquely identified. Subject identification information is information about the subject's features used when extracting the subject from an image or when acquiring location information from an image. Subject identification information can be any information that can identify the subject with high accuracy.

[0036] The current position can also be stored as information about the current position of the subject. The current position is set to a value similar to the initial position, and is updated by the process described below with reference to Figure 7. Therefore, when processing is first started, there is no current position information, and only the initial position information is included.

[0037] By storing the preset ID, subject ID, subject identification information, and initial position of the subject in association with each other, when a preset designation is accepted, it is possible to obtain information about the subject included in the designated preset and the initial position of that subject at the time of preset registration.

[0038] If multiple subjects exist within the same preset, the position information of each subject may be acquired and saved. In this case, multiple subject IDs, multiple subject identification information, multiple initial positions, and multiple current positions are associated with one preset ID.

[0039] <Processing during shooting> 7 is a flowchart showing the procedure of processing during video capture according to this embodiment. This processing may start when video recording begins. Alternatively, the processing may start when the information processing system is started, or after one or more presets have been registered.

[0040] In step S701, the image acquisition unit 401 acquires an image from the overhead camera 104 and outputs image data 410 to the object extraction unit 402. In step S702, the object extraction unit 402 acquires pre-registered preset information 415. Then, the object extraction unit 402 extracts an object from the image data 410 in accordance with the preset information 415 and outputs object information data 411 to the position information acquisition unit 403.

[0041] In step S703, the position information acquisition unit 403 acquires the current position of the subject extracted from the image data of the overhead camera 104 in accordance with the subject information data 411, and updates the current position of the subject included in the preset information 415. The current positions of all subjects that are included in the preset information 415 and that can be detected from the image acquired from the overhead camera 104 are to be updated.

[0042] In step S704, the preset designation receiving unit 413 determines whether or not a preset designation for instructing a change in the imaging area has been received from the operator. If a preset designation has been received, the preset ID of the designated preset is output to the position change amount acquiring unit 404, and the process proceeds to step S705. On the other hand, if a preset designation has not been received, the process returns to step S701.

[0043] The processing from step S701 to step S704 may be performed each time a frame of video is acquired, depending on the frame rate of the overhead camera 104, or the number of times the processing is repeated within a specific time period may be set arbitrarily.

[0044] In step S705, the position change amount acquisition unit 404 acquires position information and the like associated with the input preset ID from the preset information 415, and calculates and acquires the position change amount by comparing the initial position at the time of preset registration of the subject with the current position.

[0045] In step S706, the correction unit 405 determines whether or not the position change amount of the subject is greater than or equal to a threshold value. If the position change amount of the subject is greater than or equal to the threshold value, it can be determined that PTZ angle-of-view correction is necessary because it affects the composition, and the process proceeds to step S707. On the other hand, if the position change amount of the subject is less than the threshold value, the process proceeds to step S709. The threshold value may be arbitrarily changed.

[0046] In step S707, the correction unit 405 determines the PTZ value of the PTZ camera 103 calculated according to the position change of the subject. The corrected (changed) PTZ value is determined by converting the calculation result of the position change amount output by the correction value calculation unit 406 into the coordinate system used by the PTZ camera 103. For example, the PTZ value is determined by controlling the imaging direction and the zoom magnification so that the inside of the imaging area has the same composition as at the time of preset registration based on the current position of the subject. An example of correcting this PTZ value will be described later.

[0047] In step S708, the shooting control unit 409 outputs the corrected PTZ value to the PTZ camera 103, thereby executing the PTZ movement of the PTZ camera 103. In step S709, the shooting control unit 409 outputs the preset-registered PTZ value to the PTZ camera 103, thereby executing the PTZ movement of the PTZ camera 103. Thus, the series of processes in FIG. 7 is completed.

[0048] <PTZ Value Correction> Next, a correction example of the PTZ value according to the present embodiment will be described using FIGS. 8(a) to 8(d) to FIGS. 10(a) to 10(c).

[0049] 8(a) to 8(d) are diagrams showing examples of correction when a composition in which the subject is at the center of the screen cannot be established due to the movement of the subject. First, Fig. 8(a) shows an example of an image captured by the PTZ camera 103 with the PTZ values ​​set when registering a preset. The preset shown in Fig. 8(a) has a shooting area set to capture a person as the subject, with the entire head included in the shooting area.

[0050] 8(b) shows an example of an image captured by the PTZ camera 103 at the PTZ value set at the time of preset registration after the subject's head has moved from the center position of the shooting area at the time of preset registration. The center of the subject's head after the movement is indicated as point P.

[0051] FIG. 8(c) shows an example of correction values ​​when performing angle of view correction. For example, as shown in FIG. 8(c), the correction value for the PTZ camera 103 can be calculated by calculating the distance in the pan direction and the distance in the tilt direction from point P using the center of the screen as a reference. In the case of FIG. 8(c), since the distance from the PTZ camera 103 does not change, the distances in the pan and tilt directions from point P are correction values ​​x and y, respectively. Therefore, by performing correction to shift the shooting area by correction values ​​x and y as shown in FIG. 8(c), it is possible to reproduce a composition in which the subject's head can be captured at the center of the shooting area, as shown in FIG. 8(d). In this way, the angle of view is corrected so that the subject is positioned at the center of the shooting area after correction.

[0052] 9(a) to 9(d) are diagrams showing examples of correction when the number of subjects changes due to movement of the subjects. First, Fig. 9(a) shows an example of an image captured by the PTZ camera 103 with the PTZ value set when registering a preset. In the preset shown in Fig. 9(a), two people are set as subjects, and a shooting area is set to capture images that include the entire heads of the two people in the shooting area.

[0053] 9(b) shows an example of comparing the state of the subject before and after the movement from a bird's-eye view. In the example after the movement shown in FIG. 9(b), one of the subjects moves out of the shooting area that can be captured by the PTZ camera 103 shown in FIG. 9(a).

[0054] FIG. 9C shows an example of an image captured by the PTZ camera 103 with the PTZ values ​​set at the time of preset registration after the subject has moved out of the shooting area at the time of preset registration.

[0055] 9(d) shows an example of an image acquired from the PTZ camera 103 when the angle of view is corrected. For example, as a correction method, the zoom value of the PTZ camera 103 may be corrected to the wide side so that both of the two subjects are included in the shooting area. Also, in order to position the center of gravity of multiple subjects at the center of the screen, the corrected PTZ value may be calculated so that the position of point C, which is the midpoint between points P and Q, which are the centers of the heads of the two people, is positioned at the center of the screen. In this way, the angle of view is corrected so that the change in the number of subjects included in the shooting area after correction is small compared to the number of subjects previously associated with the preset shooting area to be changed.

[0056] 10A to 10C are diagrams showing examples of correction when the size of the subject being photographed changes due to the movement of the subject.

[0057] First, Fig. 10(a) shows an example of an image captured by the PTZ camera 103 with the PTZ values ​​set when the preset was registered. The preset shown in Fig. 10(a) sets a shooting area for capturing images of three people as subjects, with the entire heads of the three people included in the shooting area. The head areas in this case are indicated by dotted lines, with the heights of the head areas being A, C, and E, and the widths of the head areas being B, D, and F.

[0058] 10(b) shows an example of an image captured by the PTZ camera 103 using the PTZ values ​​set at the time of preset registration when one of the subjects moves closer to the PTZ camera 103. In this example, the size of the subject's area after movement is greater in height G and width H than at the time of preset registration, as shown in the figure.

[0059] 10(c) shows an example of an image acquired from the PTZ camera 103 when the angle of view has been corrected. For example, one method of correction may be to correct the zoom value of the PTZ camera 103 to the wide side so that the area sizes G and H of the subject become close to the sizes C and D at the time of preset registration. However, because only one of the three subjects is closer to the PTZ camera 103, if the zoom value is corrected based on that person, the sizes of the head areas of the remaining two subjects will become smaller than they were at the time of preset registration.

[0060] In such a case, the PTZ value may be adjusted so that the average value of the area sizes indicated by I×J, K×L, and M×N becomes the average value of A×B, C×D, and E×F. In other words, the angle of view is corrected so that the change in the size of the subject included in the corrected shooting area is small relative to the size of the subject previously associated with the preset shooting area to be changed. Also, the maximum or minimum size of the area size may be determined in advance, and the PTZ value may be corrected so that the area falls within the determined size.

[0061] If the correction results obtained by the correction methods shown in FIGS. 8(a) to 8(d) through 10(a) to 10(c), or other correction methods, are contradictory, the operator may determine in advance which correction method to prioritize. That is, if multiple correction methods are used to correct the angle of view of a PTZ camera and the multiple correction methods are contradictory and cannot be executed simultaneously, a predetermined correction method may be prioritized. Of the multiple correction methods (change methods), a correction method (change method) according to a predetermined priority may be executed. Furthermore, the correction method to prioritize may be determined for each preset. This allows for improved reproducibility of the composition.

[0062] The correction method is not limited to the correction examples shown in Figures 8(a) to 8(d) and 10(a) to 10(c). For example, the PTZ value may be corrected in accordance with the movement of the subject. Furthermore, as described above, the subject is not limited to a person, and may be any object that is included in the composition intended by the operator and can be recognized from the image.

[0063] If the number of subjects included in the new shooting area increases compared to the number of subjects previously associated with the new shooting area, the angle of view may be corrected so that the subjects previously associated with the new shooting area fit within the corrected shooting area and are maximized in size. For example, if the original composition had three subjects A, B, and C in the shooting area, but the subjects moved, increasing the number of subjects A, B, C, and D within the shooting area as a result of the current preset movement, the angle of view may be corrected so that subjects A, B, and C fit within the shooting area and the sizes of subjects A, B, and C are maximized within the shooting area. In this case, part or all of subject D may or may not be included within the shooting area as a result. Alternatively, instead of correcting to maximize the size, the center of gravity of subjects A, B, and C may be corrected to be at the center of the shooting area (e.g., the center of the screen). These corrections may also be performed in combination.

[0064] As described above, in this embodiment, when PTZ camera 103 receives an instruction to change the area to be photographed to a preset area, information on the current position of the subject associated with the preset is acquired from overhead camera 104 that photographs the subject. Then, based on the information on the current position, the amount of positional change of the subject from a predetermined position in the preset area (for example, the center position of the screen) is acquired, and the angle of view of PTZ camera 103 is corrected based on the amount of positional change, thereby correcting the preset area.

[0065] This allows the desired subject to be automatically tracked at an appropriate position, size, etc. when a preset movement is performed, reducing the effort required for adjustments after the preset movement. Therefore, it is possible to capture continuous, smooth video even if the position of the subject changes.

[0066] (Other embodiments) The present invention can also be realized by supplying 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.

[0067] 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]

[0068] 101: Information processing device, 103: PTZ camera, 104: Bird's-eye view camera, 401: Image acquisition unit, 402: Object extraction unit, 403: Position information acquisition unit, 404: Position change amount acquisition unit, 405: Correction unit, 406: Photography control unit, 411: Preset registration unit, 413: Preset instruction reception unit

Claims

1. a receiving means for receiving an instruction to change an area photographed by the first photographing means from the first photographing area to the second photographing area; an acquisition means for acquiring, when the instruction is received by the receiving means, position information of a subject associated in advance with the second photographing area based on an image acquired by a second photographing means having a wider angle than the first photographing means; a difference acquiring means for acquiring a difference between a predetermined position in the second photographing area and a position of the subject based on the position information; a change unit that changes the angle of view of the first image capturing unit based on the difference to change the second image capturing area; Equipped with The information processing device is characterized in that, when there are multiple subjects that are pre-associated with the second shooting area and the area size of the multiple subjects changes due to movement of the multiple subjects, the change means changes the angle of view after the change in accordance with the area size of the multiple subjects before the change.

2. 2. The information processing apparatus according to claim 1, wherein the change unit changes the second shooting area when the difference is equal to or greater than a threshold value, and does not change the second shooting area when the difference is less than the threshold value.

3. 3. The information processing apparatus according to claim 2, further comprising a control unit that controls the first photographing unit so that photographing is performed in accordance with the second photographing area or the photographing area changed by the change unit.

4. 4. The information processing apparatus according to claim 1, wherein the change unit changes the angle of view so that the subject is positioned at the center of a post-change shooting area.

5. 5. The information processing device according to claim 1, wherein the change means changes the angle of view so as to reduce the change in the number of subjects included in the corrected shooting area relative to the number of subjects previously associated with the second shooting area.

6. The information processing device according to any one of claims 1 to 5, characterized in that the change means changes the angle of view so as to reduce the change in size of the subject included in the changed shooting area relative to the size of the subject previously associated with the second shooting area.

7. The information processing device described in any one of claims 1 to 3, characterized in that when the number of subjects included in the second shooting area increases compared to the number of subjects pre-associated with the second shooting area, the change means changes the angle of view so that the subjects pre-associated with the second shooting area fit within the shooting area and so that the size of the subjects is maximized within the shooting area.

8. 8. The information processing apparatus according to claim 1, wherein the change unit executes a change method according to a predetermined priority from among a plurality of change methods.

9. the first photographing means is a PTZ camera capable of controlling at least one of pan, tilt, and zoom; 2. The information processing apparatus according to claim 1, wherein the second image capturing means is an overhead camera that captures an image overlooking the area captured by the first image capturing means.

10. The information processing device described in Claim 1, characterized in that the change means changes the angle of view so that the average area size of the multiple subjects after the change is equal to the average area size of the multiple subjects before the change.

11. a receiving step of receiving an instruction to change an area photographed by the first photographing means from the first photographing area to the second photographing area; an acquisition step of acquiring, when the instruction is received in the receiving step, position information of the subject associated in advance with the second photographing area based on an image acquired by a second photographing means having a wider angle than the first photographing means; a difference obtaining step of obtaining a difference between a predetermined position in the second photographing area and a position of the subject based on the position information; a changing step of changing the second photographing area by changing the angle of view of the first photographing means based on the difference; and In the change process, when there are a plurality of subjects that are pre-associated with the second shooting area, and the area size of the plurality of subjects changes due to movement of the plurality of subjects, the angle of view after the change is changed according to the area size of the plurality of subjects before the change.

12. A program for causing a computer to function as the information processing device according to any one of claims 1 to 10.

Images