Imaging apparatus
The imaging device addresses the challenge of determining shooting range for multiple subjects by using person recognition and characteristic information to automatically adjust pan/tilt controls based on the shooting instructor, enabling efficient capture of the instructor and related subjects.
Patent Information
- Application Number
- JP2024093792
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-06-10
- Publication Date
- 2025-12-22
AI Technical Summary
Conventional imaging devices struggle to determine the shooting range when multiple target subjects, such as the person instructing photography and their family, are involved, requiring complex voice instructions beyond timing.
An imaging device equipped with person recognition and characteristic information recording means to determine the shooting range based on the relationship with the shooting instructor by recognizing the instructor and incorporating them as a subject, using voiceprint information to identify and adjust the pan/tilt controls.
Enables the device to automatically set the shooting range to include the shooting instructor and related subjects without complex instructions, allowing for efficient capture of multiple subjects.
Smart Images

Figure 2025185508000001_ABST
Abstract
Description
[Technical Field]
[0001] The present invention relates to an imaging device, and more particularly to an automatic photography technique. [Background technology]
[0002] In recent years, automatic imaging devices have appeared that can automatically perform panning, tilting, zooming, and the like without requiring a user to perform physical operations, thereby enabling photography with a variety of compositions.
[0003] In such an automatic imaging device, the timing of photographing can be set not only periodically and steadily, but also in response to a vocal instruction from the user.
[0004] Basically, vocal instructions for shooting are given when more detailed instructions for shooting, including the timing of shooting, are desired.
[0005] However, it takes a lot of time and effort to give instructions other than those related to the timing of photography, specifically instructions related to the photography range, each time by voice.
[0006] Therefore, Patent Document 1 discloses an automatic imaging device that can capture an image of a target subject within a shooting range without detailed instructions when a user issues a shooting instruction through speech. [Prior art documents] [Patent documents]
[0007] [Patent Document 1] Japanese Patent Publication No. 2021-135368 Summary of the Invention [Problem to be solved by the invention]
[0008] However, the conventional technology disclosed in the above-mentioned Patent Document 1 does not take into consideration cases where photography is performed that include multiple target subjects, such as the person instructing photography and his / her family.
[0009] Therefore, an object of the present invention is to provide an imaging device that makes it possible to determine the shooting range based on the relationship with the shooting instructor by simply giving instructions related to the timing of shooting. [Means for solving the problem]
[0010] In order to achieve the above object, the imaging device of the present invention is an imaging device having a photographing means, a person recognition means for recognizing a person who has instructed the photographing means to photograph as a photographing instructor, and a characteristic information recording means for recording characteristic information related to the photographing instructor, and is characterized in that the photographing means determines the photographing range based on the characteristic information stored in the photographing instructor-related information recording means and so as to include the photographing instructor as a subject. [Effects of the Invention]
[0011] According to the present invention, it is possible to provide an imaging device that can determine the shooting range based on the relationship with the shooting instructor by simply giving instructions related to the timing of shooting. [Brief explanation of the drawings]
[0012] [Figure 1] 1 is a block diagram showing an example of the configuration of an imaging apparatus according to a first embodiment of the present invention; [Figure 2] 4 is a flowchart showing the operation of the first embodiment of the present invention. [Figure 3] FIG. 2 is a diagram showing an example of a photographing range in the first embodiment of the present invention. [Figure 4] FIG. 10 is a block diagram showing an example of the configuration of an imaging apparatus according to a second embodiment of the present invention. [Figure 5] 10 is a flowchart showing the operation of the second exemplary embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION
[0013] Hereinafter, an embodiment of the present invention will be described with reference to the drawings. [Example]
[0014] The configuration of the first embodiment of the present invention will be described below.
[0015] FIG. 1 is a diagram showing the configuration of an imaging apparatus according to a first embodiment of the present invention.
[0016] The imaging device 100 includes a CPU 101, an imaging unit 102, an image processing unit 103, a compression encoding unit 104, an image recording unit 105, a shooting instruction detection unit 106, a subject detection unit 107, a person information recording unit 108, a personal authentication unit 109, a feature information recording unit 110, a lens control unit 111, a pan / tilt control unit 112, a pan driving unit 113, and a tilt driving unit 114.
[0017] 1, each internal component of the image capture device 100 is connected to a system bus 120, and necessary data can be transmitted and received between them via the system bus 120. A CPU 101 controls the entire image capture device 100, and executes programs stored in a ROM (not shown) to realize each process of this embodiment, which will be described later.
[0018] The imaging unit 102 is composed of a lens unit including a focus lens and a zoom lens, an imaging element, an A / D conversion circuit, and the like, and performs image capture processing.
[0019] The image processing unit 103 performs various types of image processing, such as correction processing and white balance processing for reducing noise, on the image data captured by the image capturing unit 102 .
[0020] The compression encoding unit 104 performs compression encoding on the image data processed by the image processing unit 103 based on a format such as JPEG or H.264.
[0021] The image recording unit 105 records the image data compressed and coded by the compression coding unit 104 on a recording medium such as a non-volatile memory (not shown).
[0022] The photographing instruction detection unit 106 detects a photographing instruction from the user, and if a photographing instruction is detected, notifies the CPU 101 of the photographing instruction.
[0023] The photographing instruction detection unit 106 also includes a microphone with a sound collection function.
[0024] The shooting instruction is given by voice, and the shooting instruction is detected based on whether or not the collected input voice matches the voice of the shooting instruction registered in advance in a ROM (not shown).
[0025] In addition, the input voice is used to extract the characteristics (voiceprint information) of the person instructing the shooting.
[0026] The subject detection unit 107 detects a subject from the image data processed by the image processing unit 103, and further extracts the feature amount of the subject from the face region.
[0027] The personal information recording unit 108 registers personal information representing a specific individual, such as a name, linked to the feature amount of the person.
[0028] The personal authentication unit 109 compares the feature amounts of the subject extracted by the shooting instruction detection unit 106 or the subject detection unit 107 with the feature amounts of the person previously recorded in the person information recording unit 108, and detects whether or not the person is a specific person.
[0029] Since the personal authentication technology using face information or voiceprint information is well known, a detailed description thereof will be omitted here.
[0030] The characteristic information recording unit 110 registers the relationships between the people registered in the person information recording unit .
[0031] There is no particular restriction on the method for registering the relationship between people, but for example, a person who gives a shooting instruction after a person who gives a shooting instruction may be automatically registered as a related person to each other, since the shooting instructions were given at approximately the same time and in the same place.
[0032] The lens control unit 111 controls the focal length and zoom of the imaging unit 102 .
[0033] The pan / tilt control unit 112 controls the pan driving unit 113 and the tilt driving unit 114 .
[0034] The pan driving unit 113 drives the imaging unit 102 in the pan direction based on the control signal from the pan / tilt driving unit 112 .
[0035] The tilt driving section 114 drives the imaging section 102 in the tilt direction based on the control signal from the pan / tilt driving section 112 .
[0036] The operation of the imaging device in the first embodiment will be described below with reference to the flowchart in Fig. 2. This flowchart may be processed by the CPU 101 executing a program stored in a ROM (not shown), or may be processed by the CPU 101 executing a program transmitted via a network rather than from the ROM.
[0037] In step S201, when the shooting instruction detection unit 106 detects a vocal shooting instruction, the drive positions of the pan driving unit 113 and the tilt driving unit 114 are recorded, and the process proceeds to step S202.
[0038] In step S202, the person who issued the instruction to take a photograph is detected in the personal authentication unit 109, and the process proceeds to step S203.
[0039] Personal authentication is performed using voiceprint information of the uttered photographing instruction detected by the photographing instruction detection unit 106.
[0040] In step S203, if the person is identified as a result of the detection in step S202, that is, if the feature amount of the shooting instructor has been registered in advance in the personal information recording unit 108, the process proceeds to step S204. If the person is not identified, that is, if the feature amount of the shooting instructor has not been registered in advance in the personal information recording unit 108, the process proceeds to step S210.
[0041] In step S204, subject detection unit 107 detects subjects within the current shooting range, and personal authentication unit 109 determines whether the person detected in step S203 exists. If the person exists, the process proceeds to step S206. If the person does not exist, the process proceeds to step S205.
[0042] In step S205, a search for a photography instructor is performed.
[0043] Specifically, first, the lens control unit 111 performs zoom control on the imaging unit 102 to the wide-angle end.
[0044] Furthermore, the pan / tilt control unit 112 issues a drive instruction to the tilt drive unit 114 to drive it in the tilt direction to the lower limit.
[0045] Next, the pan / tilt control unit 112 issues a drive instruction to the pan drive unit 113, causing it to move in the pan direction until the person detected in step S203 is within the shooting range captured by the imaging unit 102 or until the limit of the driving range of the pan drive unit 113 is reached.
[0046] If the shooting instructor cannot be detected, the pan / tilt control unit 112 issues a drive instruction to the tilt drive unit 114 to drive in the tilt direction until the upper limit of the current shooting range reaches the lower limit.
[0047] Thereafter, the pan driving process and tilt driving process are repeatedly performed until the person detected in step S203 is present in the imaging range captured by the imaging unit 102 or the limit of the driving range of the tilt driving unit 114 is reached.
[0048] The driving process of the pan driving unit 113 and the tilt driving unit 114 is stopped when the shooting instructor is detected, and the driving positions of the pan driving unit 113 and the tilt driving unit 114 are recorded. This position is the position where the shooting instructor is always present within the shooting range.
[0049] When the person detected in step S203 is present in the photographing range, the drive positions of the pan drive unit 113 and the tilt drive unit 114 are recorded.
[0050] Although the detection of the shooting instructor is performed using voiceprint information of the utterance of the shooting instruction, it is also possible to, for example, identify the direction from which the shooting instruction is uttered, drive the pan driving unit 113 and tilt driving unit 114 in that direction, and then identify a subject that falls within the shooting range as the shooting instructor.
[0051] In this case, the search for the photography instructor is completed when the photography instructor is detected. The method for identifying the direction of the voice may be, for example, a method of using multiple microphones and identifying the direction from the sound collection level of each microphone, but is not particularly limited thereto.
[0052] In step S206, it is determined whether or not the search for the shooting instructor has been successful. If the search is successful, the process proceeds to step S207. If not, the process proceeds to step S210.
[0053] In step S207, it is determined whether the person related to the shooting instructor detected in step S202 and the feature amount of that person are registered in the feature information recording unit 110 and the person information recording unit 108. If the result of the determination is that they are registered, the process proceeds to step S208. If they are not registered, the process proceeds to step S210.
[0054] In step S208, subject detection unit 107 detects subjects within the current shooting range, and personal authentication unit 109 determines whether all related persons detected in step S207 are present. If they are present, the process proceeds to step S209. If they are not present, the process proceeds to step S209.
[0055] In step S209, a search for related people is performed.
[0056] Specifically, first, the lens control unit 111 performs zoom control on the zoom lens of the image capturing unit 102 to the wide-angle end.
[0057] Also, the pan / tilt control unit 112 issues a drive instruction to the tilt drive unit 114, causing it to drive in the tilt direction to the lower limit of the range in which the shooting instructor is within the shooting range.
[0058] Next, the pan / tilt control unit 112 issues a drive instruction to the pan drive unit 113, causing it to drive in the pan direction within a range in which all of the relevant persons detected in step S207 are present within the shooting range captured by the imaging unit 102, or within which the person instructing the shooting is present within the shooting range.
[0059] If no person is present, the maximum value is set to the range where the shooting instructor is within the shooting range, from the upper limit to the lower limit of the current shooting range, and the pan / tilt control unit 112 issues a drive command to the tilt drive unit 114 to drive in the tilt direction.
[0060] Thereafter, the pan driving process and tilt driving process are repeatedly performed within the range where all of the related persons detected in step S207 are present within the shooting range captured by the imaging unit 102, or where the shooting instructor is present within the shooting range.
[0061] Furthermore, during the search in step S209, the drive positions of the pan drive unit 113 and the tilt drive unit 114 at the time when the number of related persons present within the current shooting range is the largest are recorded and updated each time the number of related persons increases. If no related persons are found, the drive positions are not updated even once, and the recorded drive positions of the pan drive unit 113 and the tilt drive unit 114 remain the drive positions recorded in step S201 or step S205.
[0062] In step S210, the lens control unit 111 and pan / tilt control unit 112 issue control instructions to the imaging unit 102, pan driving unit 113, and tilt driving unit 114, and determine the imaging range of the imaging unit 102.
[0063] First, the pan / tilt control unit 112 drives the pan driving unit 113 and the tilt driving unit 114 to the driving positions last recorded before reaching step S210.
[0064] If the search for the shooting instructor is not successful in step S206, the lens control unit 111 does not perform any special control.
[0065] In step S206, if the search for the photography instructor is successful and no related person has been found, the pan driving unit 113 and tilt driving unit 114 are further driven so that the photography instructor is at the center of the photography range.
[0066] Furthermore, the lens control unit 111 performs zoom control to a magnification that provides an appropriate size for the face area of the person instructing the photography.
[0067] In step S206, if the search for the photography instructor is successful and one or more related persons have been found, zoom control is performed so that the photography instructor and all of the found related persons are included and the size of the face area is appropriate.
[0068] In step S211, image data captured by the imaging unit 102 is subjected to a photographing process by the image recording unit 105 via the image processing unit 103 and the compression encoding unit 104, until the image data is recorded on a recording medium.
[0069] An example of the shooting range determined in step S210 is shown in FIG.
[0070] Reference numeral 301 denotes a photography instructor. Reference numerals 302a and 302b denote people who are not related to the photography instructor 301.
[0071] 310 indicates the range captured by the imaging unit 102 when the imaging device 100 performs zoom control to the wide-angle end and drives the pan driving unit 113 and tilt driving unit 114 to their limits within the range in which the shooting instructor 301 fits within the shooting range.
[0072] If the people 303a and 303b are not related to the photography instructor 301, the photography range is 320 with the photography instructor 301 at the center.
[0073] If the people 303a and 303b are related to the photography instructor 301, the photography range is 330 which includes the photography instructor 301 and the people 303a and 303b.
[0074] As explained above, the shooting range is determined based on the relationship between the shooting instructor and the person instructing the shooting, simply by giving instructions regarding the timing of shooting, so it is possible to shoot multiple subjects, such as the person instructing the shooting and their family, without complex instructions.
[0075] In this embodiment, the shooting range is determined based only on instructions regarding the timing of shooting. However, the shooting range may be specified more precisely by instructions using gestures from the shooting instructor. In this case, the gestures are analyzed by analyzing the hand movements of the user who instructs shooting through the imaging unit 101. The meanings of the gestures are registered in the feature information recording unit 110 in association with people registered in the person information recording unit 108. [Example]
[0076] An imaging device according to a second embodiment of the present invention will now be described.
[0077] In the first embodiment, the imaging instruction is given after the imaging instructor and related persons are searched for.
[0078] In this case, it may take some time to search, and the photographer may have to wait until they can take a photo.
[0079] Therefore, in the second embodiment, an imaging device will be described that captures 360-degree images in all directions before searching for the photography instructor and related persons, and then cuts out an image only in the range that includes the photography instructor and related persons.
[0080] The same components as those in FIG. 1 described in the first embodiment are given the same numbers, and some of the description will be omitted.
[0081] The imaging device 400 of the second embodiment includes wide-angle imaging units 402a and 402b instead of the imaging unit 102 of the imaging device 100 of the first embodiment.
[0082] The wide-angle imaging units 402a and 402b are lens units including a focus lens and a zoom lens, and are composed of a wide-angle lens capable of capturing a wide range of 180 degrees or more, an image sensor, an A / D conversion circuit, etc., and perform image capture processing.
[0083] The image processing unit 103 performs various types of correction processing and image processing such as white balance processing for reducing noise on the image data captured by the image capturing units 402a and 402b.
[0084] The image synthesis unit 415 calculates an overlapping area between the two pieces of image data processed by the image processing unit 103, and performs image alignment and synthesis processing. Through the synthesis processing, 360-degree omnidirectional image data is obtained.
[0085] The image cutout unit 416 cuts out an image of a specified region from the image data processed by the image synthesis unit 415 .
[0086] The compression encoding unit 104 performs compression encoding on the image data processed by the image synthesis unit 415 or the image clipping unit 416 based on a format such as JPEG or H.264.
[0087] The subject detection unit 107 detects a subject from the image data processed by the image synthesis unit 415, and further extracts the feature amount of the subject from the face region.
[0088] Next, the operation of the imaging device 400 in the second embodiment will be described with reference to the flowchart in FIG.
[0089] In step S501, when the photographing instruction detection unit 106 detects a vocalized photographing instruction, the process proceeds to step S502.
[0090] In step S502, 360-degree shooting processing is performed. The 360-degree shooting processing is performed from the wide-angle shooting units 402a and 402b via the image processing unit 103 and the image synthesis unit 415, as described above.
[0091] In step S503, the person who issued the instruction to take a photograph is detected in the personal authentication unit 109, and the process proceeds to step S504.
[0092] In step S504, if the person is identified as a result of the detection in step S503, that is, if the feature amount of the shooting instructor has been registered in advance in the personal information recording unit 108, the process proceeds to step S505. If the person is not identified, that is, if the feature amount of the shooting instructor has not been registered in advance in the personal information recording unit 108, the process ends.
[0093] In step S505, the shooting instructor detected in step S503 is searched for from the 360-degree omnidirectional image data captured in step S502.
[0094] In step S506, it is determined whether or not the related person of the person detected by the personal authentication unit 109 and the feature amount of that related person are registered in the feature information recording unit 110 and the personal information recording unit 108. If the result of the determination is that they are registered, the process proceeds to step S507. If they are not registered, the process proceeds to step S508.
[0095] In step S507, a search is made for people related to the photography instructor extracted in step S506 from the 360-degree omnidirectional image data photographed in step S502.
[0096] In step S508, the image cutout range is set based on the position information of the photographing instructor found in step S505 and the position information of the person related to the photographing instructor found in step S507.
[0097] If the search for the photography instructor is successful in step S505 and if no related persons are found in step S507, the cropping range is set to a preset image size with the photography instructor at the center.
[0098] In step S506, if the search for the photography instructor is successful and one or more related persons have been found, the cropping range is set to the smallest area that can accommodate the photography instructor and all of the found related persons.
[0099] In step S509, the cutout process is performed within the cutout range set in step S508.
[0100] As explained above, 360-degree photography is performed before searching for the photography instructor and related persons, and then only the area in which the photography instructor and related persons are captured is cut out later, making it possible to obtain an image of the photography range that takes into account the relationship with the photography instructor without making the subject wait. [Explanation of symbols]
[0101] 100 Imaging device 101 CPU 102 Imaging unit 103 Image processing section 104 Compression Encoding Unit 105 Image recording unit 106 Shooting instruction detection unit 107 Subject detection unit 108 Personal Information Recording Department 109 Personal Authentication Unit 110 Characteristic information recording unit 111 Lens control unit 112 Pan / Tilt control unit 113 Pan drive unit 114 Tilt drive unit 120 System Bus
Claims
1. Photography means, a person recognition means for recognizing a person who has instructed the photographing means to photograph as a photographing instructor; An imaging device having a feature information recording means for recording feature information associated with the photography instructor, The imaging device is characterized in that the imaging means determines a photographing range based on the characteristic information stored in the imaging instructor related information recording means so as to include the imaging instructor as a subject.
2. 2. The imaging apparatus according to claim 1, wherein the means for determining the photographing range includes panning, tilting, and zooming.
3. Photography means, a person recognition means for recognizing a person who has instructed the photographing means to photograph as a photographing instructor; a feature information recording means for recording feature information associated with the photography instructor; An imaging device having a captured image cutting means for cutting out an image of a certain range from an image captured by the imaging means, The imaging device is characterized in that the captured image cropping means determines a cropping range based on the characteristic information stored in the characteristic information recording means and so as to include the person instructing the photography as a subject.
4. 4. The imaging device according to claim 1, wherein the characteristic information includes information about people related to the photographer, and the imaging and cropping range is determined so that the people related to the photographer are also included in the subject.
5. 5. The imaging device according to claim 1, wherein the photographing instruction is an instruction that includes only the content of starting a photographing operation.
6. 6. The imaging device according to claim 1, wherein, when the shooting instruction includes a content related to a shooting operation other than a content for starting a shooting operation, the imaging device operates in accordance with the content related to the shooting operation.
7. 7. The imaging device according to claim 1, wherein the feature information includes gesture information of the photographer, and the imaging and cropping ranges are determined in accordance with the gesture.
8. The imaging device according to any one of claims 1 to 7, characterized in that, when a shooting instruction is received from a second shooting instructor after a shooting instruction is received from a first shooting instructor, the second photographer is added to the related person information of the first photographer.
Citation Information
Patent Citations
Imaging apparatus, control method of the same, program and storage medium
JP2021135368A