Information processing apparatus, imaging apparatus, system, information processing method, and program
The information processing system helps photographers at events by identifying and directing them to areas of interest based on image analysis and attributes, addressing the challenge of missing notable scenes.
Patent Information
- Application Number
- JP2024103025
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-06-26
- Publication Date
- 2026-01-15
AI Technical Summary
Photographers at events like sporting events or concerts may miss highly noticeable scenes because they cannot determine where other spectators are photographing, leading to dissatisfaction.
An information processing system that includes an overhead camera and multiple photographing devices, which generates and transmits information on areas of interest based on image analysis and photographer attributes, allowing photographers to know where others are capturing notable moments.
Enables photographers to identify and capture notable scenes by providing direction and attention level information for areas of interest, enhancing the photography experience.
Smart Images

Figure 2026004929000001_ABST
Abstract
Description
[Technical Field]
[0001] The present disclosure relates to methods for presenting information to a photographer. [Background technology]
[0002] 2. Description of the Related Art Methods for supporting a photographer taking pictures using a photographing device are known.
[0003] Patent Document 1 discloses a method in which a photographer has a person he or she wishes to photograph carry an IC tag in advance, and provides the photographer with location information of the person based on information transmitted from the IC tag. [Prior art documents] [Patent documents]
[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-66963 Summary of the Invention [Problem to be solved by the invention]
[0005] For example, when a spectator at an event venue such as a sporting event or concert takes a photograph, the photographer may want to know the area where a highly noticeable event that other spectators at the event venue are photographing is occurring. However, with the method of Patent Document 1, the photographer cannot know the area where other spectators are photographing. For this reason, with the method of Patent Document 1, the photographer may miss a highly noticeable scene while photographing, which may cause dissatisfaction, such as a lack of a sense of unity. [Means for solving the problem]
[0006] The information processing device disclosed herein is characterized by having a generation means for generating information for a first photographer in a specific space to photograph an area of interest being photographed by a second photographer different from the first photographer in the specific space, based on images captured by a first photographing device used by the first photographer and a second photographing device used by the second photographer, and a transmission means for transmitting the information so that the content of the information is notified to the first photographer via the first photographing device. [Effects of the Invention]
[0007] According to the techniques of the present disclosure, a photographer can know the area that another photographer is photographing. [Brief explanation of the drawings]
[0008] [Figure 1] FIG. 1 is a schematic diagram showing an example of a system configuration. [Figure 2] FIG. 2 is a block diagram showing an example of the hardware configuration of each device. [Figure 3] FIG. 2 is a block diagram showing an example of the functional configuration of each device. [Figure 4] FIG. 10 is a diagram showing an example of a photographer attribute input screen. [Figure 5] FIG. 4 is a diagram showing an example of overhead camera image data. [Figure 6] FIG. 2 is a diagram showing an example of captured camera image data. [Figure 7] 10 is a flowchart for explaining the flow of a photographing process in the overhead camera. [Figure 8] 10 is a flowchart for explaining the flow of a photographing process in the photographing camera. [Figure 9] 10 is a flowchart for explaining a process for generating information for photographing an area of interest. [Figure 10] FIG. 2 is a diagram showing an example of a photographing area and a region of interest. [Figure 11] 10 is a flowchart illustrating a process for identifying an attention area. [Figure 12] FIG. 10 is a diagram for explaining a method for specifying an attention area. [Figure 13]FIG. 4 is a diagram showing an example of a screen displayed on a display unit of the photographing camera. [Figure 14] 10 is a flowchart for explaining the flow of display processing in the photographing camera. DETAILED DESCRIPTION OF THE INVENTION
[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that the configurations shown in the following embodiments are merely examples, and the technical scope of the present disclosure is not limited to only those configurations.
[0010] <Embodiment 1> [System Configuration] 1 is a schematic diagram showing the configuration of an information processing system according to an embodiment of the present invention. The information processing system includes an overhead camera 101, photographing cameras 102 to 104, and an information processing device 110.
[0011] The overhead camera 101 is a photographing device that is installed in a space such as a venue where an event such as a sporting event or a concert is held. The overhead camera 101 is used to identify the photographing area of the photographing cameras 102 to 104, which will be described later. Therefore, the angle of view of the overhead camera 101 is set to photograph at a wider angle than the angles of view of the photographing cameras 102 to 104, for example. Furthermore, the overhead camera 101 is preferably installed so that it photographs from the same direction as the photographing cameras 102 to 104 in the photographing area.
[0012] Cameras 102, 103, and 104 are photographing devices, and camera 102 is a photographing device used by photographer 105. Photographer 105 is a photographer who operates camera 102 to take photographs. Similarly, camera 103 is a photographing device operated by photographer 106, and camera 104 is a photographing device operated by photographer 107. Photographers 105 to 107 are spectators who have come to watch sports, a concert, or the like in the space where overhead camera 101 is installed. Note that, for simplicity's sake, FIG. 1 illustrates an example in which there is one overhead camera and three photographing cameras, but there may be multiple overhead cameras, or the number of photographing cameras may be two or more than three.
[0013] The overhead camera 101 and the photographing cameras 102 to 104 are connected to an information processing device 110 via a network 109. The network 109 is the Internet, but is not limited to this and may be other types of networks such as a local area network (LAN) or a wide area network (WAN).
[0014] The information processing device 110 identifies the shooting area and the area of interest of each of the shooting cameras 102 to 104 connected via the network 109 from the results of shooting by the cameras. The shooting area refers to the area of the angle of view (field of view) captured by each of the cameras 102 to 104. The area of interest refers to an area of high interest in the shooting area of the overhead camera 101, and is determined based on areas where the shooting areas of the cameras overlap. Details of how the shooting area and the area of interest are identified will be described later.
[0015] The information processing device 110 transmits information to each of the photographing cameras 102-104 so that the photographers 105-107 of the photographing cameras 102-104 can photograph the area of interest. The photographing cameras 102-104 notify the photographers 105-107 of the received information for photographing the area of interest.
[0016] [Hardware configuration of overhead camera] FIG. 2 is a block diagram showing an example of the hardware configuration of each device constituting the information processing system of FIG.
[0017] The overhead camera 101 includes a CPU 201, a ROM 202, a RAM 203, a storage medium 204, an imaging unit 205, a power supply unit 206, and a communication unit 207, and each of these components is connected via a bus so as to be able to communicate with each other.
[0018] The CPU 201 is a control unit having at least one processor or circuit, and controls the overhead camera 101 as a whole.
[0019] The ROM 202 is an electrically erasable and recordable memory, and stores constants, programs, etc. for the operation of the CPU 201. In this embodiment, the programs include computer programs for executing various flowcharts described below.
[0020] The RAM 203 is used to expand constants and variables for the operation of the CPU 201, programs read from the ROM 202, and the like.
[0021] The storage medium 204 is a recording medium such as a memory card for recording images captured by the overhead camera 101, and is made up of a semiconductor memory or the like.
[0022] The image capturing unit 205 is an image capturing element that is configured with a CCD, CMOS element, etc. that converts an optical image into an electrical signal. The image capturing unit 205 also has multiple microlenses on the image capturing sensor surface, and is configured to enable distance measurement of the subject using phase difference.
[0023] The power supply unit 206 is a means for supplying power to the overhead camera 101. The power supply unit 206 may be configured to be powered by a built-in battery such as a lithium ion battery, a removable portable battery, or an AC power source.
[0024] The communication unit 207 is an interface for communicating with an external device such as a network device or a USB device, and performs data communication via a network or sending and receiving data to and from the external device.
[0025] [Camera hardware configuration] Each of the photographing cameras 102 to 104 has a CPU 211, ROM 212, RAM 213, storage medium 214, photographing unit 215, power supply unit 216, communication unit 217, display unit 218, and input unit 219, and each component is connected via a bus in a communicable state. The hardware configuration will be explained below using the photographing camera 102 as a representative of the photographing cameras 102 to 104.
[0026] The display unit 218 is configured with a liquid crystal monitor or the like, and displays an image showing the shooting area currently being shot by the shooting unit 215. The display unit 218 also functions as a notification unit that displays a screen to notify the photographer 105. The input unit 219 is an operation unit configured with a touch panel, button switches, etc., and accepts input from the photographer 105. A keyboard, mouse, etc. may also be connected as an external device.
[0027] The CPU 211, ROM 212, RAM 213, storage medium 214, image capturing unit 215, power supply unit 216, and communication unit 217 are similar to the CPU 201, ROM 202, RAM 203, storage medium 204, image capturing unit 205, power supply unit 206, and communication unit 207 of the overhead-view camera 101. The storage medium 214 records images captured by the image capturing camera 102. The power supply unit 216 serves as a means for supplying power to the image capturing camera 102. The CPU 211 also operates as a display control unit that controls the display unit 218 and an operation control unit that controls the input unit 219.
[0028] [Hardware configuration of information processing device] The information processing device 110 includes a CPU 221, a ROM 222, a RAM 223, a storage medium 224, a power supply unit 226, a communication unit 227, a display unit 228, and an input unit 229, and each component is connected via a bus in a communicable state.
[0029] The CPU 221, ROM 222, RAM 223, storage medium 224, power supply unit 226, and communication unit 227 are similar to the CPU 201, ROM 202, RAM 203, storage medium 204, power supply unit 206, and communication unit 207. The display unit 228 and input unit 229 are similar to the display unit 218 and input unit 219, and therefore their description will be omitted. The power supply unit 226 is a means for supplying power to the information processing device 110.
[0030] At least one of the display unit 228 and the input unit 229 may exist as a separate device outside the information processing device 110. The CPU 221 operates as a display control unit that controls the display unit 228 and an operation control unit that controls the input unit 229.
[0031] [Functional configuration of overhead camera] FIG. 3 is a block diagram showing an example of the functional configuration of each device constituting the information processing system of FIG.
[0032] The overhead camera 101 includes a captured image acquisition unit 301 , a position information acquisition unit 302 , a time acquisition unit 303 , and a transmission / reception unit 304 .
[0033] The captured image acquisition unit 301 acquires data of the captured image captured by the imaging unit 205 of the overhead camera 101. The acquired captured image data is transmitted to the information processing device 110 via the transmission / reception unit 304.
[0034] The position information acquisition unit 302 estimates the position of the overhead camera 101 and acquires the resulting position information of the overhead camera 101. The position information is transmitted to the information processing device 110. In this embodiment, the position is estimated by receiving the position information from the transmission / reception unit 304. The position information is, for example, position information obtained using a GPS. Note that the method of estimating the position is not limited to a method using a GPS, and other methods such as three-point positioning using a beacon or position input by the photographer may also be used. Furthermore, the position information synchronized with the timing of acquisition of the captured image by the captured image acquisition unit 301 is transmitted to the information processing device 110.
[0035] The time acquisition unit 303 acquires time information. In this embodiment, the time information is acquired from the transmission / reception unit 304 using GPS. The time acquisition method is not limited to a method using GPS, and the time information may be acquired using an RTC (real-time clock) or the like. Furthermore, the time information synchronized with the timing of acquisition of the captured image by the captured image acquisition unit 301 is transmitted to the information processing device 110.
[0036] The transmitting / receiving unit 304 performs data communication via a network or transmits and receives data to and from an external device.
[0037] [Camera function configuration] The photographing cameras 102 to 104 each have a photographed image acquisition unit 311, a location information acquisition unit 312, a time acquisition unit 313, a transmission / reception unit 314, a photographer attribute acquisition unit 315, and an attention area information display unit 316. Below, the functional configuration will be explained using the photographing camera 102 as a representative of the photographing cameras 102 to 104.
[0038] The captured image acquisition unit 311, location information acquisition unit 312, time acquisition unit 313, and transmission / reception unit 314 have the same functional units as the captured image acquisition unit 301, location information acquisition unit 302, time acquisition unit 303, and transmission / reception unit 304 of the overhead camera 101, so their explanation will be omitted.
[0039] The photographer attribute acquisition unit 315 acquires the attributes (photographer attributes) of the photographer 105 of the photographing camera 102 based on the content input by the photographer via the input unit 219 of the photographing camera 102. The photographer attributes are used to determine an area of interest based on the photographing results of other photographers who have the same photographer attributes.
[0040] Fig. 4 is a diagram showing an example of a photographer attribute input screen 401, which is a screen for inputting photographer attributes and is displayed on the display unit 218 of each of the shooting cameras 102 to 104. The photographer attribute input screen 401 in Fig. 4 is a photographer attribute input screen that is displayed when photographers 105 to 107 are at the venue of a live music event and are spectators of the live music event. Each of the photographers 105 to 107 selects and answers the relevant item from the questions on the photographer attribute input screen 401 via the input unit 219, and the photographer attribute acquisition unit 315 acquires the photographer attributes.
[0041] In this embodiment, the photographer attributes are described as the photographer's hobbies and preferences. For this reason, the photographer attribute input screen 401 in FIG. 4 includes "facial expression," "dance," and "production" as items that are important when watching a live performance. In the example of FIG. 4, "dance" is selected. For this reason, when the photographer attribute input screen 401 in FIG. 4 is the screen displayed on the display unit 218 of the shooting camera 102, pressing the confirm button causes the photographer attribute acquisition unit 315 of the shooting camera 102 to acquire "dance" as the photographer attribute of the photographer 105. In this embodiment, the photographer attributes are attributes related to the photographer's hobbies and preferences, but the photographer attributes are not limited to these. Other photographer attributes may also be, for example, the photographer's age, gender, etc.
[0042] The photographing cameras 102-104 in this embodiment are assumed to be photographing cameras loaned to photographers 105-107 at the event venue. For this reason, when the photographing cameras 102-104 are started up, a photographer attribute input screen 401 of FIG. 4 is displayed at the time of start-up, which is set in advance according to the content of the event. Note that the photographing cameras 102-104 may be photographing cameras owned by the photographers 105-107. In that case, for example, when the photographing cameras 102-104 are started up, a screen that allows the user to select what kind of scene they will be shooting is displayed on the display unit 218. Then, when the photographer selects "live viewing," the photographer attribute input screen 401 of FIG. 4 may be displayed.
[0043] The attention area information display unit 316 performs control to display the contents of information generated by a display information generation unit 328 of the information processing device 110, which will be described later, on the display unit 218. Details will be described later.
[0044] [Functional configuration of information processing device] The information processing device 110 has a transmitting / receiving unit 324, a shooting area specifying unit 325, an attention area specifying unit 326, an attention level determining unit 327, and a display information generating unit 328. The function of the transmitting / receiving unit 324 is similar to that of the transmitting / receiving unit 304, and therefore description thereof will be omitted.
[0045] The photographing area specifying unit 325 uses the overhead camera image data 331 and photographing camera image data 332 stored in the storage unit 321 to specify the photographing area, which is the range photographed by each of the photographing cameras 102 to 104.
[0046] The attention area specifying unit 326 specifies an attention area based on the number of overlaps of the shooting areas of the shooting cameras 102 to 104 specified by the shooting area specifying unit 325. Details will be described later.
[0047] The attention level determination unit 327 determines the attention level of the attention area identified by the attention area identification unit 326. Details will be described later.
[0048] The display information generation unit 328 generates information for photographing the attention area based on the shooting area of each of the shooting cameras 102 to 104 identified by the shooting area identification unit 325, the attention area identified by the attention area identification unit 326, and the attention level calculated by the attention level determination unit 327.
[0049] The information for capturing an image of the region of interest is, for example, at least one of the image capturing direction to the region of interest, the zoom direction to the region of interest, and the attention level of the region of interest, as will be described in detail later.
[0050] 3 is realized by the CPU of each device executing a predetermined program, but is not limited to this. Other hardware, such as a graphics processing unit (GPU) or a field programmable gate array (FPGA), may also be used to speed up calculations. Each functional unit may be realized by a combination of software and hardware, such as a dedicated IC, or some or all of the functions may be realized solely by hardware.
[0051] [About overhead camera image data and shooting camera image data] The information processing device 110 has a storage unit 321 that stores overhead camera image data 331 and captured camera image data 332. The storage unit 321 may be included in, for example, the ROM 222 or the storage medium 224, or may be included in an external device that can be connected to the information processing device 110 via a network or the like.
[0052] 5 is a diagram illustrating overhead camera image data 331 stored in storage unit 321. The overhead camera 101 captures video, and overhead camera image data 331 will be described as data of frames of video captured by overhead camera 101. Video is an image made up of multiple frames.
[0053] The image ID column in FIG. 5 holds a unique value (image ID) that can identify the stored overhead camera image data. The overhead camera ID column holds a unique value (overhead camera ID) that can identify the overhead camera 101 that took the image to obtain the overhead camera image data indicated by the image ID. The image data binary column holds identification information for binary data that represents the captured image of the overhead camera image data indicated by the image ID. The shooting position column holds information on the position where the overhead camera 101 took the image to obtain the overhead camera image data indicated by the image ID. The shooting time column holds information on the date and time when the image was taken to obtain the overhead camera image data indicated by the image ID. In the table in FIG. 5, the row that holds the overhead camera image data indicated by the image ID holds the overhead camera ID, image data binary, shooting position, and shooting time, which allow these to be managed in association with each other.
[0054] 6 is a diagram illustrating the photographic camera image data 332 stored in the storage unit 321. The photographic cameras 102 to 104 capture video, and the photographic camera image data 332 will be described as data of frames of video captured by the photographic cameras 102 to 104.
[0055] The image ID column in FIG. 6 holds a unique value (image ID) capable of identifying the stored photographic camera image data. The photographic camera ID column holds a unique value (photographing camera ID) capable of identifying the photographic camera that took the image to obtain the photographic camera image data indicated by the image ID. The image data binary column holds identification information of binary data representing the photographed image in the photographic camera image data indicated by the image ID. The photographing location column holds information on the location at which the photographic camera took the image to obtain the photographic camera image data indicated by the image ID. The photographing time column holds information on the date and time at which the image was taken to obtain the photographic camera image data indicated by the image ID. The photographer attribute column holds photographer attributes acquired by the photographer attribute acquisition unit 315 of the photographic camera that took the image to obtain the photographic camera image data indicated by the image ID. In the table in FIG. 6, the row holding the photographic camera image data indicated by the image ID holds the photographic camera ID, image data binary, photographing location, photographing time, and photographer attribute, which are managed in association with each other.
[0056] [About image data transmission processing] The process of transmitting image data from the overhead camera 101 or the photographing cameras 102 to 104 to the information processing device 110 will be described.
[0057] Fig. 7 is a flowchart for explaining the transmission process of captured images in the overhead camera 101. The series of processes shown in the flowchart in Fig. 7 are performed by the CPU 201 of the overhead camera 101 expanding program code stored in the ROM 202 into the RAM 203 and executing it. Also, some or all of the functions of the steps in Fig. 7 may be realized by hardware such as an ASIC or electronic circuit. The symbol "S" in the explanation of each process indicates a step in the flowchart, and this also applies to subsequent flowcharts.
[0058] In S701, the captured image acquisition unit 301 acquires data of the captured image captured by the overhead camera 101. In S701, for example, data of one frame of the captured image is acquired. Data of several frames of the captured image may also be acquired.
[0059] In S702, the position information acquisition unit 302 acquires information about the shooting position of the overhead camera 101 when the overhead camera 101 captured the image to obtain the captured image obtained in S701. In addition, the time acquisition unit 303 acquires information about the shooting time, which is the time when the image was captured to obtain the captured image obtained in S701.
[0060] In S703, the transmitter / receiver 304 transmits the data of the captured image acquired in S701 and the information on the shooting position and shooting time acquired in S702 to the information processing device 110. The transmitted data is received and stored as overhead camera image data 331 in the information processing device 110.
[0061] In S704, the captured image acquisition unit 301 determines whether the user has instructed to end image capture. If the captured image acquisition unit 301 determines that the user has not instructed to end image capture (NO in S704), the process returns to S701 and acquires captured image data for the next frame. If the captured image acquisition unit 301 determines that the user has instructed to end image capture (YES in S704), the process ends in the flowchart of FIG.
[0062] Fig. 8 is a flowchart for explaining the transmission process of captured images in the photographic cameras 102 to 104. The process of the flowchart in Fig. 8 is performed by each of the photographic cameras 102 to 104. The series of processes shown in the flowchart in Fig. 8 are performed by the CPU 211 of each of the photographic cameras 102 to 104 by loading program code stored in ROM 212 into RAM 213 and executing it. Furthermore, some or all of the functions of the steps in Fig. 8 may be realized by hardware such as an ASIC or electronic circuit. The following description will be given assuming that the flowchart in Fig. 8 is executed by the photographic camera 102.
[0063] In S801, the photographer attribute acquisition unit 315 acquires the photographer attribute input by the user.
[0064] In S802, the captured image acquisition unit 311 acquires data of the captured image captured by the photographing camera 102. In S801, for example, data of one frame of the captured image is acquired. Data of several frames of the captured image may also be acquired.
[0065] In S803, the position information acquisition unit 312 acquires information about the shooting position of the shooting camera 102 when the shooting camera 102 captured the image to obtain the captured image obtained in S802. In addition, the time acquisition unit 313 acquires information about the shooting time, which is the time when the image was captured to obtain the captured image obtained in S802.
[0066] In S804, the transmitter / receiver unit 314 transmits the photographer attributes acquired in S801, the captured image data acquired in S802, and the information on the shooting location and shooting time acquired in S803 to the information processing device 110. The transmitted data is received and stored as captured camera image data 332 in the information processing device 110.
[0067] In S805, the captured image acquisition unit 311 determines whether the user has instructed to end image capture. If the captured image acquisition unit 311 determines that the user has not instructed to end image capture (NO in S805), the process returns to S802 and acquires captured image data of the next frame. If the captured image acquisition unit 311 determines that the user has instructed to end image capture (YES in S805), the process ends.
[0068] [Area of interest determination process] Fig. 9 is a flowchart for explaining processing such as identifying a region of interest in the information processing device 110. The series of processing shown in the flowchart in Fig. 9 is performed by the CPU 221 of the information processing device 110 expanding program code stored in the ROM 222 into the RAM 223 and executing it. In addition, some or all of the functions of the steps in Fig. 9 may be realized by hardware such as an ASIC or an electronic circuit.
[0069] 9 below explains the processing when the photographing camera 102 is selected as the processing target among the photographing cameras 102 to 104. The processing is similar when the photographing cameras 103 and 104 are selected as the processing targets.
[0070] In S901, the transmitting / receiving unit 324 receives captured camera image data of the processing target capturing camera 102. As described above, the captured camera image data includes information on the capturing position and the capturing time in addition to the captured image data.
[0071] In S902, the transmitting / receiving unit 324 acquires the shooting time from the captured camera image data received in S901.
[0072] In S903, the shooting area identification unit 325 acquires overhead camera image data from the overhead camera image data stored in the storage unit 321, the overhead camera image data having a shooting time that is different from the shooting time acquired in S902 by within a threshold value. That is, to obtain the shooting camera image data received in S901, overhead camera image data acquired by the overhead camera 101 at the same time or a time close to the time when the shooting camera 102 took the image is acquired. The threshold is a parameter that can be treated as data from the same time, and may be any value.
[0073] In S904, the shooting area identification unit 325 determines whether overhead camera image data was acquired in S903. If overhead camera image data obtained by shooting at the corresponding shooting time does not exist and therefore overhead camera image data was not acquired (NO in S904), the process proceeds to S912 without identifying the area of interest. If overhead camera image data was acquired (YES in S904), the process proceeds to S905.
[0074] In S905, the photographing area identification unit 325 acquires, from among the photographing camera image data stored in the storage unit 321, photographing camera image data that holds a photographing time whose difference from the photographing time acquired in S902 is within a threshold value. That is, in order to obtain the photographing camera image data received in S901, photographing camera image data that was acquired by another photographing camera at the same time or a time close to the time when the photograph was taken by the photographing camera 102 is acquired. If multiple photographing camera image data with the same camera ID are acquired, in the following steps, the photographing camera image data that holds the photographing time closest to the time acquired in S902 is used.
[0075] In S906, the photographing area identification unit 325 determines whether photographed camera image data holding a photographing camera ID different from the photographing camera ID of the photographing camera image data received in S901 in S905 has been acquired. That is, it is determined whether photographed camera image data obtained by a photographing camera other than the photographing camera 102 to be processed has been acquired. If other photographed camera image data obtained by photographing at the corresponding photographing time does not exist and photographed camera image data has not been acquired (NO in S906), the process proceeds to S912 without performing area of interest identification. If photographed camera image data has been acquired (YES in S906), the process proceeds to S907.
[0076] In S907, the photographic area identification unit 325 identifies the photographic camera area of the photographic camera 102 to be processed when the photographic camera captured the image data received in S901 and the photographic camera image data acquired in S905. The photographic area is identified by performing image pattern recognition between the photographic image indicated by the overhead camera image data acquired in S903 and the photographic image indicated by the photographic camera image data of the target. As a specific example, the similarity between the area in the photographic image indicated by the overhead camera image data and the photographic image indicated by the photographic camera image data of the target photographic camera is calculated based on image pattern recognition, and an area with a similarity equal to or greater than a certain level is identified as the range photographed by the target photographic camera (photographic area).
[0077] That is, image pattern recognition is performed on the image captured by the overhead camera and the image captured by the target camera, both of which were taken at the same or similar time, to identify the area captured by the target camera. If no area exists with a certain degree of similarity, the area captured by the target camera is left unidentified. The position and size of the area captured are identified by coordinates. The coordinates are based on the top left corner of the image captured by the overhead camera (origin).
[0078] If several frames of data are acquired in S901, image comparison may be performed using one of those frames. The method for selecting one frame may be to give priority to the most recent frame, and by selecting a frame in this manner, it is possible to reduce the discrepancy with the currently captured image area. Furthermore, if the image area has already been identified in another process, information on the identified image area may be acquired in S907.
[0079] FIG. 10 is a diagram showing an example of an image captured by the overhead camera. The captured image 1001 is an image captured by the overhead camera 101, indicated by the overhead camera image data acquired in S903. In other words, the captured image 1001 is an image representing the capture area of the overhead camera 101. The capture area 1002 is the capture area of the capturing camera 102 to be processed. As described above, the overhead camera captures the space where the event is taking place so that the capture area of the overhead camera 101 is wider than the capture areas of the capturing cameras 102 to 104. Therefore, the capture area of the overhead camera 101 includes the capture areas of each of the capturing cameras 102 to 104. Therefore, the capture areas of each of the capturing cameras 102 to 104 can be identified from the capture image 1001 captured by the overhead camera 101.
[0080] In S908, the shooting area identification unit 325 determines whether or not the shooting area of at least the target shooting camera 102 could be identified in S907. If the shooting area identification unit 325 determines that the shooting area could not be identified (NO in S908), it does not identify an area of interest and transitions to S912. If the shooting area identification unit 325 determines that the shooting area could be identified (YES in S908), it transitions to S909.
[0081] In S909, the attention area specifying unit 326 specifies an attention area and determines the attention level of the attention area. The attention area is specified as a rectangular range, similar to the shooting area in S906.
[0082] FIG. 11 is a flowchart for explaining details of step S909 for identifying an attention area and an attention level in this embodiment.
[0083] In S1101, the attention area identification unit 326 acquires the photographer attributes of the photographer who took the photograph in order to obtain the photographing camera image data received in S901. That is, the photographer attributes input by the photographer 105 of the photographing camera 102 that is the processing target of S901 via the photographer attribute input screen 401 in FIG. 4 are acquired.
[0084] In S1102, the attention area identification unit 326 acquires, from the photography areas identified in S907, a photography area identified from a photographed image indicated by photographic camera image data holding the same photographer attribute as the photographer attribute acquired in S1101. S1102 is a process of selecting a photography area to be used in subsequent processing from the photography areas identified in S907 in order to determine an attention area from photography results of other photographers who have the same hobbies and preferences as the photographer. Note that, in cases such as when photographer attributes were not acquired in S1101, the photography areas of all photographic cameras identified in S907 may be acquired in S1102.
[0085] In S1103, the attention area identification unit 326 determines a weight value for the photographing area acquired in S1102 based on the photographing positions of photographing cameras other than the photographing camera 102 being processed. The weight is set to a larger value the closer the photographing position is to the photographing position of the photographing camera 102 being processed that captured the photographed image data received in S901, and a smaller value the farther the photographing position is. This weight is set to increase the influence of photographing cameras that are photographing at a distance close to the photographing camera 102 being processed when determining the attention area described below.
[0086] In S1104, the attention area identification unit 326 generates a heat map of the imaging area.
[0087] FIG. 12 is a diagram illustrating an example of a method for generating a heat map.
[0088] Shooting area maps 1201 and 1202 are shooting area maps corresponding to the shooting areas of the overhead cameras. A shooting area 1203 of one of the shooting cameras among the shooting areas acquired in S1102 is mapped onto the shooting area map 1201. A shooting area 1204 of another of the shooting cameras among the shooting areas acquired in S1102 is mapped onto the shooting area map 1202.
[0089] In the shooting area maps 1201 and 1202, pixel values in the shooting areas 1203 and 1204, respectively, have the weight value determined in S1103. The pixel values of the shooting area 1203 are held with a weight of "5" determined in S1103 for the shooting area 1203. The pixel values of the shooting area 1204 are held with a weight of "1" determined in S1103 for the shooting area 1204. As described above, the weight value of a shooting area that is located closer to the shooting area of the shooting camera 102 to be processed is larger. In FIG. 12, the shooting area 1203 is located closer to the shooting area of the shooting camera 102 to be processed than the shooting area 1204, and therefore has a larger weight value. A heat map 1205 is generated by overlaying all the shooting area maps 1201 and 1202 and adding up the pixel values.
[0090] Note that in S1103, the weighting value may be determined by a method other than the position information. For example, in S1102, the shooting areas of all shooting cameras other than the shooting camera 102 to be processed are acquired without relying on attribute information. Then, in S1103, shooting area maps 1201 and 1202 may be generated by giving a large weight to the shooting areas of shooting cameras taken by a photographer with attribute information that is the same as the attribute information of the photographer 105 of the shooting camera 102 to be processed.
[0091] Alternatively, the weighting determination process may not be performed in S1103. In this case, for example, in S1104, the heat map 1205 may be generated by uniformly setting the pixel values in the imaging areas 1203 and 1204 to "1."
[0092] In S1105, the attention area specifying unit 326 determines whether there are pixel values greater than or equal to a threshold value (TH_VAL) within the heat map 1205 generated in S1104. "Greater than or equal to the threshold value" may mean exceeding the threshold value. The threshold value (TH_VAL) is a threshold value for specifying the attention area and may be set to any value. If the attention area specifying unit 326 determines that there is no area greater than or equal to the threshold value on the heat map 1205 and the attention area cannot be specified (S1105 is NO), the flowchart of FIG. 11 ends with no attention level. If the attention area specifying unit 326 determines that there is an area greater than or equal to the threshold value on the heat map 1205 (S1105 is YES), it proceeds to S1106.
[0093] In S1106, the attention level determining unit 327 obtains the maximum value (MAX_VAL) among the pixel values within the heat map 1205 generated in S1104. The attention level determining unit 327 determines the attention level according to the obtained maximum value (MAX_VAL). In this embodiment, the attention level will be described as being one of the values "high", "medium", or "low" as an example. In this case, the attention level determining unit 327 determines the attention level according to the following conditions. The relationship between α and β is 0 < α < β.
[0094] If TH_VAL ≦ MAX_VAL < TH_VAL + α, the attention level is "low" If TH_VAL + α ≦ MAX_VAL < TH_VAL + β, the attention level is "medium" If TH_VAL + β ≦ MAX_VAL, the attention level is "high"
[0095] In S1107, the attention area identification unit 326 identifies an attention area from the heat map 1205 generated in S1104. The attention area identification unit 326 determines, as the attention area, the rectangular area with the largest area among rectangular areas in the heat map 1205 that include pixels with a pixel value of MAX_VAL and are made up of pixels whose pixel values are equal to or greater than a threshold value (TH_VAL). As an example, if the threshold value (TH_VAL) is set to 10, the thick rectangular area is identified as the attention area 1206, as shown in FIG. 12. FIG. 10 also shows the attention area 1003 identified in S1107 in the image (captured area) captured by the overhead camera 101. The flowchart in FIG. 11 ends, and the process proceeds to S910 in FIG. 9.
[0096] In S910, the display information generation unit 328 generates information for the photographer of the target camera 102 to photograph the area of interest based on the shooting area of the target camera 102 identified in S907 and the area of interest and level of attention identified in S909.
[0097] 13 is a diagram showing a screen 1300 displayed on the display unit 218 of the photographing camera 102 to be processed. A photographed image 1301 included in the screen 1300 displays an image photographed by the photographing camera 102 to be processed. In other words, the photographed image 1301 is an image representing the photographing area of the photographing camera 102 to be processed, which was identified in S907. In this embodiment, the information for photographing the area of interest generated in S910 is a photographing direction 1302, a zoom direction 1303, and an attention level 1304. Therefore, the processing of S910 can also be said to be processing for determining the display content to be displayed on the display unit 218 of the photographing camera 102 to be processed.
[0098] The shooting direction 1302 is information indicating the direction from the current shooting area of the target shooting camera 102 to the area of interest. That is, it indicates the direction of movement of the angle of view (field of view) of the target shooting camera 102 so that the angle of view (field of view) of the target shooting camera 102 matches the angle of view (field of view) corresponding to the area of interest.
[0099] The zoom direction 1303 indicates the direction of enlarging or reducing the angle of view (field of view) of the photographing camera 102 to be processed so that the angle of view (field of view) coincides with the angle of view (field of view) corresponding to the region of interest. The attention level 1304 is information indicating the attention level of the region of interest.
[0100] This display content notifies the photographer 105 of information for photographing the area of interest. Note that the information for photographing the area of interest is not limited to the photographing direction 1302, zoom direction 1303, and attention level 1304, and an image of the area of interest may be displayed on the screen 1300 as a picture-in-picture.
[0101] A method for determining the shooting direction to the area of interest and the zoom direction to the area of interest, which are information for shooting the area of interest in this embodiment, will be described with reference to Fig. 10. In Fig. 10, the area of interest 1003 is an area whose vertex position coordinates are (Xb, Yb), whose length in the X direction is sizeXb, and whose length in the Y direction is sizeYb. Also, the shooting area 1002 of the shooting camera 102 to be processed is an area whose vertex position coordinates are (Xa, Ya), whose length in the X direction is sizeXa, and whose length in the Y direction is sizeYa.
[0102] First, a method for determining the shooting direction to the area of interest will be described. First, the coordinate difference between the left and right and the coordinate difference between the center coordinates of the shooting area 1002 of the shooting camera 102 to be processed identified in S907 and the center coordinate of the area of interest 1003 identified in S909 are calculated as follows:
[0103] Left and right coordinate difference = {Xa + (sizeXa / 2)} - {Xb + (sizeXb / 2)} Difference between top and bottom coordinates = {Ya + (sizeYa / 2)} - {Yb + (sizeYb / 2)}
[0104] When the left-right coordinate difference is greater than the up-down coordinate difference, the display information generation unit 328 generates information to display an image indicating the left direction, which is the origin direction, if the coordinate difference is positive, and generates information to display an image indicating the right direction if the coordinate difference is negative.When the up-down coordinate difference is greater than the left-right coordinate difference, the display information generation unit 328 generates information to display an image indicating the up direction, which is the origin direction of the up-down direction, if the coordinate difference is positive, and generates information to display an image indicating the down direction if the coordinate difference is negative.The image indicating the direction is, for example, an arrow image.As a result, the shooting direction 1302 is displayed as shown in FIG. 13.
[0105] In this embodiment, information is generated that displays either the left-right direction or the up-down direction as the shooting direction to the attention area. This is just one example, and information that displays both the left-right direction and the up-down direction as the shooting direction 1302 may be generated, or an oblique direction may be displayed.
[0106] Next, a method for determining the zoom direction to the region of interest will be described. First, the area of the photographing region 1002 of the photographing camera 102 to be processed, which was identified in S907, and the area of the region of interest 1003, which was identified in S909, is calculated as follows:
[0107] Area of the imaging area = sizeXa × sizeYa Area of interest = sizeXb × sizeYb
[0108] The display information generation unit 328 generates information that displays an image indicating the Tele direction when the area of the shooting area 1002 is larger than the area of the attention area 1003. When the area of the attention area 1003 is larger, the display information generation unit 328 generates information that displays an image indicating the Wide direction. As a result, the zoom direction 1303 is displayed as shown in FIG.
[0109] Furthermore, the display information generation unit 328 generates information for displaying an image indicating the attention level determined in S909. As a result, an attention level 1304 is displayed as shown in Fig. 13. Note that if it is determined in S909 that no attention area exists, no content is displayed.
[0110] In S911, the transmitting / receiving unit 324 transmits information for photographing the area of interest generated in S910 to the photographing camera 102 that is the processing target and that captured the image to obtain the photographing camera image data received in S901. That is, the transmitting / receiving unit 324 transmits the information so that the photographer 105 is notified of the content of the information generated in S910 via the photographing camera 102.
[0111] In S912, the display information generation unit 328 determines whether or not to end the process of identifying the area of interest. If it is determined that the process of identifying the area of interest is to be ended (YES in S912), the flow chart of Fig. 9 is ended. For example, if a notification to end the process is received from the photographing camera 102 to be processed, it is determined that the process of identifying the area of interest is to be ended. If it is determined that the process of identifying the area of interest is not to be ended (NO in S912), the process returns to S901 and is repeated.
[0112] [Display processing] 14(a) is a flowchart for explaining the process of displaying the contents of information for capturing an area of interest in the capturing camera to be processed that captured the image data received in step S901. The flowchart in FIG. 14 will be explained assuming that the capturing camera to be processed is the capturing camera 102.
[0113] In S1401, the transmitting / receiving unit 314 determines whether or not the information for photographing the area of interest transmitted from the information processing device 110 in S911 has been received. If the information for photographing the area of interest has been received (YES in S1401), the process proceeds to S1402. In S1402, the area of interest information display unit 316 displays the contents of the information for photographing the area of interest on the display unit 218. As a result, as shown in FIG. 13, a screen 1300 is displayed on the display unit 218 of the photographing camera 102, in which a photographed image 1301 representing the photographing area, a photographing direction 1302 to the area of interest, a zoom direction 1303, and an attention level 1304 are all included on the same screen.
[0114] In addition, the information for photographing the area of interest, namely, the photographing direction 1302, the zoom direction 1303, and the attention level 1304, may be displayed on the display unit 218 when it is considered that the photographer 105 is unaware of the area of interest.
[0115] FIG. 14(b) is a flowchart in which S1411 is added to the flowchart of FIG. 14(a). When information for photographing the attention area is received (YES in S1401), the process proceeds to S1411. In S1411, the attention area information display unit 316 determines whether photographing is being performed at a magnification equal to or greater than a predetermined value. When the attention area information display unit 316 determines that photographing is being performed at a magnification equal to or greater than a predetermined value, the process proceeds to S1402. When the attention area information display unit 316 determines that photographing is not being performed at a magnification equal to or greater than a predetermined value, the process skips S1402. When the photographer 105 photographs with an increased zoom magnification, it is considered that the photographer 105 will not easily notice the attention area. For this reason, when it is determined that photographing is being performed at a magnification equal to or greater than a predetermined value, the process may proceed to S1402.
[0116] The flowchart of FIG. 14 may be performed every time a predetermined time period elapses.
[0117] As described above, according to this embodiment, the attention area and attention level can be presented to the photographer, so the photographer can share the excitement with other photographers without missing any scenes of interest.
[0118] In this embodiment, the method of notifying the photographer of the method for photographing the area of interest is described as a method of notifying the photographer by an image on the screen as shown in Fig. 13. The method of notifying the photographer of the method for photographing the area of interest is not limited to an image, and may be, for example, audio.
[0119] <Other embodiments> The present disclosure 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.
[0120] The disclosure of the above-described embodiment includes the following configurations.
[0121] (Configuration 1) information for a first photographer in a specific space to photograph an area of interest being photographed by a second photographer different from the first photographer in the specific space, a generating means for generating the image based on photographed images obtained by photographing with a first photographing device used by the first photographer and a second photographing device used by the second photographer; a transmitting means for transmitting the information so that the content of the information is notified to the first photographer via the first photographing device; An information processing device comprising:
[0122] (Configuration 2) a receiving means for receiving a first photographed image obtained by photographing with the first photographing device and a second photographed image obtained by photographing with the second photographing device; a photographing area specifying means for specifying a first photographing area, which is an area photographed by the first photographing device, and a second photographing area, which is an area photographed by the second photographing device, based on the first photographed image and the second photographed image; The generating means generates information for photographing the region of interest based on the first photographing region and the second photographing region. 2. The information processing device according to configuration 1,
[0123] (Configuration 3) The imaging device further includes an attention area specifying means for specifying the attention area based on the second imaging area. 3. The information processing device according to configuration 2.
[0124] (Configuration 4) The generating means generates information for displaying a direction from the first imaging area to the area of interest as information for imaging the area of interest. 4. The information processing device according to configuration 3.
[0125] (Configuration 5) The generating means generates, as information for photographing the region of interest, information for displaying a zoom direction for making the angle of view corresponding to the region photographed by the first photographing device coincide with the angle of view corresponding to the region of interest. 5. The information processing device according to configuration 3 or 4.
[0126] (Configuration 6) the receiving means further receives a third captured image obtained by an image capturing device capturing an image of the specific space at a wider angle of view than the first image capturing device and the second image capturing device; The imaging area specifying means The first photographed area and the second photographed area are identified from the third photographed image. 6. The information processing device according to any one of configurations 2 to 5.
[0127] (Configuration 7) The imaging area specifying means A region in the third captured image that is similar to the first captured image is identified as the first captured region, and a region in the third captured image that is similar to the second captured image is identified as the second captured region. 7. The information processing device according to configuration 6.
[0128] (Configuration 8) There are a plurality of second photographers in the specific space, the receiving means receives the second captured images obtained by the second photographing devices of the second photographers, The photographing area specifying means specifies the second photographing area from each of the plurality of second photographed images. 6. The information processing device according to any one of configurations 3 to 5.
[0129] (Configuration 9) The attention area specifying means An area where the plurality of second imaging areas overlap is identified as the area of interest. 9. The information processing device according to configuration 8.
[0130] (Configuration 10) The attention area specifying means A weight value is determined for each of the plurality of second imaging areas, and the weight value of an area where two or more second imaging areas overlap is set to a value obtained by adding the weight values of the two or more second imaging areas, and an area where the weight value is equal to or greater than a threshold is identified as the area of interest. 10. The information processing device according to configuration 8 or 9.
[0131] (Configuration 11) the receiving means receives position information of the first image capture device and position information of each of the plurality of second image capture devices; The attention area specifying means assigns a larger weight value to the image capturing area of an image capturing device closer to the first image capturing device. 11. The information processing device according to configuration 10.
[0132] (Configuration 12) a determination unit for determining an attention level based on the weight value; The generating means generates information for displaying the attention level in the attention area as information for photographing the attention area. 12. The information processing device according to configuration 10 or 11.
[0133] (Configuration 13) the receiving means further receives attribute information of the first photographer, The attention area specifying means The attention area is identified by using the second photographing area corresponding to the photographed image taken by a photographer having the same attribute information as the attribute information of the first photographer, among the plurality of second photographing areas. 13. The information processing device according to any one of configurations 8 to 12.
[0134] (Configuration 14) the receiving means receives first time information when the image was captured to obtain the first captured image and second time information when the image was captured to obtain the second captured image; The imaging area specifying means The second photographing area photographed by the second photographing device is identified based on the second photographed image obtained by photographing at a time whose difference from the time indicated by the first time information is within a predetermined value. 14. The information processing device according to any one of configurations 2 to 13.
[0135] (Configuration 15) An imaging means for imaging a region in a specific space; a display means for displaying a photographed image corresponding to the photographing area; a receiving means for receiving information for photographing an area of interest photographed by another photographer in the specific space; a display control means for displaying the content of the information together with the photographed image on the display means; An imaging device comprising:
[0136] (Configuration 16) A system comprising: an information processing device according to any one of configurations 1 to 14; and an imaging device according to configuration 15.
[0137] (Configuration 17) information for a first photographer in a specific space to photograph an area of interest being photographed by a second photographer different from the first photographer in the specific space, a generating step of generating the image based on captured images obtained by capturing images using a first image capturing device used by the first photographer and a second image capturing device used by the second photographer; a transmitting step of transmitting the information via the first photographing device so that the content of the information is notified to the first photographer; An information processing method comprising:
[0138] (Configuration 18) 15. A program for causing a computer to execute each means of the information processing device according to any one of configurations 1 to 14. [Explanation of symbols]
[0139] 328 Display information generation section 324 Transmitter / Receiver 110 Information processing equipment
Claims
1. a generation means for generating information for a first photographer in a specific space to photograph an area of interest being photographed by a second photographer different from the first photographer in the specific space, based on photographed images obtained by a first photographing device used by the first photographer and a second photographing device used by the second photographer; a transmitting means for transmitting the information so that the content of the information is notified to the first photographer via the first photographing device; An information processing device comprising:
2. a receiving means for receiving a first photographed image obtained by photographing with the first photographing device and a second photographed image obtained by photographing with the second photographing device; a photographing area specifying means for specifying a first photographing area, which is an area photographed by the first photographing device, and a second photographing area, which is an area photographed by the second photographing device, based on the first photographed image and the second photographed image; The generating means generates information for photographing the region of interest based on the first photographing region and the second photographing region.
2. The information processing apparatus according to claim 1, wherein:
3. The imaging device further includes an attention area specifying means for specifying the attention area based on the second imaging area.
3. The information processing apparatus according to claim 2, wherein:
4. The generating means generates information for displaying a direction from the first imaging area to the region of interest as information for imaging the region of interest.
4. The information processing apparatus according to claim 3,
5. The generating means generates, as information for photographing the region of interest, information for displaying a zoom direction for making the angle of view corresponding to the region photographed by the first photographing device coincide with the angle of view corresponding to the region of interest.
4. The information processing apparatus according to claim 3,
6. The receiving means further receiving a third captured image obtained by an image capturing device capturing the specific space at a wider angle of view than the first image capturing device and the second image capturing device; The imaging area specifying means The first photographed area and the second photographed area are identified from the third photographed image.
3. The information processing apparatus according to claim 2, wherein:
7. The imaging area specifying means A region in the third captured image that is similar to the first captured image is identified as the first captured region, and a region in the third captured image that is similar to the second captured image is identified as the second captured region.
7. The information processing apparatus according to claim 6,
8. a plurality of second photographers are present in the specific space; the receiving means receives the second captured images obtained by the second photographing devices of the second photographers, The photographing area specifying means specifies the second photographing area from each of the plurality of second photographed images.
4. The information processing apparatus according to claim 3,
9. The attention area specifying means An area where the plurality of second imaging areas overlap is identified as the area of interest.
9. The information processing apparatus according to claim 8,
10. The attention area specifying means A weight value is determined for each of the plurality of second imaging areas, and the weight value of an area where two or more second imaging areas overlap is set to a value obtained by adding the weight values of the two or more second imaging areas, and an area where the weight value is equal to or greater than a threshold is identified as the attention area.
9. The information processing apparatus according to claim 8,
11. the receiving means receives position information of the first image capture device and position information of each of the plurality of second image capture devices; The attention area specifying means assigns a larger weight value to the image capturing area of an image capturing device closer to the first image capturing device.
11. The information processing apparatus according to claim 10,
12. a determination unit for determining an attention level based on the weight value; The generating means generates information for displaying the attention level in the attention area as information for photographing the attention area.
11. The information processing apparatus according to claim 10,
13. the receiving means further receives attribute information of the first photographer; The attention area specifying means The attention area is identified by using the second photographing area corresponding to the photographed image taken by a photographer having the same attribute information as the attribute information of the first photographer, among the plurality of second photographing areas.
9. The information processing apparatus according to claim 8,
14. the receiving means receives first time information when the image was captured to obtain the first captured image and second time information when the image was captured to obtain the second captured image; The imaging area specifying means The second photographing area photographed by the second photographing device is identified based on the second photographed image obtained by photographing at a time whose difference from the time indicated by the first time information is within a predetermined value.
3. The information processing apparatus according to claim 2, wherein:
15. An imaging means for imaging a region in a specific space; a display means for displaying a photographed image corresponding to the photographing area; a receiving means for receiving information for photographing an area of interest photographed by another photographer in the specific space; a display control means for displaying the content of the information together with the photographed image on the display means; An imaging device comprising:
16. A system comprising: an information processing device according to claim 1; and an imaging device according to claim 15.
17. a generating step of generating information for a first photographer in a specific space to photograph an area of interest being photographed by a second photographer different from the first photographer in the specific space, based on photographed images obtained by a first photographing device used by the first photographer and a second photographing device used by the second photographer; a transmitting step of transmitting the information via the first photographing device so that the content of the information is notified to the first photographer; An information processing method comprising:
18. A program for causing a computer to execute each means of the information processing apparatus according to any one of claims 1 to 14.
Citation Information
Patent Citations
Photography support system, and camera
JP2008066963A