JP2008098954A - Imaging apparatus, method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an imaging apparatus which can improve operability of a user suppressing a processing load. <P>SOLUTION: The imaging apparatus includes: an image acquisition means which acquires frame image data in an imaging range; a figure detection means which detects a human part based on the acquired frame image data; a tracing means which traces the detected human part on other succeeding frame image data; a focus means to focus on the figure part; and an imaging means which receives an input of an imaging instruction, and performs imaging processing in a condition that the figure part is focused by the focus means. The figure detection means detects a predetermined position in the imaging range, for example, the figure part which is the nearest to a center position of the imaging range. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an imaging apparatus, and more particularly to an imaging apparatus having an autofocus function.

  In a standard camera, the focus area that is the target of autofocus is the center of the captured image. Therefore, for example, when taking a commemorative photo at a travel destination, when you try to shoot a landscape with a landscape in the center and a person in the side, focus on a distant landscape located in the center of the composition, and the person will be out of focus. There was a problem of becoming. In order to avoid this problem, it is possible to shoot in a state where the person is focused by first changing the composition to the composition centered on the landscape while the focus is locked with the composition centered on the person. However, users who are not used to operating the camera often do not know such an operation method, and thus it has been difficult to take appropriate photographs.

  In order to solve the above problem, a method in which focus areas are arranged at a plurality of points in the screen and the most appropriate focus area is selected to perform a focus operation has been conventionally used. However, in this method, since it is necessary to perform the focus operation in a plurality of focus areas, it takes time to process, and when the subject is out of the fixedly arranged focus area, the user wants to focus on the desired subject. The problem of being unable to do so has arisen.

  Many of the subjects are people, but there may be a camera that detects a face and operates as a focus target in order to prevent the defocusing of the person's face when photographing a person. For example, Patent Documents 1 and 2 disclose a camera equipped with a technique for detecting a face portion of a person as a subject from within a shooting range and performing autofocus on the detected face portion. Further, Patent Document 3 discloses a technique for automatically tracking a target subject.

JP 2005-318554 A JP 2006-145629 A JP-A-6-268894

  However, the technique disclosed in the above-described patent document does not disclose a technique for focusing and automatically tracking when a plurality of faces are detected. For example, in Patent Document 2, when there are a plurality of human face portions, each face portion is detected, and the user operates the operation unit of the camera to select the desired human face portion on the preview screen. A method of explicitly focusing an arbitrary face portion is disclosed. In particular, the distance from the camera is checked according to the area of the face portion, and the selection target by the user is moved based on the distance. However, in the above technique, it is necessary for the user to operate the operation unit while viewing the preview screen, and there is a problem that the operation is troublesome. In particular, it is necessary to perform an operation for moving the selection target of the face portion on the preview screen in the order corresponding to the distance from the camera, which may increase the time and effort during the operation. Furthermore, although it is conceivable to simultaneously track a plurality of detected faces, there is a problem that the processing load increases and it is difficult to process in a small electronic device such as a mobile phone with limited processing capability.

  Therefore, an object of the present invention is to provide an imaging apparatus that can improve the inconvenience of the above-described conventional example, and in particular, can improve the operability of the user while suppressing the processing load.

Therefore, an imaging apparatus which is one embodiment of the present invention is
Frame image acquisition means for acquiring frame image data of the shooting range;
Person detecting means for detecting a person portion based on the acquired frame image data;
Tracking means for tracking the detected person part on other subsequent frame image data;
Focusing means to focus on the person part,
An imaging device that receives an input of a shooting command and performs an imaging process in a state in which the person portion is focused on the focus unit,
The person detection means detects one person part closest to a preset position in the shooting range, for example, the center position of the shooting range.
It is characterized by that.

  According to the above invention, first, in the imaging device, frame image data that is image data of the imaging range is always captured from the lens at a constant time interval, and is previewed on, for example, a display unit provided in the imaging device. The Then, a process for detecting a person portion is performed on the frame image data. At this time, one person part closest to a preset position, for example, the center position of the shooting range, is detected in the shooting range. Then, the detected one person portion is tracked on the subsequent frame image data. Thereafter, when an imaging command is input, imaging processing is performed while focusing on the person portion being tracked or in a focused state during tracking, and image data in the imaging range is acquired and stored.

  As a result, even if there are a plurality of person parts in the shooting range, the one person part closest to the set position is set as the detection target and tracking target, so that the focus target can be set automatically. In addition, the processing time can be shortened and the processing load can be reduced. In addition, since person detection is performed on the acquired frame image data, it is not necessary to perform person detection processing after the shooting command is input (shutter button pressed), and the processing time from shooting command to imaging processing is reduced. Therefore, the user can suppress missing a photo opportunity.

  In addition, re-detection instruction means for inputting a person part re-detection command to the person detection means is provided, and the person detection means performs re-detection of the person part based on the frame image data in response to the re-detection instruction. It is characterized by that. Thereby, when the user inputs a redetection command, the person portion that is closest to the set position of the shooting range is redetected in the frame image data at that time. Therefore, the tracking target to be focused can be switched to a person portion close to the set location such as the center position of the screen at the timing of the user operation, and the user can track and capture any desired person. Therefore, operability can be improved.

  Further, the person detecting means is characterized in that a person portion is detected based on the frame image at a constant time interval. At this time, it is provided with detection stop command means for inputting a person part detection stop command to the person detection means, and the person detection means stops the human part detection process in response to the detection stop command. Yes. As a result, since the person portion is automatically re-detected at regular time intervals, it is easy to photograph the person intended by the user. Further, when the user inputs a detection stop command, the human part detection process is stopped. Then, the person portion detected at that time is subsequently tracked. That is, the tracking target can be fixed and the target person can be imaged, so that the operability can be improved.

  Further, the focusing means operates when it receives an input of a shooting command. Thus, when a shooting command is input, a focus process is performed on the person portion being tracked at that time, and an imaging process is performed. Accordingly, since the focus process is executed only immediately before imaging, the lens driving necessary for the focusing operation is activated only immediately before imaging, and power consumption can be reduced.

  Alternatively, the focusing means is characterized in that it operates after the human part detection process and / or after the tracking process. Thereby, the focus process for the person portion is always executed during the tracking process for each frame image. Accordingly, since it is not necessary to execute the focus process during the imaging process, it is possible to shorten the processing time from the imaging command to the imaging process.

  The above-described imaging device is preferably provided in a portable electronic device such as a cellular phone because operability is improved and processing load can be reduced.

Moreover, the program which is the other form of this invention is:
In the control unit of the imaging device that captures an image of a predetermined range,
Frame image acquisition means for acquiring frame image data of the shooting range;
Person detecting means for detecting a person portion based on the acquired frame image data;
Tracking means for tracking the detected person part on other subsequent frame image data;
An imaging unit that receives an input of a shooting command and performs an imaging process in a state where the person part is focused;
Is a program for realizing
The person detecting means detects one person part closest to a preset position in the photographing range.
It is characterized by that.

Furthermore, an imaging method according to another aspect of the present invention includes:
A method of capturing an image of a predetermined range with an imaging device,
A frame image acquisition step of acquiring frame image data of the shooting range;
A person detection step of detecting a person portion based on the acquired frame image data;
A tracking step of tracking the detected previous person portion on other subsequent frame image data;
Receiving an input of a shooting command, and performing an imaging process in a state in which the person portion is focused,
The person detection step detects one person part closest to a preset position (for example, the center position of the shooting range) in the shooting range.
It is characterized by that.

  In the person detection step, when a person part redetection command is received, the person part is redetected based on the frame image data. Alternatively, the person detection step detects a person portion based on the frame image at a constant time interval. At this time, in the person detection step, when the input of the person part detection stop command is accepted, the person part detection process is stopped.

  Further, in the imaging process, when an input of a shooting command is received, the person portion is focused and imaged. Alternatively, the person detection step focuses on the person portion after detecting the person portion and / or the tracking step tracks the person portion.

  Even the invention of the program and method having the above-described configuration can achieve the object of the present invention because it operates in the same manner as the imaging apparatus described above.

  Since the present invention is configured and functions as described above, according to this, since only one person portion closest to the position set in the photographing range is set as the detection target and the tracking target, the focus target is automatically set. And the operability can be improved, and the processing time can be shortened and the processing load can be reduced.

  The present invention detects and tracks the face of a subject in a frame image acquired for preview display or the like when shooting a person with an imaging device, and performs an autofocus operation at the position of the face during shooting. It is characterized by preventing blurring. Hereinafter, a digital camera mounted on a mobile phone will be described as an example of the imaging device. However, the imaging apparatus according to the present invention may be mounted on another electronic device, or may be a digital camera itself.

  A first embodiment of the present invention will be described with reference to FIGS. FIG. 1 is a diagram showing the appearance of a mobile phone equipped with an imaging device, and FIG. 2 is a functional block diagram showing the configuration of the imaging device portion. FIG. 3 is a flowchart illustrating the operation of the imaging apparatus, and FIG. 4 is a diagram illustrating an example of a preview screen during imaging.

[Constitution]
A mobile phone 1 shown in FIG. 1 is a foldable general mobile phone 1, and an upper casing 1 </ b> A is equipped with a display unit 15 that is a liquid crystal display, and a lower casing 1 </ b> B is provided with a numeric keypad or the like. A key operation unit 13 having a plurality of operation buttons is provided. In addition, the mobile phone 1 includes an imaging device 10 that is a digital camera. The mobile phone 1 is equipped with a camera unit 11 having a lens or the like on the back side of the upper housing 1A, and images are taken inside the lower housing 1B. A control device or the like (camera control unit 12, arithmetic device 20 or the like) for realizing the function is provided. Hereinafter, the configuration of the imaging device 10 will be described with reference to FIG.

  As illustrated in FIG. 2, the imaging device 10 includes a camera unit 11, a camera control unit 12, a key operation unit 13, a key input control unit 14, a display unit 15, a display control unit 16, and a calculation device 20. And a storage device 30. Hereinafter, each component of the imaging device 1 will be described in detail.

  As described above, the camera unit 11 is a camera module that captures an image in a shooting range as image data that is electronic data. The camera control unit 12 has a function of controlling the operation of the camera unit 11 to perform processing for capturing image data, or performing autofocus control for focusing the camera unit 11 in cooperation with the camera unit 11 ( Focus means).

  The key operation unit 13 is an operation unit of the mobile phone 1 as described above, and the key input control unit 14 detects an input to the key operation unit 13. The display unit 15 is the display of the mobile phone 1 as described above, and the display control unit 16 displays the preview image acquired by the camera unit 11 or the actually captured image on the display unit 15. Control.

  The arithmetic device 20 is a CPU that is connected to the control units 12, 14, and 16 and controls the operation of the imaging device 10. Then, a predetermined program is incorporated in the arithmetic device 20, so that an image acquisition processing unit 21, a face detection / tracking control processing unit 22, an image display processing unit 23, and a data storage processing unit 24 are included. Has been built.

  The image acquisition processing unit 21 (frame image acquisition means) controls the operation of the camera control unit 12 to capture frame image data in a predetermined shooting range acquired by the camera unit 11. At this time, frame image data is continuously acquired at a constant time interval (for example, 0.5 second interval), and transferred to the face detection / tracking control processing unit 22. The frame image data is sequentially displayed as a preview image on the display unit 15 by the image display processing unit 23 via the face detection / tracking control unit 22.

  Further, the image acquisition processing unit 21 receives the imaging command via the key input control unit 14 and the face detection / tracking control processing unit 22 when the imaging command is input from the key operation unit 13, and receives from the camera unit 11. The frame image data is captured, and this frame image data is transferred to the data storage processing unit 24 as a captured image. Then, the data storage processing unit 24 stores the frame image data that is a captured image in the image storage unit 31 of the storage device 30. As described above, the image acquisition unit 21 and the data storage processing unit 24 function as an imaging unit.

  Furthermore, the image acquisition processing unit 21 designates the autofocus area based on the autofocus area instructed from the face detection / tracking control processing unit 22 described later at the time of shooting described above, and controls the autofocus instruction by the camera. To the unit 12. That is, the image acquisition processing unit 21 functions as a focusing unit in cooperation with the camera unit 11, the camera control unit 12, and the like. Thereby, in this embodiment, autofocus is executed only after a shooting command is issued, and a shot image is acquired and stored.

  The face detection / tracking control processing unit (person detection unit, tracking unit) 22 receives the frame image data for preview display acquired from the camera unit 11 by the image acquisition processing unit 21, and for the frame image data, First, detection processing of a human face portion (person portion) is performed. For example, a color portion set in advance based on the color information of the image is detected as a face portion. After that, the detected face portion is tracked on successive subsequent frame image data. For example, on the subsequent frame image data, the same feature point as the detected feature point of the face part is detected and specified as the tracked face part.

  Here, the detection and tracking of the face portion is not limited to being executed by the above-described processing, and the detection and tracking algorithm is arbitrary. Further, the part to be detected and tracked is not limited to the face part, but may be another part of the human body.

  Further, the face detection / tracking control processing unit 22 specifies one face part closest to the photographing range, that is, the center position of the frame image data when a plurality of face parts are detected during the face part detection described above. To detect. That is, the face portion located closer to the center position on the plane frame image is specified and detected as a later tracking target. At this time, for example, the distance to each face part is calculated based on the coordinates on the frame image data, and the face part with the shortest distance is specified as the tracking target. Note that one face part to be identified is not necessarily limited to the one close to the center position. For example, a face portion that is closest to a position such as the right corner of the shooting range or a marker position arbitrarily set and displayed on the display unit 15 in advance may be specified.

  Further, the face detection / tracking control processing unit 22 uses, for example, rectangular face detection frame data R (see the dotted line frame R in FIG. 4) for specifying the position of the face portion detected or tracked as described above. Then, it is synthesized on the frame image data and outputted to the image display processing unit 23. Further, when a button corresponding to the shutter button of the key operation unit 13 is pressed and a shooting command signal is received from the key input control unit 14, the face detection (tracking) position in the immediately previous frame image data is used as an autofocus area. The acquisition processing unit 21 is notified, and focus and image acquisition are instructed.

  Further, when the face detection / tracking control processing unit 22 in this embodiment receives a face part re-detection command input from the key input control unit 14 to the key operation unit 13, the face detection / tracking control processing unit 22 determines the position of the currently tracked face part. After resetting, the face portion detection process is newly performed from the latest frame image data in the same manner as described above. Then, the tracking of the newly detected face part is continued.

  As described above, the image display processing unit 23 displays the preview image and the face detection frame R, which are frame image data received from the face detection / tracking control processing unit 22, on the display unit 15 using the display control unit 16. .

[Operation]
Next, the operation of the imaging apparatus 1 having the above configuration will be described with reference to the flowchart of FIG. 3 and the preview screen of FIG. Note that the flowchart of FIG. 3 loops every time a frame image is acquired, that is, every time a preview image of one frame is updated, and the loop is repeated until the shutter key or the end key is pressed.

  First, when the imaging apparatus 1 is activated, the image acquisition processing unit 21 acquires a preview image from the camera unit 11 (step S01, frame image acquisition step). Subsequently, it is determined whether face detection or face tracking has succeeded in the immediately preceding frame (step S02). At this time, since it is still the first frame image and the first loop, it is determined that it has not succeeded (step S02: NO). Also, if a re-detection flag set in step S11 to be described later is set, it is determined that it has not been successful (step S02: NO), and the process proceeds to face detection processing (step S05, person detection step). If the face portion has already been detected in the previous frame and has been successful (step S02: YES), the process proceeds to face tracking processing (step S03).

  Subsequently, in the face detection process in step S05, the entire current frame image data acquired in step S01 is scanned to detect all face portions included in the image based on color information and the like. Then, it is determined whether or not the face detection process in step S05 is successful (step S06). If successful (step S06: YES), the process proceeds to step S07. If the face detection process is successful, the face closest to the center of the image is selected from the plurality of faces detected in step S05 (step S07). In the case of failure or when the face is not included in the image (step S06: NO), step S07 and step S08 are skipped.

  Subsequently, when a face part is selected in step S07, a rectangular face detection frame R indicating the position of the selected face part is synthesized on the preview image (step S08). Then, the preview image is sent to the image display processing unit 23, and the preview image is displayed on the display unit 15 (step S09). A display example of the preview screen at this time is shown in FIG. As described above, when two persons (user A and user B) are included in the shooting range, the user A located closer to the center position C is detected as a shooting target, and a face detection frame is included in the face portion. R is displayed and output.

  Thereafter, the key input from the user is accepted (step S10), but if there is no key input, the frame image data of the shooting range is continuously captured (step S01). Since the face part has already been detected and the face is being tracked (step S02: YES), the face part is tracked (step S03, tracking process). In this tracking process, the same face part that was tracked in the previous frame is detected from the current frame using the results of the face tracking / face detection process of the previous frame, and the position of the detected face part is tracked. It is set as the position. For example, by detecting a face part having the same feature point as the face part to be tracked only around the face part position of the previous frame, the tracking process can be performed in a short time with a small amount of processing. it can.

  Then, it is determined whether or not the face tracking process in step S03 described above is successful (step S04). If successful (step S04: YES), a rectangular shape indicating the position of the tracked face portion is obtained as described above. The face detection frame R is synthesized on the preview image (step S08). If the same feature point is not detected, it is determined that tracking has failed, and step S08 is skipped. Then, the preview image is sent to the image display processing unit 23, and the preview image is displayed on the display unit 15 (see step S09, FIG. 4A).

  Thereafter, the key input from the user is accepted (step S10), but when the input of the redetection key is accepted, the tracking of the currently tracked face part is finished (step S11), the redetection flag is set, and the step Return to S01. This re-detection key is used when, for example, a plurality of faces are in the shooting range and displayed on the preview screen, and a face different from the face that the user wants to focus on becomes a tracking target. The direction of the camera unit 11 is changed so that the portion becomes a focus target, and the user presses the portion. For example, in the example shown in FIG. 4A, the face portion of the user A is the tracking target. However, when the user desires to focus the user B on the preview screen, the user B The direction of the camera unit 11 is moved so that the face portion of the camera is closer to the center position C of the shooting range (arrow Y in FIG. 4A), and the re-detection key is pressed. Then, a new face detection process is executed for the latest frame screen data (step S01, step S02: NO, step S03), and the face portion of user B close to the center position C is selected (step S07). Then, the face detection frame R is combined with the face portion (step S08), and a preview image is displayed on the display unit 15 as shown in FIG. 4B (step S09). Thereby, the user can select an arbitrary desired face as a focus target by an easy operation. Thereafter, as long as no re-detection key or shutter key is input, the detected face portion is continuously tracked as described above.

  If the key input from the user (step S10) is the shutter key, the process proceeds to the focus operation (step S12). In this focusing operation, an area in which a face portion is detected or tracked in the current frame, that is, the face detection frame R shown in FIG. Focus processing is performed. Thereafter, a captured image is acquired using the image acquisition processing unit 21, and the acquired image data is stored in the image storage unit 31 by the data storage processing unit 24 (step S13, imaging step). When the end key is pressed, the image capturing itself is terminated.

  As described above, according to the present embodiment, since one face portion closest to the center position of the photographing range is detected and only this one face portion is a tracking target, the focus target can be easily set. The operability can be improved. In particular, even when there are multiple faces in the shooting range, the desired face can be set as the focus target by a simple operation such as roughly changing the orientation of the imaging device so that the desired face is located near the center. Can do.

  In addition, since there is only one tracking target, the processing time for face tracking can be reduced, so that it can be easily mounted on a small electronic device such as a mobile phone that does not have high processing capability. In the present embodiment, since the face detection and tracking process is performed on the preview image, the focus target position is already set before the shutter button is pressed. The time lag can be shortened. In particular, in this embodiment, since the focus operation is not performed at the time of face tracking but only when the shutter button is pressed, the mechanical driving time of the lens necessary for the focus operation can be suppressed. Reduction can be achieved.

  Next, a second embodiment of the present invention will be described with reference to the flowchart of FIG. The imaging device 10 provided in the mobile phone 1 in the present embodiment has the configuration shown in the block diagram of FIG. 2 in substantially the same manner as that disclosed in the first embodiment. However, in this embodiment, the operation at the time of the face tracking process is different. The following description will focus on the different parts.

[Constitution]
The face detection / tracking processing unit 22 (person detection means) constructed in the arithmetic device 20 of the imaging apparatus 10 in the present embodiment is configured to automatically perform face redetection processing at regular time intervals. . That is, in the first embodiment, once the face tracking is started, the same face is tracked until the user presses the re-detection key or the tracking failure state occurs. By performing the face re-detection process, the tracking target is automatically moved to the face closest to the center position of the shooting range. When the face detection / tracking processing unit 22 receives an input (detection stop command) of the tracking fixed key input from the user to the key operation unit 13 (detection stop command means), the face detection / tracking processing unit 22 does not detect a new face portion. The tracking process of the face portion detected or tracked immediately before is continuously performed. That is, the user can fix the tracking target by pressing the tracking fixing key when the desired face becomes the tracking target.

[Operation]
Next, the operation of the image pickup apparatus in the present embodiment will be described. In the flowchart of FIG. 5, the same processes as those in the first embodiment are denoted by the same reference numerals. That is, the processes of step S14 and step S15 are different.

  First, as in the first embodiment, face detection processing is executed on the acquired preview image (step S01) (step S05, etc.), and a preview image is displayed (steps S08 and S09). Thereafter, it is incremented by one to the set frame number counter (step S14). Then, when there is no key input from the user thereafter (returning from step S10 to step S01), the detected face portion is tracked (step S03, etc.), and a preview image is displayed (step S08, S09). When the value of the frame number counter reaches a certain value, face tracking end processing is performed and the counter is reset. That is, when a face portion is tracked for a certain time (for example, 3 seconds), a new face detection process is executed, and the tracking target moves to the face portion close to the center position at that time. However, when the tracking face fixing flag is set in step S15, which will be described later, the face tracking end process is not performed even when the counter becomes a constant value.

  Thereafter, when the user inputs the tracking fixed key (step S10), the currently detected face portion is fixed as the tracking target (step S15), the tracking face fixing flag is set, and the process returns to step S01. Thereafter, no new face part is detected, and the tracking process is continuously executed with reference to the feature points of the face part set as the tracking target (step S02: YES, step S03). A preview image in which a face tracking frame is combined with the face portion thus displayed is displayed (steps S08 and S09).

  Thereafter, when the shutter key is pressed (step S10), focus processing is performed on the currently tracked face portion (step S12), and an image is acquired and stored (step S13).

  As a result, the face part is automatically re-detected, so that the user can easily shoot the target face part, and the tracking target can be fixed by the user's operation, thereby improving human operability. Can be planned.

  Next, a third embodiment of the present invention will be described with reference to the flowchart of FIG. The imaging device 10 provided in the mobile phone 1 in the present embodiment has the configuration shown in the block diagram of FIG. 2 in substantially the same manner as that disclosed in the first embodiment. However, in this embodiment, the timing at which the focus processing is executed is different. Hereinafter, the operation will be described focusing on the different parts. In the flowchart of FIG. 6, the same processes as those in the first embodiment are denoted by the same reference numerals. That is, the position of the focus operation in step S12 is different.

[Operation]
First, as in the first embodiment, face detection processing is executed on the acquired preview image (step S01) (step S05, etc.), and a face tracking frame is synthesized with the detected face portion (step S08). . At this time, focus processing is performed on the detected face portion (step S12). Thereafter, a preview image is displayed (step S09).

  Subsequently, the tracking process of the face portion that is the tracking target is executed for the subsequent frame (step S03 and the like). After this tracking process, the focus operation is performed on the position of the tracked face portion. It is executed (step S12). That is, after the face detection / tracking control processing unit 22 performs face detection and tracking processing for each frame, a focus command is issued to the camera control unit 12 via the image acquisition processing unit 21, and the camera control unit 12. The focus process is executed by the above.

  Thereafter, when the shutter key is pressed (step S10), since the focus on the tracking symmetry has already been performed, the image acquisition process is performed immediately and the image is stored (step S13).

  Thereby, since it is not necessary to perform the focus process during the imaging process, it is possible to shorten the processing time from the imaging command to the imaging process. Therefore, the time lag from the shutter pressing to the image acquisition can be reduced, and missed shutter chances can be suppressed.

  The present invention can be configured as a digital camera body or mounted on an electronic device such as a mobile phone, and has industrial applicability.

It is a figure which shows the external appearance of a mobile telephone. It is a functional block diagram which shows the structure of the imaging device with which the mobile telephone was equipped. 3 is a flowchart illustrating an operation of the imaging apparatus according to the first exemplary embodiment. It is a figure which shows an example of a preview screen. 6 is a flowchart illustrating the operation of the imaging apparatus according to the second embodiment. 10 is a flowchart illustrating the operation of the imaging apparatus according to the third embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Cellular phone 11 Camera part 12 Camera control part 13 Key operation part 14 Key input control part 15 Display part 16 Display control part 20 Arithmetic device 21 Image acquisition process part 22 Face detection / tracking control process part 23 Image display process part 24 Data storage Processing unit 30 Storage device 31 Image storage unit A, B User C Image center position R Face detection frame

Claims (16)

Frame image acquisition means for acquiring frame image data of the shooting range;
Person detecting means for detecting a person portion based on the acquired frame image data;
Tracking means for tracking the detected person portion on other subsequent frame image data;
Focusing means for focusing on the person part;
An imaging device that receives an input of a shooting command and performs an imaging process in a state where the focus unit is focused on the person part,
The person detecting means detects one person part closest to a preset position in the photographing range;
An imaging apparatus characterized by that. The person detecting means detects one person part closest to the center position of the shooting range;
The imaging apparatus according to claim 1. Re-detection command means for inputting a re-detection command of the person portion to the person detection means,
The person detecting means performs redetection of the person portion based on the frame image data in response to the redetection command;
The imaging apparatus according to claim 1 or 2, wherein The person detecting means detects a person part based on the frame image at a constant time interval;
The imaging apparatus according to claim 1 or 2, wherein A detection stop command means for inputting a detection stop command for the person portion to the person detection means;
The person detecting means stops the detection process of the person portion in response to the detection stop command;
The imaging apparatus according to claim 4. The focusing means operates when receiving an input of the shooting command;
The imaging apparatus according to claim 1, 2, 3, 4 or 5. The focusing means operates after the human part detection process and / or after the tracking process,
The imaging apparatus according to claim 1, 2, 3, 4 or 5.   A portable electronic device comprising the imaging device according to claim 1. In the control unit of the imaging device that captures an image of a predetermined range,
Frame image acquisition means for acquiring frame image data of the shooting range;
Person detecting means for detecting a person portion based on the acquired frame image data;
Tracking means for tracking the detected person portion on other subsequent frame image data;
An imaging unit that receives an input of a shooting command and performs an imaging process in a state in which the person portion is focused;
Is a program for realizing
The person detecting means detects one person part closest to a preset position in the photographing range;
A program characterized by that. A method of capturing an image of a predetermined range with an imaging device,
A frame image acquisition step of acquiring frame image data of the shooting range;
A person detection step of detecting a person portion based on the acquired frame image data;
A tracking step of tracking the detected person portion on other subsequent frame image data;
Receiving an input of a shooting command, and performing an imaging process in a state in which the person portion is focused,
The person detection step detects one person part closest to a preset position in the photographing range.
An imaging method characterized by the above. The person detecting step detects one person portion closest to the center position of the shooting range.
The imaging method according to claim 10. The person detection step performs redetection of the person part based on the frame image data when a re-detection instruction for the person part is received.
12. The imaging method according to claim 10 or 11, wherein: The person detecting step detects a person part based on the frame image at a constant time interval.
12. The imaging method according to claim 10 or 11, wherein: The person detection step stops the detection process of the person part when receiving the input of the stop detection command of the person part;
The imaging method according to claim 13. The imaging step is to focus and image the person portion when receiving an input of a shooting command,
15. The imaging method according to claim 10, 11, 12, 13, or 14. After the person detecting step detects the person part and / or after the tracking step tracks the person part, the person part is focused;
15. The imaging method according to claim 10, 11, 12, 13, or 14.

Images