JP2014033265A - Imaging device, imaging method, and program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an imaging device, an imaging method, and a program that are capable of performing photographing while focusing on a tracked subject even when the tracked subject cannot be detected by pattern matching based on face detection.SOLUTION: An imaging device 1 comprises a photographing control unit 221d that, when a subject detection unit 207b has succeeded in detecting a subject in a predetermined posture state in a case where a face detection unit 207a cannot detect a person's face, executes tracking processing for performing tracking while changing a photographing parameter for an area of the subject.

Description

  The present invention relates to an imaging apparatus, an imaging method, and a program for imaging a subject and generating image data of the subject.

  In recent years, an imaging device such as a digital camera detects a tracking subject to be tracked while matching the imaging device's focus position between adjacent images by pattern matching based on face detection, and shoots in an optimal state for the detected tracking subject. The technique to do is known (refer patent document 1). In this technique, image processing is performed on the tracking subject in an optimal state by performing image processing of image parameters associated in advance with the face of the tracking subject detected by pattern matching based on face detection.

JP 2012-70222 A

  By the way, in the above-described conventional technology, even if the tracking subject is captured in the image, if the face of the tracking subject cannot be detected by pattern matching based on face detection, the focus position of the imaging device cannot be adjusted. There has been a problem that the subject to be tracked is shot out of focus or shot with an inappropriate exposure.

  The present invention has been made in view of the above, and even when a tracking subject cannot be detected by pattern matching based on face detection, it is possible to perform shooting that focuses on the tracking subject. An object is to provide an imaging apparatus, an imaging method, and a program.

  In order to solve the above-described problems and achieve the object, an imaging apparatus according to the present invention includes a plurality of lenses, and a lens unit that collects light from a predetermined field of view, and the light is collected by the lens unit. From an imaging unit that receives light and generates electronic image data continuously in time, a face detection unit that detects a human face from an image corresponding to the image data, and an image corresponding to the image data When a subject detection unit that detects a subject in a predetermined posture state and the face detection unit cannot detect the face of the person and the subject detection unit detects the subject, an area corresponding to the subject is detected. And a shooting control unit that executes a tracking process for tracking between images that are temporally adjacent to each other while changing the shooting parameter.

  Further, the imaging apparatus according to the present invention is the above-described invention, wherein the subject is extracted based on the feature point extracting unit that extracts the feature points of each part constituting the subject and the feature points extracted by the feature point extracting unit. A subject information generating unit that generates subject information used when specifying the posture of the subject, wherein the subject detecting unit has a degree of coincidence with the subject information generated by the subject information generating unit equal to or greater than a predetermined threshold value. It is characterized by detecting a subject in a certain posture state.

  In the imaging device according to the present invention, in the above invention, a joint model generation unit that generates a joint model that models a person with a plurality of joints based on the feature points extracted by the feature point extraction unit. The subject information generation unit generates the subject information with reference to the joint model generated by the joint model generation unit.

  The imaging apparatus according to the present invention further includes an operation input unit that receives an input of a selection signal for selecting any one of a plurality of persons included in the image, and the subject information generation unit includes the face information When the detection unit detects a person's face according to the selection signal, the subject information of the person is generated.

  In the image pickup apparatus according to the present invention, in the above invention, a recording unit that records the image data, a display unit that displays an image corresponding to the image data, and a plurality of images included in the image displayed by the display unit. An operation input unit that receives an input of a selection signal for selecting one of the persons, and the subject information generation unit reproduces the image recorded by the recording unit by the display unit In this case, when the face detection unit detects a person's face according to the selection signal, the subject information of the person is generated.

  In the image pickup apparatus according to the present invention as set forth in the invention described above, the photographing parameter is any one of a focus position of the lens unit, an exposure value, an optical zoom and an electronic zoom of the lens unit.

  In the imaging device according to the present invention, in the above invention, the photographing control unit may detect the subject when the subject detection unit detects the subject when the face detection unit cannot detect the face of the person. A tracking process is performed in which the generation timing of the imaging unit tracks between adjacent images while adjusting the focus position of the lens unit with respect to a corresponding region.

  Further, the imaging apparatus according to the present invention further includes a subject setting unit that sets a tracking subject to be tracked while focusing the lens unit between images whose generation timings by the imaging unit are temporally adjacent to each other in the above invention. The face detection unit detects a face of the tracking subject from a plurality of persons included in the image corresponding to the image data, and the subject detection unit detects a plurality of subjects included in the image corresponding to the image data. When the face detection unit detects the face of the tracking subject, the shooting control unit performs tracking while adjusting the focus position of the lens unit to the area of the face of the tracking subject. While the one tracking process is executed, the subject detection unit can detect the tracking subject when the face detection unit cannot detect the face of the tracking subject. , And executes the second tracking processing for tracking while focus position of the lens portion in a region corresponding to 該追 tail object.

  In addition, an imaging method according to the present invention includes a lens unit that collects light from a predetermined field of view, and receives light collected by the lens unit to convert electronic image data into time. An image capturing method executed by an image capturing apparatus including a continuously generated image capturing unit, wherein a face detecting step for detecting a human face from an image corresponding to the image data, and the face detecting step When the face of the subject cannot be detected, a subject detection step for detecting a subject in a predetermined posture state from an image corresponding to the image data, and when the subject can be detected by the subject detection step, the subject is detected. A shooting control step for executing a tracking process for tracking between images whose generation timings by the imaging unit are temporally adjacent to each other while changing shooting parameters for an area. It is characterized in.

  The program according to the present invention includes a plurality of lenses, a lens unit that collects light from a predetermined field of view, and light that is collected by the lens unit to receive electronic image data temporally. A program that is executed by an imaging device comprising: a face detection step for detecting a face of a subject with respect to an image corresponding to the image data; and the face detection step. When the face of the subject cannot be detected, a subject detection step for detecting a subject in a pre-recorded posture state with respect to the image, and when the subject is detected in the subject detection step, an area corresponding to the subject is detected. And a shooting control step of executing a tracking process for tracking between images whose generation timing by the imaging unit is temporally adjacent while changing the shooting parameters. It is characterized in.

  According to the present invention, when the shooting control unit cannot detect a human face by the face detection unit, or when the subject in the predetermined posture state detected by the subject detection unit can be detected, the shooting parameter is set for the region of the subject. The tracking processing for tracking between the images whose generation timings by the imaging unit are temporally adjacent to each other is executed. Thereby, even when the tracking subject cannot be detected by the pattern matching based on the face detection, there is an effect that it is possible to perform shooting with focusing on the tracking subject.

FIG. 1 is a block diagram showing a configuration of an imaging apparatus according to an embodiment of the present invention. FIG. 2 is a diagram illustrating an example of subject information recorded by the subject information recording unit of the imaging apparatus according to the embodiment of the present invention. FIG. 3 is a diagram showing another example of subject information recorded by the subject information recording unit of the imaging apparatus according to the embodiment of the present invention. FIG. 4 is a flowchart showing the contents of processing executed by the imaging apparatus according to the embodiment of the present invention. FIG. 5 is a diagram schematically illustrating an outline when a tracking subject is set for an image displayed by the display unit of the imaging apparatus according to the embodiment of the present invention. FIG. 6 is a diagram illustrating an example of an image displayed by the display unit of the imaging apparatus according to the embodiment of the present invention. FIG. 7 is a flowchart showing an overview of the tracking subject dictionary generation process of FIG. FIG. 8 is a flowchart showing an outline of the joint modeling process of FIG. FIG. 9 is a diagram schematically illustrating an outline of a joint model generation method for a tracking subject by the joint model generation unit of the imaging apparatus according to the embodiment of the present invention. FIG. 10 is a flowchart showing an overview of the second tracking process of FIG.

  DESCRIPTION OF EMBODIMENTS Hereinafter, embodiments for carrying out the present invention (hereinafter referred to as “embodiments”) will be described with reference to the drawings. In the following description, the same portions are denoted by the same reference numerals. Note that the present invention is not limited to the embodiments.

  FIG. 1 is a block diagram showing a configuration of an imaging apparatus according to an embodiment of the present invention. An imaging apparatus 1 shown in FIG. 1 includes a main body unit 2 and a lens unit 3 that is detachably attached to the main body unit 2 and collects light from a predetermined visual field region.

  The main body 2 includes a shutter 201, a shutter driving unit 202, an image sensor 203, an image sensor driving unit 204, a signal processing unit 205, an A / D conversion unit 206, an image processing unit 207, and a distance measurement calculation. Unit 208, AE processing unit 209, AF processing unit 210, image compression / decompression unit 211, operation input unit 212, display unit 213, display drive unit 214, recording medium 215, memory I / F 216, , An SDRAM (Synchronous Dynamic Random Access Memory) 217, a flash memory 218, a main body communication unit 219, a bus 220, and a control unit 221.

  The shutter 201 sets the state of the image sensor 203 to an exposure state or a light shielding state. The shutter drive unit 202 is configured using a stepping motor or the like, and drives the shutter 201 in accordance with a signal input from the control unit 221.

  The image sensor 203 receives the light collected by the lens unit 3 and generates electronic image data continuously in time. Specifically, the image sensor 203 is configured using a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor) that receives the light collected by the lens unit 3 and converts it into an electrical signal. The image sensor 203 includes a phase difference AF (auto-Focus) element 203a. The phase difference AF element 203 a receives a pair of focus detection light beams that pass through the exit pupil of the lens unit 3. The phase difference AF element 203 a outputs a pair of signals for phase difference AF detection corresponding to the received pair of focus detection light beams to the signal processing unit 205.

  The image sensor driving unit 204 outputs image data (analog signal) from the image sensor 203 to the signal processing unit 205 at a predetermined timing. In this sense, the image sensor driving unit 204 functions as an electronic shutter.

  The signal processing unit 205 performs analog processing such as noise reduction processing, gain increase processing, and waveform shaping processing on the analog signal input from the image sensor 203 and outputs the analog signal to the A / D conversion unit 206.

  The A / D conversion unit 206 generates digital image data by performing A / D conversion on the analog signal input from the signal processing unit 205, and outputs the digital image data to the SDRAM 217 via the bus 220.

  The image processing unit 207 acquires image data (RAW data) from the SDRAM 217 via the bus 220 and performs various types of image processing on the acquired image data. The image data subjected to this image processing is output to the SDRAM 217 via the bus 220. Here, as image processing, optical black reduction processing, white balance adjustment processing, color matrix calculation processing, gamma correction processing, color reproduction processing, edge enhancement processing, and image data synchronization when the image sensor 203 is a Bayer array Processing. The image processing unit 207 includes a face detection unit 207a, a subject detection unit 207b, and a feature point extraction unit 207c.

  The face detection unit 207a detects a human face from the image corresponding to the image data by pattern matching. Specifically, the face detection unit 207a detects a face in the image by performing pattern matching based on part information indicating the characteristics of each part constituting the human body recorded in the flash memory 218 described later. By detecting the positions of facial feature points such as eyes, nose and mouth, the face position, face size (size), face orientation, face angle (tilt), etc. are detected. The face detection unit 207a also selects an image corresponding to the image data based on subject information recorded in a subject information recording unit 218b of the flash memory 218 described later from among a plurality of subjects included in the image corresponding to the image data. The face of the tracking subject is detected from a plurality of subjects included in. Note that the face detection unit 207a may detect not only a human face but also a face such as a dog or a cat. Furthermore, the face detection unit 207a may detect a human face using a known technique other than pattern matching.

  The subject detection unit 207b detects a subject in a predetermined posture state from an image corresponding to the image data. Specifically, the subject detection unit 207b has a predetermined degree of coincidence with subject information recorded in a subject information recording unit 218b of a flash memory 218 described later from among a plurality of subjects included in the image corresponding to the image data. An object that is equal to or greater than the threshold is detected. For example, the subject detection unit 207b performs pattern matching on a plurality of subjects included in the image corresponding to the image data using subject information recorded in a subject information recording unit 218b of the flash memory 218 described later, A subject whose degree of coincidence with information is a predetermined value or more is detected as a tracking subject whose generation timing by the image sensor 203 moves between temporally adjacent images.

  The feature point extraction unit 207c is configured to detect each of the parts constituting the body with respect to a subject to be tracked while adjusting the focus position of the lens unit 3 between images whose generation timings are temporally adjacent to each other (hereinafter referred to as “tracking subject”). Extract feature points. Specifically, the feature point extraction unit 207c, based on the part information recorded by the part information recording unit 218c of the flash memory 218 described later, each part constituting the body of the tracking subject, such as the head, arm, shoulder, hand, etc. Extract feature points such as waist, torso and legs.

  The distance measurement calculation unit 208 calculates the distance from the imaging device 1 to the subject based on the phase difference between the pair of image signals output from the phase difference AF element 203a, and outputs the calculated result to the control unit 221.

  The AE processing unit 209 acquires image data recorded in the SDRAM 217 via the bus 220, and sets an exposure condition when performing still image shooting or moving image shooting based on the acquired image data. Specifically, the AE processing unit 209 calculates the luminance from the image data, and performs automatic exposure of the imaging apparatus 1 by determining, for example, an aperture value (f value) and a shutter speed based on the calculated luminance. .

  The AF processing unit 210 acquires image data recorded in the SDRAM 217 via the bus 220, and adjusts the automatic focus of the imaging apparatus 1 based on the acquired image data. For example, the AF processing unit 210 extracts a high-frequency component signal from the image data, and performs AF (Auto Focus) calculation processing (contrast method) on the high-frequency component signal, thereby evaluating the focus of the imaging apparatus 1. By making the determination, the automatic focus of the image pickup apparatus 1 is adjusted. The AF processing unit 210 also adjusts the focus adjustment state of the lens unit 3 corresponding to the subject image formed on the image sensor 203 based on the phase difference between the pair of image signals output from the phase difference AF element 203a. The automatic focus adjustment of the imaging apparatus 1 is performed by a pupil division type phase difference detection method for calculating (defocus amount).

  The image compression / decompression unit 211 acquires image data from the SDRAM 217 via the bus 220, compresses the acquired image data according to a predetermined format, and outputs the compressed image data to the SDRAM 217. Here, the predetermined format includes a JPEG (Joint Photographic Experts Group) system, a Motion JPEG system, and an MP4 (H.264) system. In addition, the image compression / decompression unit 211 acquires image data (compressed image data) recorded on the recording medium 215 via the bus 220 and the memory I / F 216, expands (decompresses) the acquired image data, and transfers it to the SDRAM 217. Output.

  The operation input unit 212 instructs a release button 212a that receives an input of an instruction signal for instructing still image shooting, a moving image button 212b that receives an input of an instruction signal for instructing moving image shooting, and switching of the shooting mode of the imaging apparatus 1. A mode switching button 212c that accepts an input of an instruction signal, a menu button 212d that accepts an input of an instruction signal that instructs setting of various parameters of the imaging apparatus 1, and an instruction signal that instructs the reproduction of image data recorded on the recording medium 215 Are provided on the display screen of the display unit 213, and a contact from the outside is detected at the detected position. A touch panel 212g for receiving an input of a corresponding instruction signal. The release button 212a can be advanced and retracted by pressing from the outside. When the release button 212a is half-pressed, a 1st release signal that instructs a sequential shooting operation is input. On the other hand, when the release button 212a is fully pressed, a 2nd release signal instructing still image shooting is input.

  The display unit 213 displays an image corresponding to the image data. The display unit 213 is configured using a display panel made of liquid crystal, organic EL (Electro Luminescence), or the like. The display driving unit 214 acquires image data recorded by the SDRAM 217 via the bus 220 and causes the display unit 213 to display an image corresponding to the acquired image data. Here, for image display, a rec view display that displays image data immediately after shooting for a predetermined time (for example, 3 seconds), a reproduction display that reproduces image data recorded on the recording medium 215, and an image sensor 203 are continuously displayed. Live view display that sequentially displays live view images corresponding to image data to be generated in time series. In addition, the display unit 213 appropriately displays operation information of the imaging device 1 and information related to shooting.

  The recording medium 215 records image data generated by the image sensor 203, image data subjected to image processing by the image processing unit 207, image data processed by the image compression / decompression unit 211, RAW data, and the like. The recording medium 215 is configured using a memory card or the like that is attached from the outside of the imaging device 1 and is detachably attached to the imaging device 1 via the memory I / F 216.

  The SDRAM 217 temporarily records image data input from the A / D conversion unit 206 via the bus 220, image data input from the image processing unit 207, and information being processed by the imaging apparatus 1. For example, the SDRAM 217 temporarily records image data that the image sensor 203 sequentially outputs for each frame via the signal processing unit 205, the A / D conversion unit 206, and the bus 220.

  The flash memory 218 includes a program recording unit 218a that records various programs for operating the imaging apparatus 1, various data used during execution of the program, various parameters necessary for image processing operation by the image processing unit 207, and the like. The subject information recording unit 218b that records subject information related to the tracking subject, the face detection unit 207a, the subject detection unit 207b, and the feature point extraction unit 207c constitute a human body that is referred to when pattern matching is performed on the subject. A parts information recording unit 218c that records part information relating to each part.

  Here, the subject information recorded by the subject information recording unit 218b will be described. FIG. 2 is a diagram illustrating an example of subject information recorded by the subject information recording unit. FIG. 3 is a diagram illustrating another example of subject information recorded by the tracking subject state recording unit.

  The tracking subject dictionary table T1 shown in FIG. 2 describes subject information related to the tracking subject used by the face detection unit 207a for pattern matching. Specifically, the tracking subject dictionary table T1 includes a dictionary item, a dictionary detail item, a parameter, a pattern matching result, and a tracking classification. For example, when the dictionary item is “face”, “face size”, “hairstyle” and “glasses” are described in the dictionary detail item, and “R = 20” indicating the size of the face size in the parameter, hairstyle "Shaved" indicating "" and "Yes" indicating the presence or absence of glasses are described respectively. Furthermore, it is described as “first tracking subject determination information” in the tracking category.

  Further, the tracking subject dictionary table T2 shown in FIG. 3 describes subject information related to the tracking subject used by the subject detection unit 207b for pattern matching. Specifically, the tracking subject dictionary table T2 includes a dictionary item, a dictionary detail item, a parameter, a pattern matching result, a tracking category, and a posture category. For example, when the dictionary item is “how to run”, “details” of the dictionary includes “arm angle”, “step length”, “upper body angle”, and “running cycle”, and the parameter “20” indicating the arm angle. “100 °” indicating the stride, “30 °” indicating the angle of the upper body, and “3.6 steps / S” indicating the running cycle are described. Furthermore, it is described as the second tracking subject determination information in the tracking section, and is described as “running posture” in the posture section. As described above, the tracking subject dictionary table T1 and the tracking subject dictionary table T2 describe subject information when the subject detection unit 207b performs pattern matching on the tracking subject according to the posture state.

  The main body communication unit 219 is a communication interface for performing communication with the lens unit 3 attached to the main body unit 2. The main body communication unit 219 includes an electrical contact with the lens unit 3.

  The bus 220 functions as a transmission path that connects each component of the imaging device 1. The bus 220 transfers various data generated inside the imaging apparatus 1 to each component of the imaging apparatus 1.

  The control unit 221 is configured using a CPU (Central Processing Unit) or the like, and controls signals and signals to each unit configuring the imaging apparatus 1 in accordance with an instruction signal input from the operation input unit 212 via the bus 220. By performing transmission of various data, the operation of the imaging device 1 is comprehensively controlled. Specifically, when a 2nd release signal is input from the release button 212a, the control unit 221 performs control to start a still image shooting operation in the imaging device 1. Here, the still image shooting operation in the image pickup apparatus 1 means that the signal processing unit 205 and the image processing unit 207 perform predetermined processing on image data output from the image pickup device 203 by driving the shutter drive unit 202 and the image pickup device drive unit 204. This is the operation to perform the process. The image data processed in this way is compressed by the image compression / decompression unit 211 according to a predetermined format, and is recorded on the recording medium 215 via the bus 220 and the memory I / F 216. In this embodiment, the recording medium 215 forms a part of the recording unit. However, a recording area having the function of the recording unit is secured inside the imaging apparatus 1 separately from the recording medium 215, and this recording area is recorded. The image data may be recorded on the.

  Here, a detailed configuration of the control unit 221 will be described. The control unit 221 includes a tracking subject setting unit 221a, a joint model generation unit 221b, a subject information generation unit 221c, an imaging control unit 221d, and a display control unit 221e.

  The tracking subject setting unit 221a sets a tracking subject from a plurality of subjects included in the image in accordance with an instruction signal input from the operation input unit 212. Specifically, the tracking subject setting unit 221a sets the subject selected according to the instruction signal input from the touch panel 212g as the tracking subject.

  The joint model generation unit 221b models a tracking subject using a plurality of joints as a person or an animal based on the part information recorded by the parts information recording unit 218c and the feature points extracted from the tracking subject by the feature point extraction unit 207c. Generate a joint model. Specifically, the joint model generation unit 221b is a joint model of each part of the tracking subject, for example, a joint model of a person modeled by straight lines connecting the joints of the head, shoulders, hands, and feet with the trunk as a reference. Is generated.

  The subject information generation unit 221c uses subject information used when specifying the posture of the subject based on the feature points extracted from the tracking subject by the feature point extraction unit 207c and the joint model of the tracking subject generated by the joint model generation unit 221b. And the generated subject information is recorded in the subject information recording unit 218b.

  When the face detection unit 207a cannot detect a human face from the image and the subject detection unit 207b can detect a subject in a predetermined posture state from the image, the shooting control unit 221d takes a picture of the subject area. A tracking process for tracking between adjacent images is executed while changing parameters. Here, the shooting parameters are the focus position of the lens unit 3, the exposure value of the imaging device 1, the position of the electronic zoom by the image processing unit 207 (trimming area), the exposure time of the imaging device 1, the shutter speed, the ISO sensitivity, and the display. The brightness of the live view image displayed by the unit 213, the image size, and the like. In addition, when the face detection unit 207b cannot detect a human face from the image and the subject detection unit 207b can detect a subject in a predetermined posture state from the image, the shooting control unit 221d corresponds to the region of the subject. A tracking process for tracking the lens unit 3 while adjusting the focus position of the lens unit 3 is executed. Specifically, when the face detection unit 207a can detect the face of the tracking subject set by the subject setting unit 221a, the imaging control unit 221d detects that the lens unit 3 has a position corresponding to the face area of the tracking subject. While performing the first tracking process for tracking while adjusting the focus position, the subject detection unit 207b can detect the tracking subject when the face detection unit 207a cannot detect the face of the tracking subject set by the subject setting unit 221a. At this time, a second tracking process is performed in which tracking is performed while adjusting the focus position of the lens unit 3 to a position corresponding to the area of the tracking subject.

  The display control unit 221e controls the display mode of the display unit 213. Specifically, the display control unit 221e drives the display driving unit 214 to display an image corresponding to the image data on the display unit 213. The display control unit 221e also causes the display unit 213 to display the information related to the subject set by the tracking subject setting unit 221a on the image.

  For the main body 2 having the above-described configuration, an audio input / output unit, an auxiliary light emitting unit that emits auxiliary light (flash) to a subject, and a function of bidirectionally transmitting to an external device via the Internet You may provide further the communication part etc. which have.

  Next, the configuration of the lens unit 3 will be described. The lens unit 3 includes an optical system 301, a lens driving unit 302, a diaphragm 303, a diaphragm driving unit 304, a lens operation unit 305, a lens flash memory 306, a lens communication unit 307, a lens control unit 308, Is provided.

  The optical system 301 collects light from a predetermined visual field region. The optical system 301 is configured using a plurality of lenses. The optical system 301 has an optical zoom function for changing the focal length and a focus function for changing the focus. The lens driving unit 302 changes the focus position, the focal length, and the like of the optical system 301 by moving the optical system 301 along the optical axis L.

  The diaphragm 303 adjusts exposure by limiting the amount of incident light collected by the optical system 301. The aperture driving unit 304 is configured using a stepping motor or the like, and drives the aperture 303.

  The lens operation unit 305 is a ring provided around the lens barrel of the lens unit 3, and instructs the input of an instruction signal for starting the optical zoom operation in the lens unit 3 or the adjustment of the focus position in the lens unit 3. An input of an instruction signal is accepted. The lens operation unit 305 may be a push-type switch or a lever-type switch that can be switched on or off.

  The lens flash memory 306 records a control program for determining the position and movement of the optical system 301, the lens characteristics of the optical system 301, and various parameters.

  The lens communication unit 307 is a communication interface for communicating with the main body communication unit 219 of the main body unit 2 when the lens unit 3 is attached to the main body unit 2.

  The lens control unit 308 is configured using a CPU or the like, and controls the operation of the lens unit 3 in accordance with an instruction signal input from the lens operation unit 305 or an instruction signal input from the main body unit 2. Specifically, the lens control unit 308 drives the lens driving unit 302 in accordance with an instruction signal input from the imaging control unit 221d and performs focusing of the lens unit 3. Further, the lens control unit 308 changes the aperture value of the aperture 303 by driving the aperture drive unit 304 in accordance with the instruction signal input from the imaging control unit 221d. Further, the lens control unit 308, when the lens unit 3 is attached to the main body unit 2, via the lens communication unit 307, the focus position information, focal length information, brightness information (f value), lens, The unique information for identifying the unit 3 is transmitted to the main unit 2.

  An outline of processing performed by the imaging apparatus 1 configured as described above will be described. FIG. 4 is a flowchart illustrating an outline of processing performed by the imaging apparatus 1.

  In FIG. 4, first, the case where the imaging apparatus 1 is not set to the shooting mode (step S101: No) will be described. In this case, the display control unit 221e causes the display unit 213 to display an image corresponding to the image data recorded on the recording medium 215 (step S102).

Subsequently, the control unit 221 determines whether a tracking subject has been selected (step S103). Specifically, as illustrated in FIG. 5, the control unit 221 determines whether a tracking subject has been selected via the touch panel 212 g when the display unit 213 displays the image W ₁ . When the control unit 221 determines that the tracking subject has been selected (step S103: Yes), the imaging device 1 proceeds to step S104. On the other hand, when the control unit 221 determines that the tracking subject is not selected (step S103: No), the imaging device 1 returns to step S101.

  In step S104, the tracking subject setting unit 221a sets the selected subject as a tracking subject. At this time, as illustrated in FIG. 5, the subject information generation unit first sets information on the size of the subject face F1 detected by the face detection unit 207a, the hairstyle, and the presence / absence of glasses for the selected subject A1. It is recorded in the subject information recording unit 218b as subject information of the tracking section. After step S104, the imaging apparatus 1 returns to step S101.

  A case where the imaging apparatus 1 is set to the shooting mode in step S101 (step S101: Yes) will be described. In this case, the imaging control unit 221d causes the AE processing unit 209 to execute AE processing (step S105), and causes the AF processing unit 210 to execute AF processing (step S106). At this time, the imaging control unit 221d causes the AE processing by the AE processing unit 209 and the AF processing by the AF processing unit 210, respectively, when the tracking frame on the live view image displayed by the display unit 213 described later is displayed. .

  Subsequently, the imaging control unit 221d drives the imaging element driving unit 204, and causes the imaging element 203 to output image data to the signal processing unit 205, thereby executing imaging processing using an electronic shutter (step S107).

  Thereafter, the face detection unit 207a detects a human face included in an image corresponding to the image data generated by the image sensor 203 (step S108).

  Subsequently, the display control unit 221e causes the display unit 213 to display a live view image corresponding to the image data generated by the imaging element 203 (step S109). At this time, the display control unit 221e may display the face of the subject detected by the face detection unit 207a with a frame highlighted.

Thereafter, the control unit 221 determines whether or not the tracking subject has been selected by the user for the live view image displayed on the display unit 213 (step S110). Specifically, as shown in FIG. 6A, for the live view image W _n (n = natural number) displayed on the display unit 213, a tracking subject is selected from a plurality of subjects via the touch panel 212g. It is determined whether a selection signal to be input is input. When the control unit 221 determines that the tracking subject has been selected (step S110: Yes), the imaging device 1 proceeds to step S111. On the other hand, when the control unit 221 determines that the tracking subject is not selected (step S110: No), the imaging device 1 proceeds to step S112.

  In step S111, the tracking subject setting unit 221a sets the selected subject as a tracking subject.

  Subsequently, the control unit 221 determines whether or not the tracking subject is set (step S112). Specifically, the control unit 221 determines whether or not a flag indicating the tracking subject setting is recorded in the SDRAM 217. When the control unit 221 determines that the tracking subject is set (step S112: Yes), the imaging device 1 proceeds to step S113 described later. On the other hand, when the control unit 221 determines that the tracking subject is not set (step S112: No), the imaging device 1 proceeds to step S118 described later.

  In step S113, in the case where the first tracking can be performed for the tracking subject while the focus position of the lens unit 3 is aligned with the position corresponding to the face area of the tracking subject detected by the face detection unit 207a (step S113). : Yes), the imaging control unit 221d executes a first tracking process in which the generation timing is tracked between temporally adjacent images while the focus position of the lens unit 3 is adjusted to the face of the tracking subject detected by the face detection unit 207a. (Step S114). Specifically, the imaging control unit 221d detects the face detection unit 207a by moving the optical system 301 along the optical axis L direction by driving the lens driving unit 302 via the lens control unit 308. Shooting is performed while adjusting the generation timing between live view images that are temporally adjacent to each other while adjusting the focus position of the lens unit 3 to the face area of the tracked subject.

  Subsequently, the subject information generation unit 221c executes subject dictionary generation processing relating to the tracking subject (step S115). Details of the subject dictionary generation process will be described later.

  Subsequently, when the tracking subject is being tracked (step S116: Yes), the display control unit 221e superimposes the tracking frame for the tracking subject on the live view image and causes the display unit 213 to display the tracking subject (step S117). The tracking frame indicates one of the focus position of the lens unit 3, the position of the optical zoom by the lens unit 3, and the electronic zoom by the image processing unit 207. After step S117, the imaging apparatus 1 proceeds to step S118. On the other hand, when the tracking subject is not being tracked (step S116: No), the imaging apparatus 1 proceeds to step S118.

  When a release signal is input from the release button 212a (step S118: Yes), the shooting control unit 221d drives the shutter driving unit 202 to perform still image shooting using the mechanical shutter (step S119).

  Subsequently, when the power button 212f is operated to turn off the power of the imaging device 1 (step S120: Yes), the imaging device 1 ends this process. On the other hand, when the power supply of the imaging device 1 is not turned off (step S120: No), the imaging device 1 returns to step S101.

  In step S118, when no release signal is input (step S118: No), and the moving image button 212b is pressed (step S121: Yes), when the imaging device 1 is not moving (step S122: No), The imaging device 1 starts moving image shooting (step S123). Specifically, the control unit 221 turns on a recording flag indicating that the moving image is being recorded in the SDRAM 217, and stores a moving image file for sequentially recording the image data in time series on the recording medium 215. Generate. After step S123, the imaging apparatus 1 proceeds to step S120.

  In step S118, when no release signal is input (step S118: No) and the moving image button 212b is pressed (step S121: Yes), the imaging apparatus 1 is in the moving image (step S122: Yes). The imaging apparatus 1 ends the moving image shooting (step S124). Thereafter, the imaging device 1 proceeds to step S120.

  In step S121, when the moving image button 212b is not pressed (step S121: No), when the imaging device 1 is moving (step S125: Yes), the imaging control unit 221d drives the imaging element driving unit 204. Then, by causing the image sensor 203 to output the image data to the signal processing unit 205, the image data by the electronic shutter is recorded on the recording medium 215 as a moving image (step S116). After step S116, the imaging device 1 proceeds to step S120. On the other hand, when the imaging device 1 is not in the moving image (step S125: No), the imaging device 1 proceeds to step S120.

  In step S113, if the first tracking by the lens unit 3 is not possible for the tracking subject (step S113: No), the tracking subject is selected based on the subject information recorded by the subject information recording unit 218b of the flash memory 218. When the second tracking to be tracked is possible (step S127: Yes), the imaging device 1 executes a second tracking process (step S128). Details of the second tracking process will be described later. After step S128, the imaging device 1 proceeds to step S116.

  In step S127, when the second tracking for tracking the tracking subject is not possible (step S127: No), the imaging apparatus 1 proceeds to step S116.

  Next, the subject dictionary generation process in step S115 will be described. FIG. 7 is a flowchart showing an outline of subject dictionary generation processing.

  As illustrated in FIG. 7, the imaging device 1 executes a joint modeling process regarding the tracking subject (step S201).

  FIG. 8 is a flowchart showing an outline of the joint modeling process in step S201. As shown in FIG. 8, the feature point extraction unit 207c refers to the part information recorded by the part information recording unit 218c, and performs pattern matching on the tracking subject to obtain the feature point of the head image of the tracking subject. Extract (step S301).

  Subsequently, the joint model generation unit 221b estimates the joint position of the head of the tracking subject based on the feature point of the head image of the tracking subject extracted by the feature point extraction unit 207c (step S302). Specifically, as illustrated in FIG. 9, the joint model generation unit 221b determines the tracking subject's head based on the feature point P1 (FIG. 9A) of the head of the tracking subject extracted by the feature point extraction unit 207c. The joint position M1 of the head is estimated (FIG. 9B).

  Thereafter, the feature point extraction unit 207c extracts feature points of the upper body image of the tracking subject included in the image data by performing pattern matching with reference to the part information recorded by the part information recording unit 218c (step S303). .

  Subsequently, the joint model generation unit 221b estimates the joint position of the tracking subject based on the feature points of the upper body image of the tracking subject extracted by the feature point extraction unit 207c (step S304). Specifically, as illustrated in FIG. 9, the joint model generation unit 221b performs tracking based on the feature points P1 to P8 (FIG. 9A) of the upper body image of the tracking subject extracted by the feature point extraction unit 207c. The joint positions M2 to M8 of the upper body image of the subject are estimated (FIG. 9B).

  Thereafter, the feature point extraction unit 207c acquires the clothing information of the tracking subject from the extracted upper body image (step S305). Specifically, the feature point extraction unit 207c acquires color components included in the image data corresponding to the extracted upper body image area as clothing information of the upper body.

  Subsequently, the feature point extraction unit 207c extracts the feature points of the lower body image of the tracking subject included in the image data by performing pattern matching with reference to the part information recorded by the part information recording unit 218c (step S306). ).

  Thereafter, the joint model generation unit 221b estimates the joint position of the tracking subject based on the feature points of the lower body image of the tracking subject extracted by the feature point extraction unit 207c (step S307). Specifically, as illustrated in FIG. 9, the joint model generation unit 221b performs tracking based on the feature points P9 to P12 (FIG. 9A) of the upper body image of the tracking subject extracted by the feature point extraction unit 207c. The joint positions M9 to M12 of the lower half new image of the subject are estimated (FIG. 9B).

  Subsequently, the feature point extraction unit 207c acquires the clothing information of the tracking subject from the extracted lower body image (step S308).

  Thereafter, the joint model generation unit 221b estimates the boundary between the tracking subject and the ground with reference to the part information recorded by the parts information recording unit 218c (step S309).

  Subsequently, the joint model generation unit 221b estimates the joint position of the lower body tip of the tracking subject included in the image data by performing pattern matching with reference to the part information recorded by the part information recording unit 218c (step S310). ).

  Thereafter, the feature point extraction unit 207c acquires shoe information of the tracking subject (step S311). Specifically, the feature point extraction unit 207c acquires, as shoe information, color components included in the image data corresponding to the joint position of the lower body tip estimated by the joint model generation unit 221b. After step S310, the process returns to the tracking subject dictionary generation process of FIG.

Returning to FIG. 7, the description of step S202 and subsequent steps will be continued.
In step S202, the subject information generation unit 221c records the tracking model joint model information generated by the joint model generation unit 221b in the subject information recording unit 218b.

  Subsequently, the control unit 221 determines whether or not the tracking subject is in a standing posture (step S203). Specifically, based on the subject dictionary information recorded by the subject information recording unit 218b, the control unit 221 makes the joint position of the head of the tracking subject or the position in the image of the tracking subject substantially constant between adjacent images. If there is, it is determined that the tracking subject is in a standing posture. When the control unit 221 determines that the tracking subject is in the standing posture (step S203: Yes), the imaging device 1 proceeds to step S204 described later. On the other hand, when the control unit 221 determines that the tracking subject is not in the standing posture (step S203: No), the imaging device 1 proceeds to step S205 described later.

  In step S204, the subject information generation unit 221c updates the tracking subject dictionary information recorded by the subject information recording unit 218b by adding subject information related to the standing posture (step S204).

  Subsequently, the control unit 221 determines whether or not the position of the knee joint of the tracking subject is the maximum (step S205). When the control unit 221 determines that the position of the knee joint of the tracking subject is the maximum (step S205: Yes), the imaging device 1 proceeds to step S206. On the other hand, when the control unit 221 determines that the position of the knee joint of the tracking subject is not the maximum (step S205: No), the imaging device 1 returns to the main routine of FIG.

  In step S206, when the moving speed of the tracking subject between adjacent images is a predetermined speed, for example, 5 km / h or more (step S206: Yes), the subject information generation unit 221c tracks the tracking information recorded by the subject information recording unit 218b. The subject dictionary information is updated by adding subject information of the running posture (step S207). Specifically, as illustrated in FIG. 9B, the subject information generation unit 221c includes arm angle information (θ = 80 °) and stride information in the joint model of the tracking subject generated by the joint model generation unit 221b. (100 cm) and angle information (θ = 30 °) of the upper body are added and updated as the running posture of the subject information recorded by the subject information recording unit 218b. After step S207, the imaging apparatus 1 returns to the main routine of FIG.

  In step S206, when the moving speed of the tracking subject is not equal to or higher than the predetermined speed between adjacent images (step S206: No), the control unit 221 includes the subject related to the walking posture in the tracking subject dictionary information recorded by the subject information recording unit 218b. Information is added and updated (step S208). After step S208, the imaging apparatus 1 returns to the main routine in FIG.

  As described above, the subject information generation unit 221c takes into account the posture state of the person, for example, the standing posture, the walking posture and the running posture, the person-specific wrinkles, and the traveling speed even in the subject dictionary generation process. It may be created while updating the subject dictionary information of the tracking subject. Specifically, the subject information generation unit 221c determines the tracking subject based on an individual peculiar identifiable from the image, for example, the running speed in the running posture state, the pitch width (slide width), the elbow angle and the inclination, and the elbow angle. The subject dictionary information may be updated.

  Next, the second tracking process in step S128 of FIG. 4 will be described. FIG. 10 is a flowchart showing an overview of the second tracking process.

  As shown in FIG. 10, when not all the persons included in the image data have been searched (step S401: No), the subject detection unit 207b records the subject information recording unit 218b for the subject to be searched. Pattern matching processing is performed with reference to the subject information (step S402). At this time, the subject detection unit 207b may execute the pattern matching process using the traveling speed and posture state included in the tracking subject information recorded by the subject information recording unit 218.

  Subsequently, the control unit 221 determines whether the subject detection unit 207b has completed the pattern matching process for all persons included in the image data (step S403). When the control unit 221 determines that the subject detection unit 207b has finished the pattern matching process for all persons (step S403: Yes), the imaging device 1 proceeds to step S404. On the other hand, when the control unit 221 determines that the subject detection unit 207b has not finished the pattern matching process for all persons (step S403: No), the imaging device 1 returns to step S402.

  In step S404, when all subjects searched by the subject detection unit 207b include subjects whose matching rate is equal to or higher than a predetermined threshold (for example, 70%) (step S404: Yes), the tracking subject setting unit 221a Then, a subject whose matching rate is above a predetermined threshold is set as a tracking subject to be tracked by posture or movement (step S405).

  Thereafter, the imaging control unit 221d executes a tracking process of tracking while adjusting the focus position of the lens unit 3 to the position corresponding to the tracking subject region set by the tracking subject setting unit 221a (step S406). As a result, as shown in FIG. 6, when tracking is performed while the pinch position of the lens unit 3 is aligned with the position corresponding to the face area of the tracking subject detected by the face detection unit 207a (FIG. 6A). The user pans the imaging device 1, the posture of the tracking subject changes, or the user operates the lens unit 3 to change the angle of view of the imaging device 1 (FIG. 6B). When the face detection unit 207a cannot detect the face of the tracking subject A1 (FIG. 6C), the subject detection unit 207b detects a subject that matches the posture of the subject information in the subject information recording unit 218b. Thus, shooting can be performed while instantaneously tracking the tracking subject (FIG. 6 (c) → (FIG. 6) (d)). After step S406, the imaging apparatus 1 returns to the main routine in FIG.

  In step S401, if all the persons included in the image data have been searched (step S401: Yes), the imaging apparatus 1 returns to the main routine of FIG.

  In step S404, when all subjects searched by the subject detection unit 207b do not include a subject whose matching rate is equal to or higher than a predetermined threshold (step S404: No), the imaging apparatus 1 goes to the main routine of FIG. Return.

  According to the embodiment of the present invention described above, when the face detection unit 207a detects the face of the tracking subject set by the subject setting unit 221a, the shooting control unit 221d corresponds to the face area of the tracking subject. While the focus position of the lens unit 3 is adjusted to the position, the first tracking process of tracking between images whose generation timings are temporally adjacent to each other is executed, while the face detection unit 207a sets the face of the tracking subject set by the subject setting unit 221a When the subject detection unit 207b detects a subject in a pre-recorded posture state, the shooting control unit 221d generates the subject detected by the subject detection unit 207b between images that are temporally adjacent to each other. A second tracking process for tracking as a tracking subject to be tracked while adjusting the focus position of the lens unit 3 is executed. As a result, even when the tracking subject cannot be detected by pattern matching based on face detection, it is possible to perform shooting with focusing on the tracking subject.

  In addition, according to the embodiment of the present invention, the subject detection unit 207b tracks the subject from a plurality of subjects in the image based on the degree of coincidence with the subject information regarding the tracking subject generated by the subject information generation unit 221c. Since a subject that matches the posture state of the subject information can be detected as a tracking subject, the tracking subject can be tracked instantaneously even if the angle of view or field of view of the imaging device 1 changes.

  In the embodiment of the present invention, when the display unit 213 reproduces an image corresponding to the image data recorded by the recording medium 215, a selection signal for selecting a tracking subject is input from the operation input unit 212. Then, the subject information generation unit 221c may generate subject information regarding the selected tracking subject, and record the generated subject information in the subject information recording unit 218b. At this time, the subject information generation unit 221c may record the image data of the image reproduced by the display unit 213 in association with the subject information on the recording medium 215 or the subject information recording unit 218b.

  Further, in one embodiment of the present invention, the posture of the tracking subject is only a standing posture, a walking posture, and a running posture. Can be applied.

  In the embodiment of the present invention, the joint model generation unit 221b generates the joint model of the tracking subject based on the feature points of each part of the tracking subject extracted by the feature point extraction unit 207c. For example, a joint model of the tracking subject may be generated based on a signal output from the distance measurement calculation unit 208.

  In the embodiment of the present invention, the subject detection unit 207b detects a person in a predetermined posture state from the image. For example, the subject detection unit 207b moves with an animal (pet) in a predetermined posture state or a predetermined spade. An object to be detected may be detected.

  In the embodiment of the present invention, the subject detection unit 207b detects a person in a predetermined posture state from the image. However, the object detection unit 207b tracks an object having a predetermined shape such as a square, a sphere, or a circle. You may detect as a to-be-photographed object.

(Other embodiments)
So far, the embodiment for carrying out the present invention has been described, but the present invention should not be limited only by the embodiment described above.

  For example, in the present invention, an electronic viewfinder may be provided in the main body unit separately from the display unit, and the present invention may be applied to this electronic viewfinder. In this case, it is more preferable that the appearance of the live view image is different between the display unit and the electronic viewfinder.

  In the present invention, the main body portion and the lens portion may be integrally formed.

  In addition to a digital single-lens reflex camera, the imaging device according to the present invention is also applicable to electronic devices such as a digital camera, a digital video camera, and a mobile phone having a photographing function and a tablet-type mobile device having an imaging function. can do.

  In the description of the flowchart in the present specification, the context of the processing between steps is clearly indicated using expressions such as “first”, “after”, “follow”, etc., in order to implement the present invention. The order of processing required is not uniquely determined by their representation. That is, the order of processing in the flowcharts described in this specification can be changed within a consistent range.

  As described above, the present invention can include various embodiments not described herein, and various design changes and the like can be made within the scope of the technical idea specified by the claims. Is possible.

DESCRIPTION OF SYMBOLS 1 Imaging device 2 Main body part 3 Lens part 201 Shutter 202 Shutter drive part 203 Image pick-up element 203a Phase difference AF element 204 Image pick-up element drive part 205 Signal processing part 206 A / D conversion part 207 Image processing part 207a Face detection part 207b Subject detection part 207c Feature point extraction unit 208 Ranging calculation unit 209 AE processing unit 210 AF processing unit 211 Image compression / decompression unit 212 Operation input unit 212a Release button 212b Movie button 212c Mode switch button 212d Menu button 212e Playback button 212f Power button 213 Display unit 214 Display drive unit 215 Recording medium 216 Memory I / F
217 SDRAM
218 Flash memory 218a Program recording unit 219 Main body communication unit 220 Bus 221 Control unit 221a Subject setting unit 221b Joint model generation unit 221c Subject information generation unit 221d Shooting control unit 221e Display control unit

Claims (10)

A lens unit composed of a plurality of lenses and condensing light from a predetermined field of view;
An imaging unit that receives light collected by the lens unit and generates electronic image data continuously in time;
A face detection unit for detecting a human face from an image corresponding to the image data;
A subject detection unit for detecting a subject in a predetermined posture state from an image corresponding to the image data;
When the face detection unit cannot detect the face of the person and the subject detection unit detects the subject, the generation timing of the imaging unit is timed while changing the shooting parameters for the area corresponding to the subject. A shooting control unit that executes a tracking process for tracking between adjacent images,
An imaging apparatus comprising: A feature point extraction unit for extracting feature points of each part constituting the subject;
A subject information generating unit that generates subject information used when specifying the posture of the subject based on the feature points extracted by the feature point extracting unit;
Further comprising
The imaging apparatus according to claim 1, wherein the subject detection unit detects a subject in a posture state in which a degree of coincidence with the subject information generated by the subject information generation unit is a predetermined threshold or more. Based on the feature points extracted by the feature point extraction unit, further comprising a joint model generation unit that generates a joint model that models the person with a plurality of joints of the subject,
The imaging apparatus according to claim 2, wherein the subject information generation unit generates the subject information with reference to the joint model generated by the joint model generation unit. An operation input unit that receives an input of a selection signal for selecting any of a plurality of persons included in the image;
The imaging according to claim 2 or 3, wherein the subject information generation unit generates the subject information of the person when the face detection unit detects a person's face according to the selection signal. apparatus. A recording unit for recording the image data;
A display unit for displaying an image corresponding to the image data;
An operation input unit for receiving an input of a selection signal for selecting one of a plurality of persons included in the image displayed by the display unit;
Further comprising
In the case where the display unit reproduces the image recorded by the recording unit and the face detection unit detects the face of the person according to the selection signal, the subject information generation unit The imaging apparatus according to claim 2, wherein the subject information is generated.   The imaging apparatus according to claim 1, wherein the photographing parameter is any one of a focus position of the lens unit, an exposure value, an optical zoom and an electronic zoom of the lens unit.   The photographing control unit adjusts the focus position of the lens unit with respect to a region corresponding to the subject when the subject detection unit detects the subject when the face detection unit cannot detect the face of the person. The imaging apparatus according to claim 6, wherein tracking processing for tracking between images whose generation timings by the imaging unit are temporally adjacent to each other is executed. A subject setting unit for setting a tracking subject to be tracked while focusing on the lens unit between images that are temporally adjacent to each other at a generation timing by the imaging unit;
The face detection unit detects a face of the tracking subject from a plurality of persons included in an image corresponding to the image data;
The subject detection unit detects a subject in the posture state from a plurality of subjects included in an image corresponding to the image data;
When the face detection unit detects the face of the tracking subject, the shooting control unit performs a first tracking process for tracking while aligning the focus position of the lens unit with the face region of the tracking subject, When the face detection unit cannot detect the face of the tracking subject and the subject detection unit is able to detect the tracking subject, the second tracking is performed while adjusting the focus position of the lens unit to the area corresponding to the tracking subject. The imaging apparatus according to claim 7, wherein tracking processing is executed. A lens unit that collects light from a predetermined field of view, and an imaging unit that receives the light collected by the lens unit and continuously generates electronic image data in time. An imaging method executed by an imaging apparatus comprising:
A face detection step of detecting a human face from an image corresponding to the image data;
A subject detection step of detecting a subject in a predetermined posture state from an image corresponding to the image data when the face detection step cannot detect the face of the subject;
When the subject can be detected in the subject detection step, a tracking process is performed in which the generation timing by the imaging unit tracks between temporally adjacent images while changing the shooting parameter for the region corresponding to the subject. A shooting control step;
An imaging method comprising: A lens unit that collects light from a predetermined field of view, and an imaging unit that receives the light collected by the lens unit and continuously generates electronic image data in time. , A program to be executed by an imaging device comprising:
A face detecting step for detecting the face of the subject with respect to the image corresponding to the image data;
A subject detection step of detecting a subject in a pre-recorded posture state with respect to the image when the face detection step cannot detect the face of the subject;
When the subject is detected in the subject detection step, shooting that performs tracking processing for tracking between the images whose generation timings by the imaging unit are temporally adjacent while changing the shooting parameter for the region corresponding to the subject Control steps;
The program characterized by including.

Images