JP6270578B2 - IMAGING DEVICE, IMAGING DEVICE CONTROL METHOD, AND PROGRAM - Google Patents

Description

  The present invention relates to an imaging apparatus having an object recognition function.

  An image processing technique for automatically detecting a specific subject pattern from an image is used in many fields such as a teleconference, a man-machine interface, security, a monitor system for tracking a human face, and image compression. For example, there has been proposed an imaging apparatus that detects the position of a face in an image, focuses on the face, and captures an image with an optimal exposure to the face (see Patent Document 1). Further, as a technique for detecting various objects in an image, not limited to a face, a technique has been proposed in which a positional relationship of local regions is expressed by a probability model and recognition of a human face, a car, or the like is performed by learning ( Non-patent document 1).

  According to such a technique, it is possible to recognize various object attributes (information indicating what the object is) and its region from within the image, and accordingly, based on the recognized attribute and the region, Image capturing and image processing can be performed. In addition, by setting shooting parameters such as edge enhancement, saturation enhancement, and gradation correction according to the attributes of each recognized area, appropriate processing can be performed on the shooting target in each area. This makes it possible to acquire a high-quality image.

JP 2005-318554 A

Keiji Yanai, "Current Status and Future of General Object Recognition", Transactions of Information Processing Society of Japan: Computer Vision and Image Media, Vol48, No.SIG16 (CVIM19), November 2007

  When a plurality of objects are recognized from a captured image, there is a method in which a user designates a position in an image via a touch panel as a method for determining which object is used as a main subject to perform shooting control or image processing. . However, there are times when a recognition result has been obtained that the specified object has multiple attributes. In this case, if only the position is specified, the attribute of which area including the specified position is used for shooting control and image processing. It may be difficult to determine whether or not For example, when the position of a tree is specified in an image that includes a tree, a forest that includes a tree, and a mountain that includes a forest, which attribute should be used: tree, forest, or mountain It is not easy to make the determination accurately on the imaging device side.

  In addition, when it is desired to set shooting parameters corresponding to attributes for each area in the captured image, if there are areas where a plurality of attributes overlap, it is not easy to set the shooting parameters uniquely. For example, in the image that shows the previous tree, the forest that contains the tree, and the mountain that contains the forest, the attributes of the tree, forest, and mountain overlap in the area of the tree. It is not easy for the imaging apparatus to accurately determine which attribute should be used to set the shooting parameter.

  An object of the present invention is to provide a technique that allows a user to easily specify an attribute when a region of a predetermined object in a captured image is recognized as having a plurality of attributes. Another object of the present invention is to provide a technique capable of performing shooting with appropriate shooting parameters for each attribute when it is recognized that there are regions where a plurality of attributes overlap in the shot image. And

  An image pickup apparatus according to the present invention includes an image pickup means, a display means for displaying an image obtained by the image pickup means, a recognition means for recognizing an attribute and an area of an object in the image obtained by the image pickup means. Control means for switching each attribute of the plurality of attributes and the area to be displayed on the display means when the recognition means recognizes that the predetermined area in the image has a plurality of attributes; and the display Designation means for designating an attribute designated by the user as an attribute of the main subject among the attributes displayed on the means, and an imaging parameter in an area corresponding to the attribute based on the attribute designated as the main subject by the designation means And setting means for setting.

  Another imaging apparatus according to the present invention includes an imaging unit, a recognition unit for recognizing an attribute of an object in an image obtained by the imaging unit and a region thereof, an attribute recognized by the recognition unit, and the region thereof. Setting means for setting shooting parameters based on the above, setting means for setting shooting parameters based on the attribute and area of the object recognized by the recognition means, instruction means for instructing shooting by the imaging means, and When the recognizing unit recognizes that there is a region where a plurality of attributes overlap in the image obtained by the image capturing unit, the shooting parameter corresponding to each of the plurality of attributes is given when there is a shooting instruction by the instruction unit. And a control means for taking a plurality of images by applying to the area corresponding to the attribute.

  According to the present invention, when a recognition result is obtained that a predetermined object region in a captured image has a plurality of attributes, the user can easily specify the attribute of the object as the main subject. In addition, according to the present invention, when a recognition result indicating that there is a region where a plurality of attributes overlap is obtained, appropriate shooting parameters are set according to each attribute, thereby capturing a high-quality image. can do.

1 is a block diagram illustrating a schematic configuration of an imaging apparatus according to a first embodiment of the present invention. It is a figure which shows the example of the object recognition result by the object recognition part in the imaging device of FIG. It is a figure which shows another example of the object recognition result by the object recognition part in the imaging device of FIG. 2 is a flowchart of processing for selecting an attribute desired by a user from a plurality of attributes in the imaging apparatus of FIG. 1. It is a figure which shows the example which switches and displays a some attribute in designated time in the imaging device of FIG. It is a block diagram which shows schematic structure of the imaging device which concerns on 2nd Embodiment of this invention. It is a figure which shows the example of the object recognition result by the object recognition part in the imaging device of FIG. It is a figure which shows another example of the object recognition result by the object recognition part in the imaging device of FIG. FIG. 7 is a diagram schematically illustrating imaging parameters set for a plurality of captured images captured by the imaging apparatus of FIG. 6 when there are overlapping regions having a plurality of different attributes. FIG. 7 is a flowchart of processing for capturing a plurality of images by changing imaging parameters in the imaging apparatus of FIG. 6. 7 is a flowchart of shooting parameter setting processing for shooting an image by reducing the number of shots in the imaging apparatus of FIG. 6.

  Embodiments of the present invention will be described below with reference to the accompanying drawings.

<First Embodiment>
FIG. 1 is a block diagram showing a schematic configuration of an imaging apparatus 100A according to the first embodiment of the present invention. The imaging device 100A is, for example, a digital camera that captures a subject image. However, the imaging apparatus according to the present invention is not limited to a digital camera, and an electronic apparatus having a photographing function is included in the category of the imaging apparatus according to the present invention. For example, the imaging device 100A may be a mobile communication terminal with a camera function (such as a mobile phone or a smartphone), a portable computer with a camera function (tablet terminal), a portable game machine with a camera function, or the like.

  The imaging apparatus 100 includes an imaging optical system 101, an imaging element 102, an analog signal processing unit 103, an A / D conversion unit 104, a control unit 105, an image processing unit 106, a storage unit 107, a display unit 108, an object recognition unit 109, and photographing. A parameter setting unit 110 and an object specifying unit 111;

  The imaging optical system 101 condenses the reflected light from the subject and forms it as a subject image on the imaging element 102. Specifically, the image sensor 102 is a CCD image sensor, a CMOS image sensor, or the like that converts a subject image, which is an optical image, into an electric signal by photoelectric conversion. The image sensor 102 outputs an electrical signal corresponding to the light intensity of the formed subject image in units of pixels. An electrical signal that is a video signal output from the image sensor 102 is an analog signal indicating a photographed subject image. Therefore, the video signal output from the image sensor 102 is input to the analog signal processing unit 103, and the analog signal processing unit 103 performs signal processing such as correlated double sampling (CDS) on the received video signal. The video signal output from the analog signal processing unit 103 is converted into a digital signal (digital image data) by the A / D conversion unit 104 and sent to the control unit 105 and the image processing unit 106.

  The control unit 105 is, for example, a microcomputer. The control unit 105 includes a CPU that executes a predetermined program, a ROM that stores a program executed by the CPU, and a RAM that functions as a work area where the CPU executes the program and temporarily stores data calculated by the CPU. And have. The control unit 105 expands and executes the program code stored in the ROM in the work area of the RAM, thereby controlling each unit of the imaging device 100A, thereby controlling the overall operation of the imaging device 100A.

  In addition, the control unit 105 controls a focus control mechanism and an exposure control mechanism (not shown) included in the imaging optical system 101 based on the video signal output from the A / D conversion unit 104, thereby setting the focus at the time of shooting. And control shooting conditions such as exposure settings. The focus control mechanism is an actuator that drives a focus lens or a zoom lens included in the imaging optical system 101 in the optical axis direction, and the exposure control mechanism is an actuator that drives an aperture or a shutter. The control unit 105 performs focus control using the contrast value of the recognized object region or the recognized object region according to the imaging parameter set by the imaging parameter setting unit 110 based on the recognition result by the object recognition unit 109. Exposure control using luminance values is performed. Therefore, the imaging apparatus 100A can perform imaging processing in consideration of the area of the object in the captured image and its attributes. Further, the control unit 105 also performs readout control of the image sensor 102 (for example, output timing of video signals from the image sensor 102, adjustment of output pixels, etc.).

  The image processing unit 106 performs image processing such as gamma correction and white balance processing on the video signal (digital image data) acquired from the A / D conversion unit 104. In addition, the image processing unit 106 has a function of performing image processing using information (specifically, object attributes and areas) related to main objects in the image supplied from the imaging parameter setting unit 110.

  The storage unit 107 stores the video signal output from the image processing unit 106 in a storage medium such as a hard disk or a memory card (semiconductor memory). The storage medium may be built in the imaging apparatus 100A, may be detachable from the imaging apparatus 100A, and may be further connected to be communicable via a network. Good. The display unit 108 is, for example, an LCD or an organic EL display, and displays the video signal output from the image processing unit 106 as an image. In the present embodiment, the display unit 108 has a touch panel function. The image capturing apparatus 100 </ b> A can cause the display unit 108 to function as an electronic viewfinder (EVF) by sequentially displaying images sequentially captured in time series by the image sensor 102 on the display unit 108. In addition, the display unit 108 has a function of displaying a region and an attribute in the image of the object recognized by the object recognition unit 109.

  Based on the video signal output from the image processing unit 106, the object recognition unit 109 detects the attribute of the object in the video (image) and its region, and displays information about the detected attribute and the region on the display unit 108. Output to the shooting parameter setting unit 110. If there are a plurality of objects in the image, the attribute and the information related to the area are output by the number of the objects.

  As a method of object recognition by the object recognition unit 109, a known technique can be used. For example, a feature quantity such as a feature vector is detected from the input image, and the detected feature quantity is compared with a recognition dictionary holding a feature quantity of a detection target object such as a person, a car, a mountain, or a building. As a result of this comparison, a detection target object is detected by detecting a likelihood called similarity or an evaluation value. Note that in the method using the feature amount and the recognition dictionary, it is possible to determine whether or not the detection target object is detected when the likelihood is equal to or greater than a predetermined threshold.

  The shooting parameter setting unit 110 sets shooting parameters based on the recognition result by the object recognition unit 109. The parameters set by the shooting parameter setting unit 110 are supplied to the control unit 105 and used to control shooting conditions such as the focus state and the exposure state. The parameters set by the shooting parameter setting unit 110 are supplied to the image processing unit 106, and image processing and the like suitable for the attribute are performed for each recognized object region. For example, for areas recognized with the attribute “sky”, color reproduction is performed in dark blue without whitening, and edges are emphasized for areas recognized with the attribute “building”, etc. Image processing can be performed.

  The object designating unit 111 is an input interface provided for a user operation. In the present embodiment, specifically, the object designating unit 111 is a touch panel provided on the display unit 108. However, the object specifying unit 111 is not limited to the touch panel, and may be various buttons for selecting and determining an icon, a menu, or the like displayed on the display unit 108, for example.

  The user (photographer) can select the main subject by touching an object to be the main subject in the image displayed on the display unit 108. Then, the object specifying unit 111 searches for a recognition result existing in the vicinity of the specified position based on the position in the touched image specified by the user (hereinafter referred to as “specified position”). Then, the object specifying unit 111 selects an object to be a main subject from the objects recognized by the object recognition unit 109. The shooting parameter setting unit 110 sets shooting parameters based on the attribute of the object selected as the main subject and its area.

  FIG. 2 is a diagram illustrating an example of a recognition result by the object recognition unit 109 in the imaging apparatus 100A. FIG. 2A shows an input image to the object recognition unit 109. FIGS. 2B to 2D show the object recognition results 1 to 3 by the object recognition unit 109, and are the areas of the object in which the black portions are recognized.

  FIG. 2B shows that the attribute “sky” and its area are recognized on the object at the top of the image. FIG. 2C shows that the attribute “river” and its area are recognized in the object from the center of the image to the bottom of the image. FIG. 2D shows that the attribute “building” and its area are recognized on the object on the right side of the image. In this way, when one attribute is recognized for one object, when the user touches the object to be the main subject in the touch panel of the display unit 108, the object designating unit 111 determines the main subject based on the designated position information. It is possible to select the attribute of the object and its area.

  However, when a recognition result indicating that a certain area in the image has a plurality of attributes is obtained, the object designating unit 111 determines only the attribute information of the object that is the main subject and the position information of the designated position by the user. It becomes difficult to select an area. An example thereof will be described with reference to FIG.

  FIG. 3 is a diagram illustrating another example of the recognition result by the object recognition unit 109 in the imaging apparatus 100A. 3A shows an input image to the object recognition unit 109. FIGS. 3B to 3D are the same as those in FIG. 2A. FIG. ˜6 examples are shown, and a blacked portion is a recognized object region.

  In FIG. 3B, the attribute “tree” is recognized in the black object, in FIG. 3C, the attribute “forest” is recognized in the black object, and in FIG. The attribute “mountain” is recognized on the black object. Therefore, in particular, when the user designates the blackened area in FIG. 3B or a position near the area through the object designating unit 111 as an object that is the main subject, the object recognizing unit 109 selects the object attribute desired by the user. Cannot accurately determine whether it is a “tree”, “forest” or “mountain”.

  In view of this, in the imaging apparatus 100A, the attributes of the object that can be the main subject displayed on the display unit 108 are sequentially switched at the designated time based on the designated position by the user. Thus, even when there are a plurality of attributes in the area including the designated position, the user can easily designate the desired object as the main subject by touching the display unit 108 when the desired attribute is displayed. Can do. Hereinafter, processing for designating a desired attribute from a plurality of attributes will be described with reference to the flowchart of FIG.

  FIG. 4 is a flowchart of processing for selecting an attribute desired by the user from a plurality of attributes in the imaging apparatus 100A. Each process shown in FIG. 4 is realized by the CPU of the control unit 105 developing a program stored in the ROM on the RAM and controlling the operation of each unit constituting the imaging apparatus 100A.

  In step S <b> 401, the image processing unit 106 acquires a captured image (digital image data) obtained by converting a video (image) signal output from the image sensor 102 into a digital signal by the A / D conversion unit 104. Subsequently, in step S402, the object recognition unit 109 acquires the image data processed by the image processing unit 106 as an input image, and performs object recognition processing. Thereby, as the result of the object recognition process, information on the attribute of the object in the input image and its area is obtained.

  In subsequent step S <b> 403, the control unit 105 determines whether an object as a main subject is specified by the user via the object specifying unit 111. If there is an object designation (YES in S403), control unit 105 advances the process to step S404, and if there is no object designation (NO in S403), the process advances to step S409.

  In step S404, the control unit 105 determines whether there are a plurality of attributes in the position information of the position specified in step S403. If there are a plurality of attributes (YES in S404), control unit 105 advances the process to step S405. If there are no more attributes (NO in S404), control proceeds to step S406. In step S405, the control unit 105 switches and displays a plurality of attributes recognized by the object recognition unit 109 on the display unit 108 at a specified time based on the position information of the position specified in step S403, so that the user can Select the attribute of the object to be the subject.

  FIG. 5A is a diagram showing an example of switching and displaying a plurality of attributes obtained as the recognition result shown in FIG. 3 at a specified time. As described above, with respect to the input image of FIG. 3A, the attributes of “tree”, “forest”, and “mountain” are recognized from the position information of the position of “tree” shown in FIG. . For this reason, the screen for selecting “tree”, the screen for selecting “forest”, and the screen for selecting “mountain” as the attributes of the object to be the main subject are sequentially switched every specified time. When the user touches the display screen of the display unit 108 while the predetermined screen is displayed, the attribute shown on the screen is selected as the attribute of the object that is the main subject.

  In step S406, the control unit 105 determines the attribute of the object to be the main subject based on the position information of the designated position in step S403. When the attributes of the object as the main subject are determined in steps S405 and S406, in step S407, the shooting parameter setting unit 110 sets the shooting parameters based on the attributes of the object determined as the main subject and its area. . In subsequent step S408, the control unit 105 performs imaging control and performs image processing on the video signal acquired by the image processing unit 106. Thereafter, in step S409, the control unit 105 determines whether or not the shooting mode is continued. If the shooting mode is continued (YES in S409), the control unit 105 returns the process to step S401. If the shooting mode is ended (NO in S409), the control unit 105 ends this process.

  Here, in steps S404 to S405, the user is allowed to specify the object to be the main subject, and the attribute and area of the object to be the main subject are determined. The shooting control is based on the attribute of the specified object and the area. This is for changing the contents of the image processing. Therefore, if the selection result of the object to be the main subject does not change or affect the shooting control or image processing, it is not necessary for the user to select the object to be the main subject.

  In other words, even if the attributes of the object that is the main subject and the shooting parameters set based on the area are similar (substantially no difference), a plurality of attributes are treated as equivalent (single) attributes. There is no. Specifically, in the example of FIG. 3, the difference between the shooting parameters set for “tree” and “forest, mountain” is large, but the shooting parameters set for “forest” and “mountain” are large. The difference is small. Therefore, in this case, there is no problem even if grouping that handles “forest” and “mountain” as the same attribute is performed.

  FIG. 5B is a diagram illustrating an example in which attributes that do not affect the setting of the shooting parameter among the plurality of attributes obtained as the recognition result illustrated in FIG. 3 are collectively switched and displayed at a specified time. . In FIG. 5 (b), “forest” and “mountain” are not subject to switching display, but switching display between “tree” and “forest, mountain” is performed so that the object of the main subject to the user can be displayed. An example of making a selection is shown. Thereby, since the candidate of the attribute of the object shown to a user can be narrowed down, selection of the object used as a main subject becomes easy for a user, and it can move to photography operation promptly.

  In this embodiment, a configuration is adopted in which the user selects an attribute and a region of an object to be a main subject through the object specifying unit 111. For this purpose, it is necessary to notify the attribute of the object as the main subject and the candidate for the area, and the object attribute and the area are superimposed on the captured image on the display unit 108. At this time, it is preferable to use different display methods for an object area having a plurality of attributes and an object area not having a plurality of attributes. In other words, the display method (for example, the color to be superimposed on the area, the shading pattern, the color of the frame indicating the area, the frame of the frame, etc.) It is preferable that the line patterns are different. Thereby, user operability can be improved.

  As described above, according to the first embodiment, even when a recognition result that a predetermined object region has a plurality of attributes is obtained, the user easily specifies the attribute of the object that is the main subject. be able to.

Second Embodiment
FIG. 6 is a block diagram showing a schematic configuration of an imaging apparatus 100B according to the second embodiment of the present invention. The imaging device 100B is different from the imaging device 100A according to the first embodiment in that the imaging instruction unit 112 is provided and the object specifying unit 111 is not provided. Components that are included in the imaging apparatus 100B and that are the same as those included in the imaging apparatus 100A are denoted by the same reference numerals, and description thereof is omitted here.

  Specifically, the shooting instruction unit 112 includes a shutter button and operation buttons for setting shooting conditions such as the number of shots when performing bracket shooting, which will be described later, which is a feature of the second embodiment. The user instructs the control unit 105 of the shooting timing via the shooting instruction unit 112. Of course, the imaging apparatus 100A described in the first embodiment also includes a shutter button, but since it is not a characteristic part of the imaging apparatus 100A, the illustration in FIG. 1 is omitted and the description is omitted. .

  In the imaging device 100B, similarly to the imaging device 100A according to the first embodiment, the imaging control by the control unit 105 and the image by the image processing unit 106 are performed using the imaging parameters set based on the recognition result by the object recognition unit 109. Processing is performed.

  FIG. 7 is a diagram illustrating an example of a recognition result by the object recognition unit 109 in the imaging apparatus 100B. FIG. 7A shows an input image to the object recognition unit 109, and FIGS. 7B and 7C show object recognition results 7 and 8 by the object recognition unit 109, which are surrounded by bold lines. The recognized part is the recognized object region. FIG. 7B shows that the attribute “sky” and its area are recognized for the object at the top of the image, and FIG. 7C shows that the attribute “building” and its area are recognized for the object on the right side of the image. ing.

  For example, as shown in FIG. 7B, for a region recognized with the attribute of “sky”, color reproduction is performed in dark blue without whiteout. Further, as shown in FIG. 7C, image processing such as emphasizing an edge is performed on a region recognized with the attribute “building”. In this way, a high-quality image can be shot by setting shooting parameters corresponding to the attributes of each object region.

  On the other hand, as a recognition result by the object recognition unit 109, a region where a plurality of attributes overlap may be recognized. FIG. 8 is a diagram illustrating another example of the recognition result by the object recognition unit 109 in the imaging apparatus 100B. FIG. 8A shows an input image to the object recognition unit 109, which is the same as FIG. 7A. FIGS. 8B to 8D show the object recognition results 8 to 10 by the object recognition unit 109, and the area surrounded by the thick line is the area of the recognized object. In FIG. 8B, the attribute “mountain” and its area are recognized in the object surrounded by the bold line. In FIG. 8C, the attribute “forest” and its area are recognized for the object surrounded by the thick line, and in FIG. 8D, the attribute “tree” and its area are recognized for the object surrounded by the thick line. ing. Therefore, the area recognized as the attribute “tree” is the area recognized as the attribute “forest” and is also the area recognized as the attribute “mountain”. An area recognized as having the attribute “forest” is also an area recognized as having the attribute “mountain”.

  As a result of recognition by the object recognizing unit 109, for a region where different attributes do not overlap as shown in FIG. 7, the shooting parameter setting unit 110 may set shooting parameters according to the attribute of the region. However, for an area where different attributes overlap as shown in FIG. 8, the imaging parameter setting unit 110 does not know which attribute should be set for the area. In other words, in the example of FIG. 8, it is not clear which attribute of “tree”, “forest”, and “mountain” should be set.

  Therefore, in the imaging apparatus 100B, when the object recognition unit 109 recognizes that there are regions where a plurality of attributes overlap, a plurality of shootings (so-called bracket shooting) using shooting parameters corresponding to each of the plurality of attributes. Automatically). FIG. 9 is a diagram schematically illustrating shooting parameters set for a plurality of shot images shot when there are regions where a plurality of different attributes overlap.

  In the photographed image 1 of FIG. 9A, photographing parameters adapted to the attributes of “sky”, “building”, and “mountain” are applied to the “sky”, “building”, and “mountain” regions. The image is shown. Similarly, the photographed image 2 in FIG. 9B has photographing parameters that are adapted to the attributes of “sky”, “building”, and “forest” in the “sky”, “building”, and “forest” areas. Indicates an applied image. In the photographed image 3 of FIG. 9C, photographing parameters adapted to the attributes of “sky”, “building”, and “tree” are applied to the “sky”, “building”, and “tree” areas. The image is shown.

  At this time, the same shooting parameters are set in FIGS. 9A to 9C for the “empty” region where there is no overlapping of different attributes, and the “building” region is the same as in the case of “empty”. Thus, the shooting parameters are set. On the other hand, for “mountains”, “forests”, and “trees” having different attributes, the shooting parameters of “mountains”, “forests”, and “trees” are set in the corresponding areas. That is, in the example of FIG. 9, three captured images with different imaging parameters are captured. In the following, a process for shooting a plurality of images by changing shooting parameters when there are regions where a plurality of different attributes overlap will be described with reference to the flowchart of FIG.

  FIG. 10 is a flowchart of processing for capturing a plurality of images by changing the imaging parameters in the imaging apparatus 100B. Each process illustrated in FIG. 10 is realized by the CPU of the control unit 105 developing a program stored in the ROM on the RAM and controlling the operation of each unit configuring the imaging apparatus 100A.

  Since the processes in steps S1001 and S1002 are the same as steps S401 and 402 described with reference to FIG. 4, the description thereof is omitted here. In step S1003, the control unit 105 determines whether there is an area where a plurality of attributes overlap. If there is a region where a plurality of attributes overlap (YES in S1003), control unit 105 advances the process to step S1004. If there is no region where a plurality of attributes overlap (NO in S1003), control proceeds to step S1009. .

  In step S1004, one of a plurality of overlapping attributes in a certain area is selected as an attribute to be imaged. In subsequent step S1005, shooting parameter setting unit 110 sets shooting parameters based on the attribute selected in step S1004 and shooting parameters based on the attribute of the region having no attribute overlap in each corresponding region. In step S1006, the control unit 105 performs shooting processing using the shooting parameters set in step S1005. In step S1007, the storage unit 107 stores the captured image in a predetermined storage medium.

  Subsequently, in step S1008, the control unit 105 determines whether or not imaging with all attributes for a region where a plurality of attributes overlap is completed. If shooting has not been completed (NO in S1008), the control unit 105 returns the process to step S1004, and if shooting has been completed (YES in S1008), ends the shooting process.

  In step S1009, since the shooting parameter setting unit 110 has only one recognized combination of attributes, the shooting parameter setting unit uniquely sets shooting parameters corresponding to the attributes. Since the contents of the processes in steps S1010 and S1011 are the same as those in steps S1006 and S1007, the description thereof is omitted. By the end of the process in step S1011, the main photographing process is ended.

  As described above, according to the second embodiment, when there are regions in which a plurality of attributes overlap in a captured image, images are captured by sequentially optimizing the shooting parameters for each detected attribute. . Therefore, the user does not need to perform determination and operation such as designating the main subject, and can easily obtain a high-quality image.

  On the other hand, in the shooting method described with reference to FIGS. 9 and 10, the number of shots increases by the number of duplicate attributes, and some shot images are shot under shooting conditions not intended by the photographer. There is a risk of increased images. In addition, when there are attributes having the same shooting parameter among a plurality of attributes, a plurality of similar images are captured as a result, and unnecessary images are stored.

  If the images are similar, a plurality of images are not necessary and one image is considered to be sufficient. Therefore, when there are areas where a plurality of attributes overlap, and there are those with a small difference in shooting parameters among the plurality of attributes, shooting is performed with the shooting parameters of one attribute of the plurality of attributes, The number of shots will be reduced. Hereinafter, a process of performing shooting while reducing the number of shots when there are regions where a plurality of different attributes overlap will be described with reference to the flowchart of FIG.

  FIG. 11 is a flowchart of shooting parameter setting processing for shooting an image by reducing the number of shots in the imaging apparatus 100B. The process of the flowchart of FIG. 11 is a process executed by replacing the process of steps S1004 to S1005 in the series of imaging processes shown in FIG.

  In step S1101, the shooting parameter setting unit 110 generates shooting parameters based on each of the plurality of attributes as shooting candidate parameters. In subsequent step S1102, the shooting parameter setting unit 110 calculates the similarity between the shooting candidate parameters generated in step S1101. Thereafter, in step S1103, the shooting parameter setting unit 110 determines whether there is a shooting candidate parameter with a high degree of similarity. Note that there is no particular limitation on a method for determining whether or not the degree of similarity is high. For example, the determination may be made simply based on whether or not the difference in imaging parameters is smaller than a predetermined value. If there is a shooting candidate parameter with a high degree of similarity (YES in S1103), the shooting parameter setting unit 110 advances the process to step S1104. If there is no shooting candidate parameter with a high degree of similarity (YES in S1103), the shooting parameter setting unit 110 advances the process to step S1105. Proceed to

  In step S1104, the shooting parameter setting unit 110 sets one of the shooting candidate parameters having a high similarity as the shooting parameter. At this time, other imaging candidate parameters with high similarity are discarded. In step S1104, one shooting parameter may be generated from a plurality of similar shooting candidate parameters. In step S1105, the shooting parameter setting unit 110 sets one of the shooting candidate parameters generated in step S1101 as a shooting parameter. If there is no high similarity among the plurality of shooting candidate parameters generated in step S1101, as a result, shooting is performed using the shooting parameters of the plurality of shooting candidate parameters generated in step S1101. It will be. When the shooting parameters are set in steps S1104 and S1105, this process ends. Through the above processing, unnecessary shooting with similar shooting parameters can be reduced.

  In the processing of the flowchart of FIG. 11, in order not to increase the number of shots unnecessarily, a maximum value of the number of images to be shot (hereinafter referred to as “maximum number of shots”) can be set based on one shooting instruction. You may do it. In this case, the shooting instruction unit 112 can set not only the shooting timing but also the maximum number of shots. Specifically, when there are areas where a plurality of attributes overlap, whether the number of the plurality of attributes is equal to or less than the maximum number of shots that is a preset threshold is determined by the control unit 105 or the shooting parameter. The setting unit 110 or the object recognition unit 109 determines.

  If the number of attributes is equal to or less than the maximum number of shots, shooting parameters are sequentially set for each attribute and shooting is performed. On the other hand, if the number of attributes exceeds the maximum number of shots, the number of shooting parameters for actual shooting is narrowed down to the maximum number of shots. As a narrowing-down method, there is a method of selecting a shooting parameter so that a variance value becomes larger from shooting parameters determined based on each of a plurality of attributes. In this way, the number of shots can be reduced.

<Other embodiments>
Although the present invention has been described in detail based on preferred embodiments thereof, the present invention is not limited to these specific embodiments, and various forms within the scope of the present invention are also included in the present invention. included. Furthermore, each embodiment mentioned above shows only one embodiment of this invention, and it is also possible to combine each embodiment suitably.

  For example, in the present embodiment, one imaging device 100A, 100B acquires and analyzes a subject image, and performs shooting by determining an attribute of an object (subject), setting shooting parameters, and the like based on the analysis result. An example was taken up. However, the present invention is not limited to this, and the camera unit that acquires the subject image and the control unit that analyzes the subject image and controls the camera unit by determining the attribute of the object and setting the shooting parameters based on the analysis result communicate with each other. Another possible device may be used. For example, shooting information (RAW data) generated by shooting by the camera unit is transmitted to an external information processing apparatus (for example, a personal computer) as a control unit via a network or the like. Then, the information processing apparatus analyzes the acquired RAW data to determine the shooting condition in the camera unit, transmits the determined shooting condition to the camera unit via a network or the like, and the camera unit performs shooting under the received shooting condition. The structure to perform may be sufficient.

  The present invention can also be realized by executing the following processing. That is, software (program) that realizes the functions of the above-described embodiments is supplied to a system or apparatus via a network or various storage media, and a computer (or CPU, MPU, etc.) of the system or apparatus reads the program code. It is a process to be executed. In this case, the program and the storage medium storing the program constitute the present invention.

100A, 100B Imaging apparatus 101 Imaging optical system 102 Imaging element 103 Analog signal processing unit 104 A / D conversion unit 105 Control unit 106 Image processing unit 107 Storage unit 108 Display unit 109 Object recognition unit 110 Imaging parameter setting unit 111 Object specification unit 112 Shooting instruction section

Claims (13)

Imaging means;
Display means for displaying an image obtained by the imaging means;
Recognizing means for recognizing the attribute of the object and its area in the image obtained by the imaging means;
Control means for switching each attribute of the plurality of attributes and the area to be displayed on the display means when the recognition means recognizes that the predetermined area in the image has a plurality of attributes;
Designation means for designating an attribute designated by the user from among the attributes displayed on the display means as an attribute of the main subject;
An imaging apparatus comprising: setting means for setting a shooting parameter in an area corresponding to the attribute based on an attribute designated as a main subject by the designation means.   The imaging apparatus according to claim 1, wherein the control unit displays the attribute recognized by the recognition unit and the region of the attribute superimposed on the image obtained by the imaging unit.   When the recognizing unit recognizes that the predetermined area in the image has a plurality of attributes, the control unit has attributes having similar imaging parameters set by the setting unit among the plurality of attributes. 3. The imaging apparatus according to claim 1, wherein in some cases, grouping is performed in which these attributes are treated as equivalent attributes. 4.   The control means displays the object area recognized as having the plurality of attributes in the image by the recognition means and the object area recognized as not having the plurality of attributes in the display means by different display methods. The image pickup apparatus according to claim 1, wherein the image pickup apparatus displays the image.   5. The imaging according to claim 1, wherein the specifying unit specifies an attribute of an object specified by an operation on a touch panel provided in the display unit as an attribute of the main subject. apparatus. Imaging means;
Recognizing means for recognizing the attribute of the object and its area in the image obtained by the imaging means;
Setting means for setting shooting parameters based on the attribute recognized by the recognition means and its area;
Instruction means for instructing photographing by the imaging means;
When the recognizing unit recognizes that there is a region in which a plurality of attributes overlap in the image obtained by the imaging unit, when there is a shooting instruction by the instruction unit, shooting according to each of the plurality of attributes An image pickup apparatus comprising: a control unit that takes a plurality of images by applying a parameter to a region corresponding to the attribute.   The imaging apparatus according to claim 6, wherein the setting unit sets an imaging parameter for each attribute and area of the object recognized by the recognition unit in the image.   When the recognition unit recognizes that there is a region where a plurality of attributes overlap in the image, and there is a small difference in shooting parameters among the plurality of attributes, the control unit The imaging apparatus according to claim 6 or 7, wherein the imaging is performed with one of the small imaging parameters.   When the recognition unit recognizes that there is a region where a plurality of attributes overlap in the image, and there is a small difference in shooting parameters among the plurality of attributes, the control unit The imaging apparatus according to claim 6 or 7, wherein imaging is performed with one imaging parameter generated from a small imaging parameter. When the recognition means recognizes that there is a region where a plurality of attributes overlap in the image,
The instruction means sets a maximum number of images to be photographed by the imaging means,
The setting unit selects a shooting parameter so that a variance value becomes larger from shooting parameters determined based on each of the plurality of attributes when the number of the plurality of attributes is larger than the maximum number of shots. The image pickup apparatus according to claim 6, wherein the number of images taken by the image pickup unit is narrowed to the maximum number of shots or less. A method for controlling an imaging apparatus,
A recognition step for recognizing the attribute of the object and its region in the image obtained by the imaging means;
When the recognition step recognizes that a predetermined area in the image has a plurality of attributes, a display step of switching and displaying each attribute of the plurality of attributes and the area on the display means;
A designation step for designating an attribute designated by the user from among the attributes displayed on the display means as an attribute of the main subject;
A setting step for setting a shooting parameter based on the attribute specified as the main subject in the specifying step in an area corresponding to the attribute;
An imaging apparatus control method comprising: an imaging step of performing imaging by the imaging means with the imaging parameters set in the setting step. A method for controlling an imaging apparatus,
A recognition step for recognizing the attribute of the object and its region in the image obtained by the imaging means;
When it is recognized in the recognition step that there is a region where a plurality of attributes overlap in the image, when a shooting instruction is given, a shooting parameter corresponding to each of the plurality of attributes is set to a region corresponding to the attribute. An imaging device control method comprising: an imaging step of performing imaging of a plurality of applied images.   A program for causing a computer to execute the control method for an imaging apparatus according to claim 11.