Information processing apparatus, information processing method, and program product
By combining a wide-angle camera and a PTZ camera, using an information processing device for image recognition and calibration, setting viewpoint candidates, and controlling the PTZ camera's viewpoint, the cost and complexity issues of capturing multi-view images on-site in program production were solved, and high-quality viewpoint adjustment was achieved.
Patent Information
- Application Number
- CN202180023935.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Priority Date
- 2020-03-31
- Filing Date
- 2021-03-18
- Publication Date
- 2025-12-12
- Estimated Expiration
- 2041-03-18
AI Technical Summary
On the production set, using multiple imaging devices to capture images from various perspectives not only increases costs and complexity, but also existing technologies such as cutout methods and PTZ control methods suffer from image quality degradation or untimely perspective adjustments.
By combining a wide-angle camera and a PTZ camera, using an information processing device for image recognition and calibration, setting viewpoint candidates, and controlling the PTZ camera's viewpoint, multi-view image capture can be achieved.
By effectively utilizing a small number of imaging devices to acquire images with appropriate viewing angles and high quality, costs and complexity are reduced, while the flexibility and accuracy of viewing angle adjustments are improved.
Smart Images

Figure CN115315939B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present technology relates to an information processing apparatus, an information processing method, and a program, and more particularly to an information processing apparatus, an information processing method, and a program capable of easily obtaining an image having a proper angle of view with a small number of imaging devices. BACKGROUND
[0002] In the related art, at a live site of program production such as television broadcasting, many imaging devices are used to capture images having various angles of view, so that an image having a proper angle of view can be provided to viewers / listeners (see, for example, Patent Literature 1).
[0003] LIST OF CITATIONS
[0004] PATENT LITERATURE
[0005] Patent Literature 1: Japanese Patent Application Laid-Open No. 2011-101165 SUMMARY
[0006] PROBLEMS TO BE SOLVED BY THE INVENTION
[0007] On the other hand, in recent years, video distribution platforms have diversified, and video production and video distribution are increasingly performed by a small number of people or people without expertise. At the same time, there is an increasing demand for a technology capable of easily obtaining an image having a proper angle of view with a small number of imaging devices.
[0008] The present technology is made in view of such circumstances, and an object of the present technology is to easily obtain an image having a proper angle of view with a small number of imaging devices.
[0009] SOLUTION TO PROBLEM
[0010] An information processing apparatus according to an aspect of the present technology includes an angle-of-view candidate setting unit configured to set a plurality of angle-of-view candidates in accordance with a captured image range that can be captured by a first imaging device with respect to a predetermined imaging space, and an imaging angle-of-view setting unit configured to set an imaging angle of view of the first imaging device based on the plurality of angle-of-view candidates.
[0011] An information processing method according to an aspect of the present technology includes, by an information processing apparatus, setting a plurality of angle-of-view candidates in accordance with a captured image range that can be captured by an imaging device with respect to a predetermined imaging space, and setting an imaging angle of view of the imaging device based on the plurality of angle-of-view candidates.
[0012] A program according to an aspect of the present technology causes a computer to execute processing of setting a plurality of angle-of-view candidates in accordance with a captured image range that can be captured by an imaging device with respect to a predetermined imaging space, and setting an imaging angle of view of the imaging device based on the plurality of angle-of-view candidates.
[0013] According to an aspect of the present technology, a plurality of view angle candidates is set in accordance with a captured image range that can be captured by an imaging device with respect to a predetermined imaging space, and an imaging view angle of the imaging device is set based on the plurality of view angle candidates. BRIEF DESCRIPTION OF DRAWINGS
[0014] Figure 1 is a diagram illustrating an example of an imaging scene.
[0015] Figure 2 is a block diagram illustrating a first embodiment of an information processing system to which the present technology is applied.
[0016] Figure 3 is a block diagram illustrating a configuration example of an imaging device.
[0017] Figure 4 is a block diagram illustrating a first embodiment of an information processing unit of an information processing device.
[0018] Figure 5 is a flowchart for explaining a first embodiment of a view angle control process.
[0019] Figure 6 is a diagram illustrating an example of a feature point of a person.
[0020] Figure 7 is a diagram for explaining a method for setting a view angle candidate and an imaging view angle.
[0021] Figure 8 is a diagram illustrating an example of a full view angle image.
[0022] Figure 9 is a diagram illustrating an example of a cutout image.
[0023] Figure 10 is a block diagram illustrating a second embodiment of an information processing system to which the present technology is applied.
[0024] Figure 11 is a block diagram illustrating a second embodiment of an information processing unit of an information processing device.
[0025] Figure 12 is a flowchart for explaining a second embodiment of a view angle control process. DETAILED DESCRIPTION
[0026] A mode for carrying out the present technology (hereinafter referred to as an embodiment) will be described below. The description will be given in the following order.
[0027] 1. BACKGROUND
[0028] 2. First Embodiment
[0029] 3. Second Embodiment
[0030] 4. Variations
[0031] 5. Other
[0032] <<1. Background>>
[0033] As described above, in related technologies, numerous imaging devices are used at program production sites, such as television broadcasting, to capture images from various perspectives. Then, the images from these perspectives are appropriately switched between them for broadcasting, etc.
[0034] For example, Figure 1 Figure A illustrates an example of a news program scene. In this example, three people (i.e., news anchor 1, narrator 2, and narrator 3) are seated side by side from right to left. Furthermore, a monitor 4 is positioned between news anchor 1 and narrator 2.
[0035] In this case, for example, it is assumed that at least the captured image is obtained by imaging news anchor 1, commentator 2 and commentator 3 as half-body portraits respectively, the captured image is obtained by imaging adjacent commentators 2 and 3 together (group photo), and the captured image is obtained by imaging the entire scene.
[0036] Figure 1 Figure B illustrates an example of a talk show scene. In this example, three people (i.e., host 11, guest 12, and guest 13) are seated side by side from right to left.
[0037] In this case, for example, it is assumed that at least the captured image is obtained by imaging the host 11, guest 12 and guest 13 as half-body portraits respectively, the captured image is obtained by imaging adjacent guests 12 and 13 together (group photo), and the captured image is obtained by imaging the entire scene.
[0038] Figure 1 The diagram C illustrates an example of a variety show scene. In this example, host 21 stands at the left end. Furthermore, to host 21's right, guests 22 through 24 are seated in the first row of the platform, while guests 25 and 26 are seated in the second row.
[0039] In this case, for example, it is assumed that at least the captured images are obtained by imaging the host 21 and guests 22 to 26 as half-body portraits, the captured images are obtained by imaging adjacent guests 22 to 26 together (group photo), and the captured images are obtained by imaging the entire scene.
[0040] Here, if the captured images of the respective viewpoints are captured by different imaging devices, the required cost and the number of photographers increase. In addition, the control of the imaging devices and the like becomes complicated.
[0041] On the other hand, in the related art, a method of obtaining images of a plurality of viewpoints with one imaging device is used. As the method of obtaining images of a plurality of viewpoints with one imaging device, for example, a cutout method and a PTZ control method are known.
[0042] The cutout method is a method of imaging a wide range in a state where the PTZ (pan, tilt, and zoom) of the imaging device is fixed and cutting out an image having a required viewpoint from the captured image. For example, in the example of A of Figure 1 the captured image of the entire scene is captured, and an image of a half-body portrait of the respective person and the like is cut out from the obtained captured image, respectively.
[0043] In the cutout method, images of various viewpoints can be obtained at the same time. In addition, there is no physical limitation, and thus the viewpoint can be switched immediately.
[0044] On the other hand, in the cutout method, in a case where a subject to be enlarged is present, there is a possibility that the image quality (resolution) deteriorates. In addition, in a case where the motion of the subject is fast, there is a possibility that motion blur occurs.
[0045] The PTZ control method is a method of driving the PTZ of the imaging device and imaging while physically moving the viewpoint of the imaging device.
[0046] In the PTZ control method, the PTZ is driven, and thus the change of the viewpoint can be increased.
[0047] On the other hand, in the PTZ control method, the imaging device needs to be physically moved to change the viewpoint (subject or composition), which takes time to obtain an image having a required viewpoint. Thus, there is a case where, for example, an image having a desired viewpoint cannot be obtained due to the movement of the subject before the viewpoint is adjusted.
[0048] As described above, both of the methods have advantages and disadvantages, and the advantages and disadvantages are in a trade-off relationship.
[0049] On the other hand, the present technology improves the disadvantages of both methods and enables an image having an appropriate viewpoint to be easily obtained with a small number of imaging devices.
[0050] <<2. First Embodiment>>
[0051] First, a first embodiment of the present technology will be described with reference to Figures 2 to 9 to which the present technology is applied.
[0052] <Configuration of information processing system 101>
[0053] Figure 2 A configuration example of an information processing system 101 according to a first embodiment of the present technology will be illustrated.
[0054] The information processing system 101 includes a wide-angle camera 111, a microphone 112, a PTZ camera 113, an information processing apparatus 114, and a switch 115. The wide-angle camera 111, the microphone 112, the PTZ camera 113, the information processing apparatus 114, and the switch 115 are connected to each other via a wired and / or wireless network and exchange various data.
[0055] The wide-angle camera 111 includes, for example, an imaging device capable of wide-angle imaging. The wide-angle camera 111 is installed, for example, at a place where an imaging space can be widely observed (overhead), and performs wide-angle imaging so that the imaging space is widely included. The wide-angle camera 111 transmits image data (hereinafter referred to as wide-angle image data) corresponding to a captured image (hereinafter referred to as a wide-angle image) obtained by wide-angle imaging to the information processing apparatus 114.
[0056] Here, the imaging space is a three-dimensional space in which imaging of the information processing system 101 is performed, and is, for example, a space in which an event to be imaged (for example, a program production, a sports game, or the like) is performed.
[0057] Note that the positions of the PTZ and the wide-angle camera 111 are generally fixed.
[0058] The microphone 112 collects sound in the imaging space and transmits sound data corresponding to the collected sound to the information processing apparatus 114.
[0059] The PTZ camera 113 includes, for example, an imaging device capable of remotely controlling a PTZ. The angle of view of the PTZ camera 113 is controlled by driving the PTZ under the control of the information processing apparatus 114. The PTZ camera 113 images the imaging space and transmits image data corresponding to a captured image obtained to the information processing apparatus 114.
[0060] Note that the position of the PTZ camera 113 is generally fixed.
[0061] The information processing apparatus 114 includes, for example, a computer or the like. The information processing apparatus 114 calibrates the wide-angle camera 111 and the PTZ camera 113. Furthermore, the information processing apparatus 114 identifies a situation of the imaging space based on the wide-angle image data and the sound data. For example, a state of a subject in the imaging space, a content of a scene (hereinafter referred to as an imaging scene) in the imaging space, a content of sound and a position of a sound source in the imaging space, a state of an event being performed in the imaging space, and the like are identified as the situation of the imaging space.
[0062] The information processing apparatus 114 controls the angle of view of the PTZ camera 113 by driving the PTZ of the PTZ camera 113 in accordance with the situation of the imaging space. Further, the information processing apparatus 114 cuts out an image having a desired angle of view from the captured image captured by the PTZ camera 113, and transmits image data (hereinafter referred to as cut-out image data) corresponding to the cut-out image (hereinafter referred to as a cut-out image) to the switcher 115. In addition, the information processing apparatus 114 transmits the wide-angle image data to the switcher 115.
[0063] The switcher 115 selects a desired image from the wide-angle image and the cut-out image, and transmits image data corresponding to the selected image to the later stage. In addition, the switcher 115 cuts out an image having a desired angle of view from the wide-angle image as needed, and transmits image data corresponding to the cut-out image to the later stage.
[0064] <Configuration example of information processing apparatus 114>
[0065] Figure 3 A configuration example of the hardware of the information processing apparatus 114 is illustrated.
[0066] In the information processing apparatus 114, a CPU 201, a read only memory (ROM) 202, and a random access memory (RAM) 203 are connected to each other via a bus 204. An input / output interface 205 is further connected to the bus 204. An input unit 206, an output unit 207, a storage unit 208, a communication unit 209, and a drive 210 are connected to the input / output interface 205.
[0067] The input unit 206 includes, for example, a keyboard, a mouse, a microphone, and the like.
[0068] The output unit 207 includes, for example, a display, a speaker, and the like.
[0069] The storage unit 208 includes, for example, a non-volatile memory such as a hard disk.
[0070] The communication unit 209 communicates with the wide-angle camera 111, the microphone 112, the PTZ camera 113, and the switcher 115 using a predetermined communication scheme.
[0071] The drive 210 drives a removable recording medium 211 such as, for example, a magnetic disk, an optical disk, a magneto-optical disk, and a semiconductor memory.
[0072] Note that the program to be executed by the information processing apparatus 114 (CPU 201) can be provided by, for example, being recorded in the removable recording medium 211 as a package medium or the like. The program recorded in the removable recording medium 211 is installed in the storage unit 208, for example, by attaching the removable recording medium 211 to the drive 210 via the input / output interface 205.
[0073] Further, the program is received and installed in the storage unit 208, for example, by the communication unit 209 via a wired or wireless transmission medium such as a local area network, the Internet, and digital satellite broadcasting.
[0074] Further, for example, the program can be pre-installed in the ROM 202 or the storage unit 208.
[0075] Then, in the information processing apparatus 114, for example, the CPU 201 loads the program stored in the ROM 202 or the storage unit 208 into the RAM 203 via the input / output interface 205 and the bus 204 and executes the program, thereby performing a series of processes.
[0076] Note that hereinafter, the description of the bus 204 and the input / output interface 205 will be omitted in the case where each unit in the information processing apparatus 114 exchanges data and the like via the bus 204 and the input / output interface 205. For example, in the case where the CPU 201 and the communication unit 209 communicate via the bus 204 and the input / output interface 205, the description of the bus 204 and the input / output interface 205 will be omitted, and the case will be simply described as the CPU 201 and the communication unit 209 communicate.
[0077] <Configuration example of information processing unit 251>
[0078] Figure 4 A configuration example of the information processing unit 251 of the first embodiment as a function implemented by the CPU 201 of the information processing apparatus 114 executing a program is illustrated.
[0079] The information processing unit 251 includes a calibration unit 261, an imaging control unit 262, and an extraction unit 263.
[0080] The calibration unit 261 calibrates the wide-angle camera 111 and the PTZ camera 113. For example, the calibration unit 261 obtains positions and orientations of the wide-angle camera 111 and the PTZ camera 113 in a world coordinate system common to the wide-angle camera 111 and the PTZ camera 113. Specifically, the calibration unit 261 obtains a transformation matrix that transforms the world coordinate system into a camera coordinate system unique to each of the wide-angle camera 111 and the PTZ camera 113. The camera coordinate system is a coordinate system based on optical axes of the wide-angle camera 111 and the PTZ camera 113. The calibration unit 261 supplies information about the transformation matrices of the wide-angle camera 111 and the PTZ camera 113 to the imaging control unit 262.
[0081] The imaging control unit 262 controls the PTZ of the PTZ camera 113 to control the angle of view of the PTZ camera 113. The imaging control unit 262 includes an identification unit 271, an angle-of-view setting unit 272, and an angle-of-view control unit 273.
[0082] The identification unit 271 identifies a situation of the imaging space based on the wide-angle image data from the wide-angle camera 111 and the sound data from the microphone 112. The identification unit 271 supplies information about the identified situation of the imaging space to the angle-of-view setting unit 272.
[0083] The angle-of-view setting unit 272 sets an angle of view (hereinafter referred to as an imaging angle of view) at which the PTZ camera 113 images the imaging space based on the situation of the imaging space. The angle-of-view setting unit 272 includes an angle-of-view candidate setting unit 281 and an imaging angle-of-view setting unit 282.
[0084] The angle-of-view candidate setting unit 281 sets a plurality of angle-of-view candidates from captured image ranges that can be captured by the PTZ camera 113 based on the situation of the imaging space. The angle-of-view candidate is, for example, a predicted angle of view to be used in broadcasting or the like. The angle-of-view candidate setting unit 281 supplies information about the set angle-of-view candidates to the imaging angle-of-view setting unit 282.
[0085] The imaging angle-of-view setting unit 282 sets the imaging angle of view based on the angle-of-view candidates. The imaging angle-of-view setting unit 282 supplies information about the imaging angle of view to the angle-of-view control unit 273. Further, the imaging angle-of-view setting unit 282 supplies the imaging angle of view and information about the angle-of-view candidates included in the imaging angle of view to the cutout unit 263.
[0086] The angle-of-view control unit 273 controls the angle of view of the PTZ camera 113 by driving the PTZ of the PTZ camera 113. In addition, the angle-of-view control unit 273 supplies information indicating a state of the angle of view of the PTZ camera 113 to the cutout unit 263.
[0087] The cutout unit 263 cuts out an image having a required angle of view from a captured image captured by the PTZ camera 113, and transmits cutout image data corresponding to the cutout image to the switcher 115 via the communication unit 209.
[0088] <First Embodiment of the Angle-of-View Control Process>
[0089] Next, a first embodiment of an angle-of-view control process to be executed by the information processing apparatus 114 will be described with reference to the flowchart of Figure 5
[0090] This process is started, for example, when imaging of the imaging space is started and is ended when imaging of the imaging space is ended.
[0091] Further, it is assumed that the calibration unit 261 calibrates the wide-angle camera 111 and the PTZ camera 113 before this process, and the transformation matrices of the wide-angle camera 111 and the PTZ camera 113 are known. In other words, it is assumed that the positions and orientations of the wide-angle camera 111 and the PTZ camera 113 in the world coordinate system are known.
[0092] In step S1, the recognition unit 271 recognizes the situation of the imaging space.
[0093] Specifically, the recognition unit 271 acquires wide-angle image data from the wide-angle camera 111 and sound data from the microphone 112 via the communication unit 209. The recognition unit 271 recognizes the situation of the imaging space by performing image recognition on the wide-angle image data and sound recognition on the sound data.
[0094] For example, the recognition unit 271 recognizes the states of the subjects in the wide-angle image. More specifically, the recognition unit 271 recognizes the subjects present in the wide-angle image using methods such as face detection, face recognition, posture recognition, motion recognition, and object detection, and recognizes the types, positions, postures, motions, feature points, and the like of each subject.
[0095] Figure 6 An example of feature points to be detected in the case where the subjects are people is illustrated.
[0096] The feature point Pf1L corresponds to the left eye, and the feature point Pf1R corresponds to the right eye. The feature point Pf2L corresponds to the left ear, and the feature point Pf2R corresponds to the right ear. The feature point Pf3 corresponds to the nose. The feature point Pf4 corresponds to the joint of the neck. The feature point Pf5L corresponds to the joint of the left shoulder, and the feature point Pf5R corresponds to the joint of the right shoulder. The feature point Pf6L corresponds to the joint of the left elbow, and the feature point Pf6R corresponds to the joint of the right elbow. The feature point Pf7L corresponds to the joint of the left wrist, and the feature point Pf7R corresponds to the joint of the right wrist. The feature point Pf8L corresponds to the joint of the left hip, and the feature point Pf8R corresponds to the joint of the right hip. The feature point Pf9L corresponds to the joint of the left knee, and the feature point Pf9R corresponds to the joint of the right knee. The feature point Pf10L corresponds to the joint of the left ankle, and the feature point Pf10R corresponds to the joint of the right ankle.
[0097] For example, a person's skeleton, posture, motion, and the like are recognized by detecting and tracking feature points including the person's joints in this way.
[0098] Further, the recognition unit 271 recognizes the content of the imaging scene using a method such as scene recognition. Further, the recognition unit 271 recognizes a main subject (hereinafter referred to as a main subject) and a subject related to the main subject (hereinafter referred to as a related subject) based on the state of the subject and the content of the imaging scene.
[0099] For example, in a case where the content of the imaging scene is a talk show program, the main person of the talk (for example, a speaker, a guest, a main person of a topic, and the like), a monitor, a poster, and the like can be recognized as the main subject. Further, for example, a person who listens to the speaker's speech, the speaker's partner, a poster, and the like can be recognized as the related subject.
[0100] For example, in a case where the content of the imaging scene is a live music, the main person of the live (for example, a singer, a guitarist who plays a guitar solo, and the like) can be recognized as the main subject. Further, for example, a member other than the main person, a co-performer, an instrument, and the like can be recognized as the related subject.
[0101] For example, in a case where the content of the imaging scene is a sports broadcast, the main person of the sports (for example, a player who holds a ball, a player who is in the lead, and the like) can be recognized as the main subject. Further, for example, a player other than the main person, a ball, and the like can be recognized as the related subject.
[0102] Further, the recognition unit 271 recognizes, for example, the content of a sound in the imaging space, the position of a sound source, and the like.
[0103] Further, the recognition unit 271 recognizes a state of an event that is being performed in the imaging space based on, for example, a state of a subject, a content of an imaging scene, a content of a sound in the imaging space, a position of a sound source, and the like.
[0104] The recognition unit 271 supplies information on a situation of the recognized imaging space to the angle-of-view setting unit 272.
[0105] In step S2, the angle-of-view candidate setting unit 281 sets an angle-of-view candidate based on the situation of the imaging space. For example, the angle-of-view candidate setting unit 281 sets an angle-of-view candidate based on a main subject, a related subject, and a content of an imaging scene.
[0106] For example, in a case where the content of the imaging scene is a talk show program, an angle-of-view including a portion above a chest of a main person as a main subject (a half-body image), an angle-of-view including a combination of the main subject and each of the related subjects, and the like are set as the angle-of-view candidate.
[0107] For example, in a case where the content of the imaging scene is a live music, an angle-of-view including a portion above a waist of a main person as a main subject (a waist shot), an angle-of-view including a full body (a full-body image), an angle-of-view including a combination of the main subject and each of the related subjects, and the like are set as the angle-of-view candidate.
[0108] For example, in a case where the content of the imaging scene is a sports game, an angle-of-view including a full body of a main person as a main subject (a full-body image), an angle-of-view including a combination of the main subject and each of the related subjects, and the like are set as the angle-of-view candidate.
[0109] Figure 7 An example of setting of the angle-of-view candidate is illustrated. In this example, an example of a wide-angle image of a talk show program is schematically illustrated. This wide-angle image includes persons 301 to 304. Note that auxiliary lines superimposed on the persons 301 to 304 in this drawing indicate results of face recognition and skeleton recognition.
[0110] The person 301 stands near a right edge of the wide-angle image, and the persons 302 to 304 sit side by side in a range from near a center of the wide-angle image to a left edge.
[0111] Here, for example, it is assumed that the person 302 is speaking, and the person 303 is listening to the speech of the person 302. In this case, for example, the person 302 is recognized as a main subject, and the person 303 is recognized as a related subject. Then, for example, an angle-of-view candidate Ac1 including a portion above a chest of the person 302 and an angle-of-view candidate Ac2 including portions above waists of the person 302 and the person 303 are set.
[0112] The view angle candidate setting unit 281 supplies information on the set view angle candidate to the imaging view angle setting unit 282.
[0113] In step S3, the imaging view angle setting unit 282 calculates an image frame including all the view angle candidates. For example, the imaging view angle setting unit 282 calculates a minimum rectangular frame including all the view angle candidates as the image frame.
[0114] In step S4, the imaging view angle setting unit 282 adds a margin to the calculated image frame. For example, the imaging view angle setting unit 282 expands the image frame by adding a margin in at least one direction of the periphery of the calculated image frame, based on the motions of the main subject and the related subjects respectively. In this case, the margin in the direction in which the motions of the main subject and the related subjects are large becomes large, and the margin in the direction in which the motions of the main subject and the related subjects are small becomes small.
[0115] In step S5, the imaging view angle setting unit 282 determines whether the cutout size of the main view angle candidate is equal to or larger than a threshold value.
[0116] Specifically, the imaging view angle setting unit 282 selects a view angle candidate estimated to be the most important (hereinafter referred to as a main view angle candidate) from the view angle candidates based on the sizes, positions, postures, motions, and the like of the main subject and the related subjects, the content of the imaging scene, the use of the image, and the like. Here, as the use of the image, for example, television broadcasting, network distribution, production of video software, and the like are assumed.
[0117] Next, the imaging view angle setting unit 282 calculates the resolution (the number of pixels) of the main view angle candidate in a case where an image of the imaging view angle corresponding to the calculated image frame is captured by the PTZ camera 113.
[0118] Next, the imaging view angle setting unit 282 compares the calculated resolution with a predetermined threshold value. This threshold value varies depending on the use of the image, for example. For example, in a case where the use of the image is television broadcasting, the threshold value is set to 1920 pixels x 1080 pixels (FHD), and in a case where the use of the image is network distribution, the threshold value is set to 1280 pixels x 720 pixels (HD).
[0119] Then, in a case where the resolution of the main view angle candidate is smaller than the threshold value, the imaging view angle setting unit 282 determines that the cutout size of the main view angle candidate is smaller than the threshold value, and the process proceeds to step S6.
[0120] In step S6, the imaging view angle setting unit 282 excludes the view angle candidate closest to the edge of the image frame from among the view angle candidates other than the main view angle candidate.
[0121] Thereafter, the process returns to step S3, and the process of steps S3 to S6 is repeatedly executed until it is determined in step S5 that the cutout size of the main angle-of-view candidate is equal to or greater than the threshold value.
[0122] Thus, until the cutout size (resolution) of the main angle-of-view candidate becomes equal to or greater than the threshold value, the angle-of-view candidates other than the main angle-of-view candidate are sequentially deleted from the edge of the image frame, and the image frame becomes smaller. Therefore, the angle-of-view candidate to be included in the imaging angle of view is selected.
[0123] On the other hand, in step S5, in a case where the resolution of the main angle-of-view candidate is equal to or greater than the threshold value, the imaging angle-of-view setting unit 282 determines that the cutout size of the main angle-of-view candidate is equal to or greater than the threshold value, and the process proceeds to step S7.
[0124] In step S7, the imaging angle-of-view setting unit 282 sets the calculated image frame as the imaging angle of view. Therefore, a region in which a margin is provided around a rectangular region including the selected angle-of-view candidate is set as the imaging angle of view. The imaging angle-of-view setting unit 282 supplies information about the set imaging angle of view to the angle-of-view control unit 273. Further, the imaging angle-of-view setting unit 282 supplies the set imaging angle of view and information about the angle-of-view candidate included in the imaging angle of view to the angle-of-view control unit 273.
[0125] For example, in the example of Figure 7 , the imaging angle of view As including the angle-of-view candidate Ac1 and the angle-of-view candidate Ac2 and provided with a margin around the periphery is set.
[0126] In step S8, the angle-of-view control unit 273 determines whether or not to use the captured image of the PTZ camera 113. For example, in a case where a predetermined role is assigned to the captured image captured by the PTZ camera 113, for example, in a case where an image cut out from the captured image is output from the switcher 115 as an image for broadcasting, preview, or the like, the angle-of-view control unit 273 determines to use the captured image of the PTZ camera 113, and the process proceeds to step S9.
[0127] In step S9, the angle-of-view control unit 273 performs low-speed control of the PTZ camera 113 to realize the set imaging angle of view. Specifically, the angle-of-view control unit 273 drives the PTZ of the PTZ camera 113 at a gentle speed and adjusts the angle of view of the PTZ camera 113 to the set imaging angle of view.
[0128] Note that in this processing, the driving speed of the PTZ of the PTZ camera 113 is set based on, for example, the shutter speed of the PTZ camera 113, the allowable amount of motion blur, and the like. Further, the allowable amount of motion blur is set based on, for example, the content of the imaging scene (for example, sports relay, imaging in a studio, and the like), the use of the image (for example, television broadcast, web distribution, video software production, and the like), and the like. For example, in the case where the content of the imaging scene is a scene in which the motion of the subject is large (such as sports), the allowable amount of motion blur is set to a large value. On the other hand, for example, in the case where the motion of the subject is small (such as imaging in a studio), the allowable amount of motion blur is set to a small value.
[0129] Therefore, the angle of view of the PTZ camera 113 is set to an angle of view that includes all the selected angle of view candidates (hereinafter referred to as a full angle of view).
[0130] For example, as described above, in the example of FIG. 6, by setting the imaging angle of view As, as shown in FIG. 7, a full angle of view image including the person 302 and the person 303 is captured. Figure 7 Figure 8 Therefore, the angle of view of the PTZ camera 113 is set to an angle of view that includes all the selected angle of view candidates (hereinafter referred to as a full angle of view).
[0131] Further, even if the angle of view of the PTZ camera 113 is changed, motion blur occurring in the captured image being used is reduced.
[0132] Thereafter, the processing proceeds to step S11.
[0133] On the other hand, in step S8, in the case where no predetermined role is assigned to the image cut out from the captured image captured by the PTZ camera 113, for example, in the case where the image cut out from the captured image is not output from the switcher 115 as an image for broadcast, preview, or the like, the angle of view control unit 273 determines not to use the captured image of the PTZ camera 113, and the processing proceeds to step S10.
[0134] In step S10, the angle of view control unit 273 performs high-speed control of the PTZ camera 113 to achieve the set imaging angle of view. Specifically, the angle of view control unit 273 drives the PTZ of the PTZ camera 113 at high speed so that the angle of view of the PTZ camera 113 becomes the set imaging angle of view at the earliest. For example, the PTZ is driven at the maximum speed allowed by the mechanical limit of the PTZ camera 113.
[0135] Therefore, the angle of view of the PTZ camera 113 is quickly set to the full angle of view.
[0136] Thereafter, the processing proceeds to step S11.
[0137] In step S11, the cutout unit 263 cuts out the captured image. Specifically, the cutout unit 263 acquires captured image data (hereinafter referred to as full-view image data) captured with a full view from the PTZ camera 113. Then, the cutout unit 263 cuts out an image having a view corresponding to each view candidate from a full-view image corresponding to the full-view image data.
[0138] For example, as shown in Figure 9 , an image corresponding to the view candidate Ac1 of the person 302 and including a half-body image of the person 302 is cut out from the full-view image of the person 302. Figure 8 Figure 7
[0139] In this case, in a case where a plurality of view candidates are set, the cutout unit 263 cuts out view images corresponding to all the view candidates.
[0140] Further, the view of the cutout image does not necessarily have to match the corresponding view candidate completely. For example, the view of the cutout image can be adjusted so as to include a subject appropriately.
[0141] The cutout unit 263 transmits cutout image data corresponding to the cutout image to the switcher 115 via the communication unit 209.
[0142] Thereafter, the process returns to step S1, and the processing in steps S1 and subsequent steps is executed.
[0143] As described above, by effectively combining the PTZ method and the cutout method, it is possible to obtain an image having an appropriate view and image quality with a small number of imaging devices. That is, view candidates that can be used are predicted in advance, and imaging is performed at imaging views including all the predicted view candidates, so that it is possible to acquire an image having a necessary view at an appropriate timing. Further, the resolution of the main view candidate is set to be equal to or greater than a predetermined threshold, so that it is possible to obtain an image having good image quality.
[0144] <<3. Second Embodiment>>
[0145] Next, a second embodiment of the present technology will be described with reference to Figures 10 to 12 .
[0146] <Configuration of Information Processing System 401>
[0147] Figure 10 A configuration example of the information processing system 401 according to the second embodiment of the present technology is illustrated. Note that, in the drawing, portions corresponding to portions of the information processing system 101 in Figure 2 will be denoted by the same reference numerals, and the description thereof will be omitted as appropriate.
[0148] Figure 10 The information processing system 401 in Figure 2 differs from the information processing system 101 in
[0149] In the information processing system 401, the PTZ camera 113 captures both the wide-angle image and the full-view image. Then, the information processing apparatus 114 identifies a situation of the imaging space based on the wide-angle image or the full-view image captured by the PTZ camera 113 and the sound data, and controls the imaging angle of view of the PTZ camera 113.
[0150] Here, the wide-angle image is an image captured when the PTZ camera 113 is set to a wide angle of view. The wide angle of view is an angle of view from which the imaging space can be observed widely, and is, for example, an angle of view that maximizes the field of view of the PTZ camera 113. For example, the wide angle of view is an angle of view that allows a wide observation of an event occurring in the imaging space, and is an angle of view that includes many subjects (persons and objects) related to the event within a possible range.
[0151] Note that the angle of view at which the field of view is maximized is an angle of view at which the field of view is maximized within a predetermined setting range of the PTZ camera 113, and is not necessarily an angle of view at which the field of view of the PTZ camera 113 is mechanically maximized. For example, in a case where the setting range of the field of view of the PTZ camera 113 is set to a range smaller than the maximum value of the mechanical field of view of the PTZ camera 113, the angle of view at which the field of view is maximized within the setting range is set to the wide angle of view.
[0152] <Configuration example of information processing unit 451>
[0153] Figure 11 A configuration example of the information processing unit 451 of the second embodiment that illustrates a function to be realized by execution of a program by the CPU 201 of the information processing apparatus 114 is illustrated. Note that, in the drawing, portions corresponding to portions of the information processing unit 251 in Figure 3 will be denoted by the same reference numerals, and the description thereof will be appropriately omitted.
[0154] The information processing unit 451 is similar to the information processing unit 251 in that the calibration unit 261 and the cutout unit 263 are provided, and is different in that the imaging control unit 461 is provided instead of the imaging control unit 262. The imaging control unit 461 is similar to the imaging control unit 262 in that it includes the angle of view control unit 273, and is different from the imaging control unit 262 in that it includes the recognition unit 471 and the angle of view setting unit 472 instead of the recognition unit 271 and the angle of view setting unit 272. The angle of view setting unit 472 is similar to the angle of view setting unit 272 in that it includes the angle of view candidate setting unit 281, and is different from the angle of view setting unit 272 in that it includes the imaging angle of view setting unit 481 instead of the imaging angle of view setting unit 282.
[0155] The wide-angle camera 111 is not provided in the information processing system 401, and thus the calibration unit 261 calibrates only the PTZ camera 113.
[0156] The recognition unit 471 recognizes a situation of the imaging space based on a wide-angle image or a full-angle image captured by the PTZ camera 113 and sound collected by the microphone 112. The recognition unit 471 supplies information about the recognized situation of the imaging space to the angle of view setting unit 472.
[0157] The imaging angle of view setting unit 481 sets the imaging angle of view based on the angle of view candidate. Further, the imaging angle of view setting unit 481 sets the imaging angle of view to the wide angle of view at predetermined timing. The imaging angle of view setting unit 481 supplies information about the imaging angle of view to the angle of view control unit 273. Further, the imaging angle of view setting unit 481 supplies the imaging angle of view and information about the angle of view candidate included in the imaging angle of view to the cutout unit 263.
[0158] <Second Embodiment of the Angle of View Control Process>
[0159] Next, the angle of view control process to be executed by the information processing apparatus 114 according to the second embodiment will be described with reference to the flowchart in Figure 12 This process is started, for example, when imaging of the imaging space is started and is ended when the imaging of the imaging space is ended.
[0160] In step S101, the information processing unit 451 performs high-speed control of the PTZ camera 113 to achieve the wide angle of view. Specifically, the imaging angle of view setting unit 481 sets the imaging angle of view to the wide angle of view and supplies information about the set imaging angle of view to the angle of view control unit 273. The angle of view control unit 273 drives the PTZ of the PTZ camera 113 at high speed so that the angle of view of the PTZ camera 113 becomes the wide angle of view at the earliest.
[0161]
[0162] Accordingly, the angle of view of the PTZ camera 113 is set to a wide angle of view, and the PTZ camera 113 performs wide-angle imaging of the imaging space.
[0163] In step S102, the recognition unit 471 recognizes the situation of the imaging space. Specifically, the recognition unit 471 acquires wide-angle image data or full-view image data from the PTZ camera 113 and sound data from the microphone 112 via the communication unit 209. Then, the recognition unit 471 recognizes the situation of the imaging space on the basis of the wide-angle image data or full-view image data and the sound data by the similar process as in step S1. Figure 5
[0164] In step S103, the imaging angle of view setting unit 481 determines whether the image includes a main subject. In a case where the imaging angle of view setting unit 481 determines, on the basis of the recognition result of the situation of the imaging space, that the full-view image captured by the PTZ camera 113 includes a main subject, that is, in a case where it is determined that a main subject exists in the full-view image, the process proceeds to step S104.
[0165] Thereafter, in steps S104 to S109, the process similar to steps S2 to S7 in Figure 5 is performed. Accordingly, the imaging angle of view (full view) is set.
[0166] In step S110, the low-speed control of the PTZ camera 113 is performed to achieve the set imaging angle of view, similarly to the process of step S8 in Figure 5 . In other words, only the PTZ camera 113 is set as the imaging device in the information processing system 401, and the captured image of the PTZ camera 113 is always used, so that the angle of view of the PTZ camera 113 is changed at a low speed.
[0167] In step S111, the captured image is cut out similarly to the process in step S11 in Figure 5 .
[0168] In step S112, the imaging angle of view setting unit 481 determines whether a certain period of time has elapsed since the last wide-angle imaging. In a case where it is determined that a certain period of time has not elapsed since the last wide-angle imaging, the process returns to step S102. Thereafter, the process in step S102 and the subsequent steps is performed.
[0169] On the other hand, in a case where it is determined in step S112 that a certain period of time has elapsed since the last wide-angle imaging, the process proceeds to step S113.
[0170] Further, in step S103, in a case where it is determined that the full-view image captured by the PTZ camera 113 does not include a main subject, that is, in a case where it is determined that the main subject is not present in the full-view image, the processing of steps S104 to S112 is skipped, and the processing proceeds to step S113.
[0171] In step S113, the information processing unit 451 performs low-speed control of the PTZ camera 113 to achieve a wide viewing angle. Specifically, the imaging viewing angle setting unit 481 sets the imaging viewing angle to a wide viewing angle, and supplies information about the set imaging viewing angle to the viewing angle control unit 273. Similarly to the processing in step S9 in FIG. 8, Figure 5
[0172] Thereafter, the processing returns to step S102, and the processing in steps S102 and subsequent steps is performed.
[0173] As described above, since the PTZ method and the cutout method are effectively combined by means of only one PTZ camera 113, a captured image having an appropriate viewing angle and image quality can be obtained.
[0174] <<4. Modified example>>
[0175] Hereinafter, a modified example of the above-described embodiment of the present technology will be described.
[0176] <Modified example regarding the configuration of the information processing system>
[0177] For example, in the information processing system 101 of Figure 2 two or more wide-angle cameras 111 can be provided. In addition, it is also possible to provide two or more PTZ cameras 113. Thus, while the number of imaging devices increases, captured images having more types of viewing angles can be obtained at once.
[0178] Further, for example, in the information processing system 401 of Figure 10 two or more PTZ cameras 113 can be provided. Thus, while the number of imaging devices increases, images having more types of viewing angles can be obtained at once.
[0179] Further, for example, two or more microphones 112 can be provided in the information processing system 101 and the information processing system 401.
[0180] Further, for example, in the information processing system 101, some or all of the functions of the information processing device 114 (particularlyFigure 4 the function of the information processing unit 251 in the information processing system 401).
[0181] For example, the wide-angle camera 111 can perform the recognition processing of the situation of the imaging space. For example, the PTZ camera 113 can set the angle-of-view candidate and the imaging angle of view and control the angle of view. Further, for example, the PTZ camera 113 can also perform the recognition processing of the situation of the imaging space. Further, for example, the switcher 115 can include all the functions of the information processing device 114.
[0182] Further, for example, in the information processing system 401, some or all of the functions of the information processing device 114 (in particular, the functions of the information processing unit 251 in the information processing system 401) can be provided in the PTZ camera 113 or the switcher 115. Figure 11
[0183] For example, the PTZ camera 113 can perform the recognition processing of the situation of the imaging space. Further, for example, the PTZ camera 113 can also set the angle-of-view candidate and the imaging angle of view and control the angle of view. Further, for example, the switcher 115 can include all the functions of the information processing device 114.
[0184] Further, for example, the information processing device 114 can be applied to a server in cloud computing or the like, and the server can provide a service for controlling the angle of view of the PTZ camera 113.
[0185] <Modification Example Regarding the Method of Setting the Main Subject>
[0186] For example, it is also possible to recognize two or more subjects as the main subject.
[0187] Further, for example, the recognition result of the subject can be displayed on a display included in the output unit 207 of the information processing device 114, and the user can select the main subject using the input unit 206.
[0188] Further, in the processing of step S103 of the method of setting the main subject, Figure 12 in the processing of step S103 of the method of setting the main subject, the subject not included in the full-angle image can be recognized on the basis of information other than sound (for example, sensor data other than the full-angle image, and the like).
[0189] <Modification Example Regarding the Setting of the Angle-of-View Candidate>
[0190] For example, in a case where the captured image captured by the wide-angle camera 111 or the image cut out from the captured image is in good condition, the angle-of-view candidate similar to the angle of view of the image can be excluded.
[0191] Further, for example, in imaging in a studio or the like, in a case where the position of the subject is basically fixed, the user can set the angle-of-view candidate in advance.
[0192] Further, for example, the wide-angle image can be displayed on a display included in the output unit 207 of the information processing apparatus 114, the user can input the view angle candidate using the input unit 206, and the view angle candidate setting unit 281 can set the view angle candidate based on the user input.
[0193] <Modification example about setting an imaging view angle>
[0194] For example, the set view angle candidate can be displayed on a display included in the output unit 207 of the information processing apparatus 114, and the user can select a desired view angle candidate using the input unit 206. Then, the imaging view angle setting unit 282 or the imaging view angle setting unit 481 can set the imaging view angle including the view angle candidate selected by the user. Further, the user can select the main view angle candidate using a similar method.
[0195] Further, for example, the imaging view angle setting unit 282, the imaging view angle setting unit 481, or the user can select a plurality of main view angle candidates and set the imaging view angle so that the cutout size of all the main view angle candidates becomes equal to or greater than the threshold value.
[0196] <Modification example about a cutout of a captured image>
[0197] For example, the cutout unit 263 can estimate the view angle candidate that is most likely to be used from among the view angle candidates included in the imaging view angle, and cut out the image having the view angle corresponding to the estimated view angle candidate.
[0198] Further, for example, the cutout unit 263 can estimate the view angle that is likely to be used in the full view angle image regardless of the view angle candidate, and cut out the image having the estimated view angle.
[0199] Further, for example, the full view angle captured image and the view angle corresponding to the respective candidate of the view angle can be displayed on a display included in the output unit 207 of the information processing apparatus 114, so that the user can select a desired view angle using the input unit 206, and the image of the selected view angle can be cut out.
[0200] <Modification example about PTZ control of the PTZ camera 113>
[0201] In order to highly accurately control the PTZ of the PTZ camera 113, it is desirable to calculate the PTZ value (pan angle, tilt angle, and zoom ratio) of the PTZ camera 113 using three-dimensional information including the position of the subject in the depth direction.
[0202] For example, in the first embodiment, the three-dimensional information can be obtained by setting two or more wide-angle cameras 111 using a triangulation method.
[0203] Further, for example, in a case where there is one wide-angle camera 111, three-dimensional information can be obtained by using a camera including a depth sensor and a camera including a phase difference image for the wide-angle camera 111. Note that the method of the depth sensor is not particularly limited, and a method such as a time-of-flight (ToF) method or a structured light method can be used.
[0204] Further, for example, in a case where there is one wide-angle camera 111, a method of estimating the position of each subject in the depth direction based on a wide-angle image using a method such as deep learning can be employed.
[0205] Further, for example, in the first embodiment, in a case where the wide-angle camera 111 and the PTZ camera 113 are installed at substantially the same position, the PTZ value of the PTZ camera 113 can be directly estimated based on a two-dimensional wide-angle image captured by the wide-angle camera 111.
[0206] Further, for example, a sensor (for example, an ultra-wideband (UWB) sensor, an infrared sensor, or the like) can be attached to a person or the like who can be a subject, and the position of each subject in the depth direction can be recognized based on data from the sensor.
[0207] Note that even if the position of each subject in the depth direction is not recognized, for example, control of the PTZ of the PTZ camera 113 can be accelerated by using a geometric constraint using epipolar lines.
[0208] <Other Modification Examples>
[0209] In the second embodiment, the timing at which a wide angle of view is set is not necessarily every constant time, and can be, for example, at the time when a predetermined condition is satisfied or at other times.
[0210] Further, the present technology can also be applied, for example, to a case of imaging an imaging space in which no special event is performed. For example, the present technology can also be applied to a case of imaging an outdoor landscape or a case of imaging a predetermined monitoring area.
[0211] <<5. Others>>
[0212] <Configuration Example of Computer>
[0213] The series of processes described above can be executed by hardware or software. In a case where the series of processes is executed by software, a program configuring the software is installed in a computer. Here, the computer includes, for example, a computer incorporated in a dedicated hardware, a general-purpose personal computer capable of executing various functions by installing various programs, and the like.
[0214] Note that a program executed by a computer can be a program in which processing is performed in a time series in the order described in this specification, or can be a program in which processing is performed in parallel or at necessary timing such as at the time of a call.
[0215] Further, in this specification, a system refers to a collection of a plurality of components (devices, modules (parts), and the like), and whether all components are in the same housing is irrelevant. Therefore, a plurality of devices housed in separate housings and connected via a network and a device in which a plurality of modules are housed in one housing are both systems.
[0216] Further, embodiments of the present technology are not limited to the above-described embodiments, and various modifications can be made without departing from the spirit of the present technology.
[0217] For example, the present technology can have a configuration of cloud computing in which one function is shared and cooperatively processed by a plurality of devices via a network.
[0218] Further, each step described in the above-described flowchart can be executed by one device, or can be shared and executed by a plurality of devices.
[0219] Further, in a case where a plurality of processes are included in one step, the plurality of processes included in one step can be executed by one device, or can be shared and executed by a plurality of devices.
[0220] <Configuration Combination Example>
[0221] The present technology can also have the following configurations. (1)
[0223] An information processing apparatus comprising:
[0224] a view angle candidate setting unit configured to set a plurality of view angle candidates in accordance with a captured image range that can be captured by a first imaging apparatus with respect to a predetermined imaging space; and
[0225] an imaging view angle setting unit configured to set an imaging view angle of the first imaging apparatus based on the plurality of view angle candidates. (2)
[0227] The information processing apparatus according to (1), further comprising
[0228] a recognition unit configured to recognize a situation of the imaging space based on a captured image obtained by imaging the imaging space,
[0229] wherein the view angle candidate setting unit sets the view angle candidate based on the situation of the imaging space. (3)
[0231] The information processing apparatus according to (2),
[0232] wherein the recognition unit recognizes, as the situation of the imaging space, a main subject being a main subject in the imaging space and a related subject related to the main subject, and
[0233] The angle-of-view candidate setting unit sets the angle-of-view candidate based on the recognized main subject and related subject. (4)
[0235] The information processing apparatus according to (3),
[0236] wherein the recognition unit recognizes, as the situation of the imaging space, a content of a scene in the imaging space, and
[0237] The angle-of-view candidate setting unit sets the angle-of-view candidate further based on the content of the scene. (5)
[0239] The information processing apparatus according to any one of (2) to (4),
[0240] wherein the recognition unit recognizes the situation of the imaging space based on a captured image captured by a first imaging device, and
[0241] The imaging angle-of-view setting unit sets the imaging angle-of-view to a wide angle-of-view having a largest field of view at a predetermined timing. (6)
[0243] The information processing apparatus according to (5),
[0244] wherein, in a case where a main subject being a main subject in the imaging space is not present in the captured image captured by the first imaging device, the imaging angle-of-view setting unit sets the imaging angle-of-view to a wide angle-of-view. (7)
[0246] The information processing apparatus according to any one of (2) to (4),
[0247] wherein the recognition unit recognizes the situation of the imaging space based on a captured image captured by a second imaging device. (8)
[0249] The information processing apparatus according to any one of (1) to (7),
[0250] wherein the imaging angle-of-view setting unit sets the imaging angle-of-view to include a plurality of angle-of-view candidates. (9)
[0252] The information processing apparatus according to (8),
[0253] The imaging view setting unit selects a view candidate to be included in the imaging view so that a resolution of a main view candidate is equal to or greater than a predetermined threshold, the main view candidate being estimated to be important among the plurality of view candidates. (10)
[0255] The information processing apparatus according to (9), further comprising
[0256] The recognition unit is configured to recognize a situation of the imaging space based on a captured image obtained by imaging the imaging space,
[0257] The view candidate setting unit selects a main view candidate from the plurality of view candidates based on at least one of the situation of the imaging space or a use of the captured image captured by the first imaging apparatus. (11)
[0259] The information processing apparatus according to any one of (8) to (10),
[0260] The imaging view setting unit sets, as the imaging view, an area in which a rectangular area including the plurality of view candidates is provided with a margin in at least one direction. (12)
[0262] The information processing apparatus according to any one of (8) to (11), further comprising
[0263] The cutout unit is configured to cut out, from the captured image captured by the first imaging apparatus, an image of a view corresponding to at least one of the view candidates. (13)
[0265] The information processing apparatus according to (12),
[0266] The cutout unit cuts out, from the captured image captured by the first imaging apparatus, images of a plurality of views respectively corresponding to the view candidates. (14)
[0268] The information processing apparatus according to any one of (1) to (13), further comprising
[0269] The view control unit is configured to control panning, tilting, and zooming of the first imaging apparatus to realize the set imaging view. (15)
[0271] The information processing apparatus according to (14),
[0272] The view control unit controls a driving speed of the panning, tilting, and zooming of the first imaging apparatus based on whether a predetermined role is assigned to the captured image captured by the first imaging apparatus. (16)
[0274] The information processing apparatus according to one of (1) to (15),
[0275] wherein the information processing apparatus is provided in the first imaging apparatus. (17)
[0277] An information processing method, comprising:
[0278] by the information processing apparatus,
[0279] setting a plurality of view angle candidates according to a captured image range that can be captured by the imaging apparatus with respect to a predetermined imaging space; and
[0280] setting an imaging view angle of the imaging apparatus based on the plurality of view angle candidates. (18)
[0282] A program for causing a computer to execute the following processing:
[0283] setting a plurality of view angle candidates according to a captured image range that can be captured by the imaging apparatus with respect to a predetermined imaging space; and
[0284] setting an imaging view angle of the imaging apparatus based on the plurality of view angle candidates.
[0285] Note that the effects described in this specification are merely examples and are not limited, and other effects can be provided.
[0286] List of Reference Signs
[0287] 101 information processing system
[0288] 111 wide-angle camera
[0289] 112 microphone
[0290] 113 PTZ camera
[0291] 114 information processing apparatus
[0292] 115 switcher
[0293] 201 CPU
[0294] 251 information processing unit
[0295] 261 calibration unit
[0296] 262 imaging control unit
[0297] 263 cut-out unit
[0298] 271 recognition unit
[0299] 272 view angle setting unit
[0300] 273 view angle control unit
[0301] 281 view angle candidate setting unit
[0302] 282 imaging view angle setting unit
[0303] 401 information processing system
[0304] 451 information processing unit
[0305] 461 imaging control unit
[0306] 471 recognition unit
[0307] 472 view angle control unit
[0308] 481 imaging view angle setting unit
Claims
1. An information processing apparatus comprising: a view angle candidate setting unit configured to set a plurality of view angle candidates in accordance with a captured image range that can be captured by a first imaging apparatus with respect to a predetermined imaging space; and an imaging view angle setting unit configured to set an imaging view angle of the first imaging apparatus based on the plurality of view angle candidates; and a view angle control unit configured to control a pan, tilt, and zoom of the first imaging apparatus to realize the set imaging view angle, wherein the view angle control unit controls the pan, tilt, and zoom of the first imaging apparatus at a lower driving speed in a case where a predetermined role is assigned to the captured image captured by the first imaging apparatus than in a case where no predetermined role is assigned to the captured image captured by the first imaging apparatus. 2.The information processing apparatus according to claim 1, further comprising an identification unit configured to identify a situation of the imaging space based on the captured image obtained by imaging the imaging space, wherein the view angle candidate setting unit sets the view angle candidates based on the situation of the imaging space. 3.The information processing apparatus according to claim 2, wherein the identification unit identifies a main subject that is a main subject in the imaging space and a related subject that is related to the main subject as the situation of the imaging space, and the view angle candidate setting unit sets the view angle candidates based on the identified main subject and related subject. 4.The information processing apparatus according to claim 3, wherein the identification unit identifies a content of a scene in the imaging space as the situation of the imaging space, and the view angle candidate setting unit further sets the view angle candidates based on the content of the scene. 5.The information processing apparatus according to claim 2, wherein the identification unit identifies the situation of the imaging space based on the captured image captured by the first imaging apparatus, and the imaging view angle setting unit sets the imaging view angle to a wide view angle having a maximum field of view at a predetermined timing. 6.The information processing apparatus according to claim 5, wherein in a case where a main subject that is a main subject in the imaging space is not present in the captured image captured by the first imaging apparatus, the imaging view angle setting unit sets the imaging view angle to the wide view angle. 7.The information processing apparatus according to claim 2, wherein the identification unit identifies the situation of the imaging space based on a captured image captured by a second imaging apparatus. 8.The information processing apparatus according to claim 1, wherein the imaging view angle setting unit sets the imaging view angle to include the plurality of view angle candidates. 9.The information processing apparatus according to claim 8, wherein the imaging view angle setting unit selects the view angle candidates to be included in the imaging view angle so that a resolution of a main view angle candidate is equal to or greater than a predetermined threshold, the main view angle candidate being estimated to be important among the plurality of view angle candidates. 10.The information processing apparatus according to claim 9, further comprising an identification unit configured to identify a situation of the imaging space based on the captured image obtained by imaging the imaging space, The view angle candidate setting unit selects a main view angle candidate from among the plurality of view angle candidates based on at least one of a situation of the imaging space or a use of the captured image captured by the first imaging device.
11. The information processing apparatus according to claim 8, The imaging view angle setting unit sets, as the imaging view angle, a region in which a rectangular region including the plurality of view angle candidates is provided with a margin in at least one direction.
12. The information processing apparatus according to claim 8, further comprising The cutout unit is configured to cut out, from the captured image captured by the first imaging device, an image of a view angle corresponding to at least one of the view angle candidates.
13. The information processing apparatus according to claim 12, The cutout unit cuts out, from the captured image captured by the first imaging device, images of a plurality of view angles corresponding to the plurality of view angle candidates, respectively.
14. The information processing apparatus according to claim 1, The information processing apparatus is provided in the first imaging device.
15. An information processing method comprising: by an information processing apparatus, setting a plurality of view angle candidates in accordance with a range of a captured image that can be captured by an imaging device with respect to a predetermined imaging space; setting an imaging view angle of the imaging device based on the plurality of view angle candidates; and controlling pan, tilt, and zoom of the first imaging device to achieve the set imaging view angle, wherein the pan, tilt, and zoom of the first imaging device are controlled at a lower driving speed in a case where a predetermined role is assigned to the captured image captured by the first imaging device than in a case where no predetermined role is assigned to the captured image captured by the first imaging device.
16. A computer program product storing a program for causing a computer to execute the following processing: setting a plurality of view angle candidates in accordance with a range of a captured image that can be captured by an imaging device with respect to a predetermined imaging space; setting an imaging view angle of the imaging device based on the plurality of view angle candidates; and controlling pan, tilt, and zoom of the first imaging device to achieve the set imaging view angle, wherein the pan, tilt, and zoom of the first imaging device are controlled at a lower driving speed in a case where a predetermined role is assigned to the captured image captured by the first imaging device than in a case where no predetermined role is assigned to the captured image captured by the first imaging device.
Citation Information
Patent Citations
Imaging device, imaging method, display device, and display method
CN110022431A
Camera controller and control program
JP2007134845A