JP5202264B2 - Image processing apparatus and image processing method - Google Patents

Description

  The present invention relates to an image processing device, an image processing method, a program, and a storage medium, and more particularly to a technique suitable for use in detecting a specific subject.

  In recent years, in a digital camera, a technique for estimating the position and size of a specific subject such as a human face using an image recognition algorithm has been put into practical use. In the detection of the specific subject, processing such as pattern matching using a database and a detection image prepared in advance is performed to search whether the specific subject exists in the detection image.

  However, in order to perform a process for detecting a specific subject, a complicated calculation must be performed many times, which causes a problem that a long processing time is required. In particular, when shooting a moving image in which there are many scenes where the subject is moving, it is fatal that it takes time to detect the subject. Therefore, in order to solve this problem, for example, as in a digital camera described in Patent Document 1, a region where a subject is detected is limited, and the subject is detected by performing processing for detecting the subject within the region. It is conceivable to reduce the time required for processing for detection.

JP 2007-110575 A

  However, with the prior art described in Patent Document 1, it is possible to reduce the processing time, but the region where the subject is detected is pulled to the position of the subject detected first. For example, when shooting a movie with a digital camera or digital video camera, the subject is often moving, so it is uncertain where the main subject is on the screen, and where the subject detection area is set as the initial value It is difficult to decide.

  An object of the present invention is to reduce the time for detecting a subject and to detect the subject with high accuracy in view of the above-described problems.

The image processing apparatus of the present invention, the subject detection which detects an image input means for inputting an image signal constituting the moving image data, a specific object from the image signal constituting the moving image data input by said image input means means an area determining means for determining a region to be detected by the subject detecting means, and recording means for recording the moving image data input by said image input means on a recording medium, said area determining means, When the moving image data is not being recorded by the recording means, the subject detection process is not completed until the image signal constituting the moving image data is updated in the area where the subject is detected. When the moving image data is being recorded by the recording means, the area where the subject is detected is determined by the image signal constituting the moving image data. Processing of detection of the object until new is the is characterized in that determining the magnitude terminated.

The image processing method of the present invention, the subject detection which detects an image input step of inputting an image signal constituting the moving image data, a specific object from the image signal constituting the moving image data input in the image input step step and said a region determining step of determining the area to be detected by the subject detection step, and a recording step of recording the moving image data input in the image input step to the recording medium, in the region determining step When the moving image data is not being recorded in the recording step, the subject detection process is completed until the image signal constituting the moving image data is updated in the subject detection area. When the moving image data is being recorded in the recording step, the moving image data is configured as an area where the subject is detected. Processing of detection of the object until the image signal is updated and determines sized to terminate that.

Program of the present invention includes an image input step of inputting an image signal constituting the moving image data, the subject detection step of detecting a specific object from the image signal constituting the moving image data input in the image input step an area determination step of determining a region to be detected in the subject detecting step, the dynamic image data input in the image input step to execute a recording step of recording on a recording medium into a computer, in the region determining step When the moving image data is not being recorded in the recording step, the subject detection process is completed until the image signal constituting the moving image data is updated in the subject detection area. When the moving image data is being recorded in the recording step, the area where the subject is detected is set as the moving image data. And characterized by causing a computer to execute such processing for detection of the object until the image signal constituting the image data is updated it is determined to a size to end.

  The storage medium of the present invention stores the program described above.

  According to the present invention, even when moving image data is being recorded, it is possible to reduce the time required for processing for detecting a subject and improve the detection accuracy of the subject.

(First embodiment)
Hereinafter, a first embodiment of the present invention will be described with reference to the drawings.
FIG. 1 is a block diagram illustrating a configuration example of an imaging apparatus 100 according to the present embodiment.
In FIG. 1, an imaging apparatus 100 includes a lens 1, an imaging device 2, an AFE (Analog Front End) 3, a camera signal processing circuit 4, a moving image recording processing circuit 5, a subject detection circuit 6, a subject detection region determination circuit 7, and a CPU 8. It has.

  When projected onto the lens 1 and a subject image is formed on the image sensor 2, the image sensor 2 converts the subject image into an electrical signal by photoelectric conversion, generates an analog image signal S2, and outputs the analog image signal S2 to the AFE 3. The analog image signal S2 output from the image sensor 2 is converted into a digital image signal by an A / D converter inside the AFE 3, and is output as an image signal S3. The lens 1, the image sensor 2 and the AFE 3 function as image input means.

  The camera signal processing circuit 4 receives the image signal S3 output from the AFE 3, performs image pickup system signal processing such as aperture correction, gamma correction, and white balance, and outputs the image signal S4 to the moving image recording processing circuit 5.

  The moving image recording processing circuit 5 receives the image signal S4 output from the camera signal processing circuit 4 and the signal S81 output from the CPU 8. When moving image data is recorded, the image signal S4 output from the camera signal processing circuit 4 is recorded on a recording medium (recording medium) (not shown), and no processing is performed in other states. Do not.

  The subject detection circuit 6 receives an image signal S3 output from the AFE 3, a signal S7 output from the subject detection region determination circuit 7, and a signal S81 output from the CPU 8. Then, a plurality of subjects are detected by performing pattern matching between a specific image pattern stored in advance in a database (not shown) and the image of the input image signal S3. Then, information about the detected coordinate position and size of the subject is output as a signal S6.

  The subject detection area determination circuit 7 receives the signal S6 output from the subject detection circuit 6 and the signal S81 output from the CPU 8. Then, in accordance with the state of the signal S81 output from the CPU 8, a region for the next subject detection is calculated from the coordinate position and size at which the subject is detected in the signal S6 output from the subject detection circuit 6, and the signal Output as S7.

  The CPU 8 outputs a signal indicating whether or not a moving image is being recorded as a signal S81. The signal S81 is output as 1 when a moving image is being recorded, and the signal S81 is output as 0 when the moving image is being recorded.

Hereinafter, detailed contents of the processing of each block will be described.
As described above, the moving image recording processing circuit 5 receives the image signal S4 output from the camera signal processing circuit 4 and the signal S81 output from the CPU 8. At this time, if the signal S81 output from the CPU 8 is 1, it indicates that a moving image is being recorded. Therefore, the image signal S4 output from the camera signal processing circuit 4 is recorded on the recording medium. To do. On the other hand, when the signal S81 output from the CPU 8 is 0, since no moving image is recorded, no processing is performed and the process waits.

FIG. 9 is a flowchart showing an example of a processing procedure of subject detection by the subject detection circuit 6 in the present embodiment.
In FIG. 9, when an image signal S3 output from the AFE 3, a signal S7 output from the subject detection area determination circuit 7, and a signal S81 output from the CPU 8 are input, the processing is started. When the subject is detected, the image of the image signal S3 output from the AFE 3 is performed with respect to the position and size of the image designated by the signal S7 output from the subject detection region determination circuit 7.

  First, in step S901, the image signal S3 output from the AFE 3 is held as image data in a memory (not shown). Next, the read start address and the read image size are adjusted according to the information of the signal S7 output from the subject detection area determination circuit 7 for the image data held in the memory. Then, by performing pattern matching between the image pattern stored in advance in the database and the image data read from the memory, a plurality of subject detection processes are started.

  Next, in step S902, the signal S81 output from the CPU 8 is determined. If the signal S81 output from the CPU 8 is 1 as a result of the determination, the moving image is being recorded, so the process proceeds to step S903, and the detection process is performed when the image signal S3 output from the AFE 3 is updated. abort. Then, information about the coordinates and size of the subject detected at that time is output as a signal S6. Depending on the processing speed of the subject detection circuit 6, there may be a case where the subject can be detected only from a very small area when the image signal S3 output from the AFE 3 is updated. In such a case, the detection process may be terminated when the image signal S3 is updated by the number of times set according to the processing speed of the subject detection circuit 6.

  On the other hand, if the signal S81 output from the CPU 8 is 0 as a result of the determination in step S902, the moving image recording is waiting, and the process proceeds to step S904. Even if the image signal S3 output from the AFE 3 is updated, if the subject detection process is not completed, the image data held in the memory is not updated. Then, the subject detection process is continued in step S904, and when the subject detection process ends, information on the detected coordinate position and size of the subject is output as a signal S6. When the subject detection process is completed, in the next step S905, the image data held in the memory is updated by the image signal S3 output from the AFE 3.

  Next, in step S906, it is determined whether or not to end the subject detection process. As a result of this determination, if the process ends, the process ends. If not, the process returns to step S901, and the subject detection process starts again.

FIG. 10 is a flowchart illustrating an example of a processing procedure for determining a detection area by the subject detection area determination circuit 7 in the present embodiment.
In FIG. 10, when a signal S6 output from the subject detection circuit 6 and a signal S81 output from the CPU 8 are input, the processing is started. In step S1001, the signal S81 output from the CPU 8 is determined.

  If the signal S81 output from the CPU 8 is 0 as a result of this determination, the moving image recording is waiting, and the process proceeds to step S1002. Since the subject detection process is performed on the entire screen while the moving image recording is on standby, in step S1002, the read start address and the read image size are set to be the entire screen in the image data held in the memory, and the signal S7 is set. Output. In step S1003, the signal S6 output from the subject detection circuit 6 is stored as a history of detection results. The number of signals for holding the history may be an externally set value or a predetermined value.

  On the other hand, if the signal S81 output from the CPU 8 is 1 as a result of the determination in step S1001, the process proceeds to step S1004 because a moving image is being recorded. In step S1004, based on the signal S6 output from the subject detection circuit 6, the subject is detected from the detected position and size of each subject using the image signal S3 output next. The detection area is determined. If a plurality of subjects are detected by the subject detection circuit 6, a plurality of detection areas are determined according to the position and size of the subject. At this time, the size of each detection region is determined according to the relationship shown in FIG. 2 from the size of the corresponding subject. Then, it is output as a signal S7 together with information on the coordinate position of the subject included in the signal S6 output from the subject detection circuit 6.

  The example shown in FIG. 2 is an example, and the minimum value of the size of the detection area is larger than 0, the size of the detection area increases as the size of the detected subject increases, and It is only necessary that the size of the detection area is larger than the size of the detected subject.

  In step S1005, the signal S6 output from the subject detection circuit 6 is compared with the history of detection results held. Then, the position and size of the subject detected by the subject detection circuit 6 are compared with the position and size of the subject held as a history of detection results, and the one having the highest correlation value is the same subject. to decide. This correlation value is provided with a threshold value. When there is no subject whose correlation value reaches this threshold value, it is determined that the same subject does not exist. As a result of the comparison, if there is a subject that has not been detected by the subject detection circuit 6 this time among the subjects included in the history of detection results, the process proceeds to step S1006. This indicates that the subject that could be detected before could not be detected this time. In step S1006, it is determined whether or not the subject not detected this time is included N or more times following the signal S6 output from the subject detection circuit 6. This is because the subject is not always stationary, and if the subject turns back or another subject crosses the front, the previously detected subject may not be detected temporarily. is there. Therefore, even if a subject that has been detected until then can no longer be detected, it is desirable to maintain it as a detection region if it is temporary. Therefore, whether or not to maintain the detection area is switched depending on whether or not the number of continuous detections has reached N times.

  As a result of the determination, the subject whose number of times not included in the signal S6 is less than N times is set as a detection target region, and the process proceeds to step S1007. In step S1007, the size of the detection area is determined from the size of the history subject according to the relationship shown in FIG. 2, and is added to the signal S7 together with information on the coordinate position of the history subject. That is, the signal S7 includes a detection area based on the position and size of the subject detected this time by the subject detection circuit 6, and a subject that was not detected this time by the subject detection circuit 6 but was detected within the past N times. A detection area based on the position and size of the. The N times as the threshold value may be a value set from the outside or a predetermined value.

  On the other hand, as a result of the comparison in step S1005, if all the results included in the history of detection results are included in the signal S6 output from the subject detection circuit 6, the process proceeds to step S1008. Also, as a result of the determination in step S1006, if it is not included more than N times, the process proceeds to step S1008. That is, the signal S7 includes only a detection region based on the position and size of the subject detected this time by the subject detection circuit 6.

Next, in step S1008, it is determined whether or not to end the process for determining the detection area. As a result of the determination, if the process ends, the process ends. If not, the process returns to step S1001, and the process of determining the detection area is started again.
Note that the subject detection area determination circuit 7 detects when the subject detection circuit 6 has not detected a subject at all so far, or when all subjects in the detection result history have not been detected more than N times. An initial value is set as an area. According to this initial value, the area having the largest area in the range in which the subject can be detected until the image signal S3 is updated is set as the subject detection area at the center of the screen. This is because the probability of detecting a subject is increased as much as possible by setting as wide a range as possible in the subject detection region around the center of the screen where the subject's existence probability is high.

  As described above, according to the present embodiment, the method for detecting a subject is changed by changing the region where the subject is detected during standby for moving image recording and during recording of a moving image. While waiting for moving image recording, by detecting as many subjects as possible over a wide range of the screen and accumulating their histories, it is possible to extract a region suitable for the subject detection region in advance. During moving image recording, the time required for detecting a subject can be improved by limiting the detection area and detecting the subject based on the accumulated information. As a result, it is possible to detect the subject with high accuracy during recording of a moving image and to reduce the time required for the processing for detecting the subject.

(Second Embodiment)
Hereinafter, a second embodiment of the present invention will be described with reference to the drawings.
FIG. 3 is a block diagram illustrating a configuration example of the imaging apparatus 300 according to the present embodiment.
In FIG. 3, the imaging apparatus 300 includes a lens 1, an imaging device 2, an AFE 3, a camera signal processing circuit 4, a moving image recording processing circuit 5, a subject detection circuit 6, a subject detection region determination circuit 72, a CPU 82, and a lens drive control circuit 9. It has. The operation of the lens 1, the image pickup device 2, the AFE 3, the camera signal processing circuit 4, the moving image recording processing circuit 5, and the subject detection circuit 6 is the same as that of the first embodiment, and the description thereof is omitted. In the present embodiment, only the subject detection area determination circuit 72, the CPU 82, and the lens drive control circuit 9 will be described.

  The CPU 82 outputs a signal indicating the moving image recording state as a signal S81 and outputs a signal relating to lens driving control as the signal S82. Similarly to the first embodiment, the signal S81 is output as 1 when a moving image is being recorded, and the signal S81 is output as 0 when the moving image recording is on standby.

  The subject detection area determination circuit 72 receives the signal S6 output from the subject detection circuit 6 and the signal S81 and signal S82 output from the CPU 82. When the signal S81 output from the CPU 82 is 0, it means that the moving image recording is waiting, and the following processing is performed.

  While moving image recording is on standby, as in step S1002 in FIG. 10, subject detection processing is performed on the entire screen, so the read start address and read image size are set to be the full screen in the image data stored in the memory. And output as a signal S72. Similarly to step S1003, the signal S6 output from the subject detection circuit 6 is held as a history of detection results. The number for holding the history may be a value set from the outside or a predetermined value.

  On the other hand, when the signal S81 output from the CPU 82 is 1, it means that a moving image is being recorded, so the following processing is performed. The subject detection area circuit 72 determines the size of the detection area according to the relationship shown in FIG. 4A from the size of the detected subject of the signal S6 output from the subject detection circuit 6. Then, together with information on the coordinate position of the subject included in the signal S6 output from the subject detection circuit 6, the signal S72 is output.

  The minimum value Aw of the size of the detection area shown in FIG. 4A is determined by the relationship shown in FIG. Further, the position information of the lens 1 is acquired from the value of the signal S82 output from the CPU 82, the value of A is obtained from the position information, and set as an offset, thereby setting the size of the detection region.

  In addition, what is shown to Fig.4 (a) is an example. As the detected size increases, the size of the detection region increases. When the detected size is the same, if the size of the detection region is larger on the tele side than on the wide side, the lens 1 The characteristic of the graph may be changed depending on the position of. 4B is also an example, and it is sufficient that the value of A increases as the position of the lens 1 moves from the wide end toward the tele end.

  Next, as in step S1005 of FIG. 10, the signal S6 output from the subject detection circuit 6 is compared with the history of detection results held. As a result of this comparison, if there is a subject that has not been detected this time by the subject detection circuit 6 among the subjects included in the history of detection results, the detection target is detected until N detections fail continuously. Keep as an area. This is the same as in the first embodiment.

  Then, the size of the detection area is determined from the size of the history subject according to the relationship shown in FIGS. 4A and 4B, and is output as a signal S72 together with information on the coordinate position of the history subject. . The N times as the threshold value may be a value set from the outside or a predetermined value.

  On the other hand, the lens drive control circuit 9 receives the signal S82 output from the CPU 82, and calculates the moving direction of the lens 1 and the moving amount of the lens 1 based on the signal S82. Then, a control signal for driving the lens 1 is output as a signal S9.

  As described above, according to the present embodiment, the method for detecting a subject is changed by changing the region for subject detection during standby for movie recording and during movie recording, and further, the position information of the zoom lens is added. Accordingly, the size of the area for detecting the subject is dynamically controlled. As a result, it is possible to detect the subject with high accuracy during recording of a moving image and to reduce the time required for the processing for detecting the subject.

(Third embodiment)
Hereinafter, a third embodiment of the present invention will be described with reference to the drawings.
FIG. 5 is a block diagram illustrating a configuration example of the imaging apparatus 500 according to the present embodiment.
In FIG. 5, the imaging apparatus 500 includes a lens 1, an imaging device 2, an AFE 3, a camera signal processing circuit 4, a moving image recording processing circuit 5, a subject detection circuit 6, a subject detection area determination circuit 73, a CPU 83, and a resizing processing circuit 10. I have.

  Note that the operation of the lens 1, the image pickup device 2, the AFE 3, the camera signal processing circuit 4, and the subject detection circuit 6 is the same as that of the first embodiment, and thus description thereof is omitted. Also, with respect to the moving image recording processing circuit 5, the operation is the same as that of the first embodiment because the input signal is the image signal S 10 output from the resizing processing circuit 10, and the description thereof will be omitted. In the present embodiment, only the subject detection area determination circuit 73, the CPU 83, and the resizing processing circuit 10 will be described.

  The CPU 83 outputs a signal indicating the moving image recording state as a signal S81, and outputs a signal related to the zoom magnification of the electronic zoom as a signal S83. Similarly to the first embodiment, when a moving image is being recorded, the signal S81 is output as 1, and when the moving image recording is in a standby state, the signal S81 is output as 0.

  The subject detection area determination circuit 73 receives the signal S6 output from the subject detection circuit 6 and the signals S81 and S83 output from the CPU 83. If the signal S81 output from the CPU 83 is 0, it means that the moving image recording is waiting, and the following processing is performed.

  While moving image recording is on standby, as in step S1002 of FIG. 10, subject detection processing is performed on the entire screen, so the read start address and read image size are set to be the entire screen of the image data stored in the memory. And output as a signal S73. Similarly to step S1003, the signal S6 output from the subject detection circuit 6 is held as a history of detection results. The number for holding the history may be a value set from the outside or a predetermined value.

  On the other hand, when the signal S81 output from the CPU 83 is 1, it means that a moving image is being recorded, so the following processing is performed. FIG. 6 is a conceptual diagram illustrating an example in which resizing processing is performed by the resizing processing circuit 10 during recording of a moving image in the present embodiment.

  When the zoom magnification of the signal S83 output from the CPU 83 is 0, the entire image of the image signal S4 output from the camera signal processing circuit 4 is recorded as a moving image. Therefore, the clipping process is not performed and the entire screen is set as the subject detection area. Further, the image size for performing the moving image recording process in the moving image recording processing circuit 5 is constant. Therefore, as the zoom magnification increases, the image size for performing the clipping process in the resize processing circuit 10 from the image of the image signal S4 output from the camera signal processing circuit 4 decreases. Therefore, control is performed so as to change the detection area of the subject in accordance with the zoom magnification of the signal S83 output from the CPU 83.

  Based on the zoom magnification of the signal S83 output from the CPU 83, the size of the detection area is determined according to the relationship shown in FIG. 7, and is output as a signal S73 along with information on the coordinate position where the clipped image and the center match by resizing processing. Note that the example shown in FIG. 7 is an example, and it is only necessary that the detection area becomes smaller as the zoom magnification becomes higher.

  The same effect can be obtained by changing the size of the subject detection processing area according to the subject detection result using the signal S6 output from the subject detection circuit 6. A coefficient for multiplying the size of the detection area is determined from the detection result of the largest subject among the detected subject sizes in the signal S6 output from the subject detection circuit 6 according to the relationship shown in FIG. Then, the size of the detection area is determined by multiplying the size of the detection area obtained from the relationship shown in FIG. Output as S73.

  When no subject is detected in the signal S6 output from the subject detection circuit 6, a history of detection results is referred to. As a result, when N times are not continuously detected, multiplication is not performed, and the size of the detection area obtained from the relationship shown in FIG. 7 is output as a signal S73.

  On the other hand, if the subject is detected within N times as a result of referring to the detection result history, a coefficient to be multiplied by the size of the detection region is determined from the detection result history according to the relationship shown in FIG. Then, the size of the detection area is determined by multiplying the size of the detection area obtained from the relationship shown in FIG. Output as signal S73. Note that the example shown in FIG. 8 is an example, and it is sufficient that the coefficient increases as the detected size increases.

  The resize processing circuit 10 receives the image signal S4 output from the camera signal processing circuit 4 and the signal S83 output from the CPU 83. Then, the resizing processing circuit 10 determines the cutout size of the central portion of the image of the image signal S4 output from the camera signal processing circuit 4 according to the value of the signal S83 indicating the zoom magnification output from the CPU 83. Then, the enlargement process is performed and the image signal S10 is output to the moving image recording processing circuit 5.

  As described above, according to the present embodiment, the method for detecting a subject is changed by changing the region for subject detection during standby for video recording and during video recording, and further, the zoom magnification of the electronic zoom can be changed. The size of the detection area is dynamically controlled according to the information. As a result, it is possible to detect the subject with high accuracy during recording of a moving image and to reduce the time required for the processing for detecting the subject.

(Other embodiments according to the present invention)
Each means constituting the image processing apparatus and each step of the image processing method in the embodiment of the present invention described above can be realized by operating a program stored in a RAM or ROM of a computer. This program and a computer-readable storage medium storing the program are included in the present invention.

  In addition, the present invention can be implemented as, for example, a system, apparatus, method, program, storage medium, or the like. Specifically, the present invention may be applied to a system including a plurality of devices. The present invention may be applied to an apparatus composed of a single device.

  In the present invention, a software program for realizing the functions of the above-described embodiment (in the embodiment, a program corresponding to the flowcharts shown in FIGS. 9 and 10) may be supplied directly or remotely to the system or apparatus. Including. This includes the case where the system or the computer of the apparatus is also achieved by reading and executing the supplied program code.

  Accordingly, since the functions of the present invention are implemented by computer, the program code installed in the computer also implements the present invention. In other words, the present invention includes a computer program itself for realizing the functional processing of the present invention.

  In that case, as long as it has the function of a program, it may be in the form of object code, a program executed by an interpreter, script data supplied to the OS, and the like.

  Examples of the storage medium for supplying the program include a flexible disk, a hard disk, an optical disk, and a magneto-optical disk. Further, there are MO, CD-ROM, CD-R, CD-RW, magnetic tape, nonvolatile memory card, ROM, DVD (DVD-ROM, DVD-R) and the like.

  As another program supply method, there is a method of connecting to a homepage on the Internet using a browser of a client computer. The computer program itself of the present invention or a compressed file including an automatic installation function can be supplied from the homepage by downloading it to a storage medium such as a hard disk.

  It can also be realized by dividing the program code constituting the program of the present invention into a plurality of files and downloading each file from a different homepage. That is, a WWW server that allows a plurality of users to download a program file for realizing the functional processing of the present invention on a computer is also included in the present invention.

  As another method, the program of the present invention is encrypted, stored in a storage medium such as a CD-ROM, distributed to users, and encrypted from a homepage via the Internet to users who have cleared predetermined conditions. Download the key information to be solved. It is also possible to execute the encrypted program by using the key information and install the program on a computer.

  Further, the functions of the above-described embodiments are realized by the computer executing the read program. Furthermore, based on the instructions of the program, an OS or the like running on the computer performs part or all of the actual processing, and the functions of the above-described embodiments can be realized by the processing.

  As another method, a program read from a storage medium is first written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer. Then, based on the instructions of the program, the CPU or the like provided in the function expansion board or function expansion unit performs part or all of the actual processing, and the functions of the above-described embodiments are also realized by the processing.

1 is a block diagram illustrating a configuration example of an imaging apparatus according to a first embodiment of the present invention. It is a figure which shows an example of the relationship between the magnitude | size of the detected to-be-photographed object and a detection area | region in the 1st Embodiment of this invention. It is a block diagram which shows the structural example of the imaging device which concerns on the 2nd Embodiment of this invention. It is a figure which shows an example of the relationship between the magnitude | size of the detected to-be-photographed object, the position of a lens, and a detection area | region in the 2nd Embodiment of this invention. It is a block diagram which shows the structural example of the imaging device which concerns on the 3rd Embodiment of this invention. In the 3rd Embodiment of this invention, it is a conceptual diagram which shows the example in which the resizing process is performed by the resizing process circuit during the recording of a moving image. In the 3rd Embodiment of this invention, it is a figure which shows an example of the relationship between a zoom magnification and a detection area. It is a figure which shows an example of the relationship between the magnitude | size of the to-be-detected to-be-photographed object, and the coefficient by which a detection area is multiplied in the 3rd Embodiment of this invention. 4 is a flowchart illustrating an example of a processing procedure for subject detection by a subject detection circuit according to the first embodiment of the present invention. It is a flowchart which shows an example of the process sequence which determines the detection area by the to-be-photographed object detection area determination circuit in the 1st Embodiment of this invention.

Explanation of symbols

1 Lens 2 Image Sensor 3 AFE
4 Camera Signal Processing Circuit 5 Movie Recording Processing Circuit 6 Subject Detection Circuit 7 Subject Detection Area Determination Circuit 8 CPU
100 Imaging device

Claims (11)

An image input means for inputting an image signal constituting the moving image data,
A subject detecting means for detecting a specific object from an image signal constituting the moving image data input by said image input means,
Area determining means for determining an area to be detected by the subject detecting means;
And recording means for recording the moving image data input by said image input means on a recording medium,
When the moving image data is not being recorded by the recording means, the area determining means sets the area in which the object is detected until the image signal constituting the moving image data is updated. The size is determined so that the detection process is not completed, and when the moving image data is being recorded by the recording unit, the area where the subject is detected is updated until the image signal constituting the moving image data is updated. The image processing apparatus is characterized in that the size is determined so that the subject detection process is completed during the period . When the moving image data is not being recorded by the recording means, the area determining means determines the entire image signal as an area for detecting the subject, and the moving image data is being recorded by the recording means The image processing apparatus according to claim 1, wherein a part of the image signal is determined as an area for detecting the subject.   The area determining means determines an area in which the subject is detected without being based on a history of detection results by the subject detecting means when the moving image data is not being recorded by the recording means, and the moving image by the recording means is determined. The image processing apparatus according to claim 1, wherein when data is being recorded, an area in which the subject is detected is determined based on a history of detection results by the subject detection unit.   When the moving image data is being recorded by the recording unit, the region determining unit determines the size of the region where the subject is detected according to the size of the subject detected by the subject detecting unit. The image processing apparatus according to claim 2, wherein: Said image input means comprises a lens and an image processing apparatus according to claim 1, characterized in that it comprises an imaging device for generating the dynamic image data from a subject image projected by the lens .   6. The area determination unit according to claim 5, wherein when the moving image data is being recorded by the recording unit, the area determination unit determines a size of an area for detecting a subject according to the position of the lens. The image processing apparatus described.   6. The area determination unit according to claim 5, wherein when the moving image data is being recorded by the recording unit, the region determination unit determines a size of a region for detecting a subject in accordance with a magnification of the electronic zoom. The image processing apparatus described. Claim the subject detecting means, wherein when the recording means is being recorded moving image data, which is characterized in that the detection from the moving image data of different image size and dynamic image data to be recorded on said recording medium The image processing apparatus according to 2 or 3. An image input step of inputting an image signal constituting the moving image data,
A subject detection step of detecting a specific object from the image signal constituting the moving image data input in the image input step,
A region determining step for determining a region for detection in the subject detection step;
And a recording step of recording the moving image data input in the image input step to the recording medium,
In the area determination step, when the moving image data is not being recorded in the recording step, the area in which the object is detected is set as the area until the image signal constituting the moving image data is updated. When the moving image data is being recorded in the recording process, the image signal constituting the moving image data is updated in the area where the subject is detected. The image processing method is characterized in that the size is determined so that the subject detection process is completed in the meantime . An image input step of inputting an image signal constituting the moving image data,
A subject detection step of detecting a specific object from the image signal constituting the moving image data input in the image input step,
A region determining step for determining a region for detection in the subject detection step;
And a recording step of recording the moving image data input in the image input step to the recording medium is executed by a computer,
In the area determination step, when the moving image data is not being recorded in the recording step, the area in which the object is detected is set as the area until the image signal constituting the moving image data is updated. When the moving image data is being recorded in the recording process, the image signal constituting the moving image data is updated in the area where the subject is detected. A program that causes a computer to execute the process so as to determine a size at which the subject detection processing is completed .   A computer-readable storage medium storing the program according to claim 10.

Images