JP2008160280A - Imaging apparatus and automatic imaging method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an imaging apparatus and an automatic imaging method capable of performing automatic imaging with few imaging failure. <P>SOLUTION: A face detection portion 50 detects a face segment from an image photographed in preliminary imaging. A motion detection portion 60 detects movement within the image from a plurality of pictures photographed in preliminary imaging. A reception portion receives the number of faces segment to be detected and information for establishing a predetermined amount of movements. A control portion 10 performs automatic imaging, when the number of face segments detected by the face detection portion 50 matches with the number of face segments received from the reception portion and the amount of movements detected by the motion detection portion 60 is smaller than the predetermined amount of movements. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an imaging apparatus equipped with an automatic imaging function and an automatic imaging method.

  Digital still cameras and digital video cameras have become widespread, and it has become easier for general users to take photos and videos than ever before. A general user often takes a person as a subject such as a commemorative photo, and there is a strong demand for taking a picture of a person including himself. In particular, at travel destinations, there are many users who want to take pictures and videos of all of their family members, friends, and lovers.

In response to such demands, various automatic imaging techniques have been proposed and put into practical use. For example, a camera equipped with a self-timer function that takes a picture after a certain period of time using a timer has been widely put into practical use. In addition, a function of imaging when various sensors such as distance, sound, and light detect a certain value has been proposed (for example, see Patent Document 1).
JP-A-3-265282

  However, in the automatic imaging technology as described above, the automatic imaging function is activated against the photographer's intention when not all of the persons who are the subjects are in the shooting position or while the person is posing. May end up.

  The present invention has been made in view of such circumstances, and an object thereof is to provide an imaging apparatus and an automatic imaging method capable of automatic imaging with few imaging failures.

  In order to solve the above-described problems, an imaging apparatus according to an aspect of the present invention includes a face detection unit that detects a face region from a pre-captured image, a face region detected by the face detection unit, and satisfying a predetermined condition. A control unit that executes automatic imaging.

  According to this aspect, not only the face area is detected but also the imaging failure can be reduced by executing the automatic imaging when a predetermined condition is satisfied.

  You may further provide the reception part which receives conditions from a user. The reception unit may receive the number of face areas to be detected. The control unit may perform automatic imaging when the number of face areas detected by the face detection unit corresponds to the number of face areas received from the reception unit.

  According to this aspect, when the number of face areas corresponds, by executing automatic imaging, it is possible to avoid a situation in which imaging is performed before all the subjects are aligned.

  You may further provide the motion detection part which detects the motion in an image from several pictures imaged by preliminary imaging. The control unit may perform automatic imaging when the number of face regions corresponds and the motion amount detected by the motion detection unit is smaller than a predetermined motion amount. “Picture” is a unit of encoding, and the concept may include a frame, a field, a VOP (Video Object Plane), and the like.

  According to this aspect, when the amount of motion is smaller than the predetermined amount of motion, by performing automatic imaging, the image is captured before the subject is ready, such as moving to the shooting position or deciding on the pose. Can be avoided.

  The reception unit may receive information for setting a predetermined amount of movement from the user. According to this, the user can adjust the sensitivity of the automatic imaging function.

  The control unit may perform automatic imaging when the face area detected by the face detection unit is in focus. Automatic imaging may be performed when the number of face areas detected by the face detection unit corresponds to the number of face areas received from the reception unit, and the face area detected by the face detection unit is in focus. . According to these, a high-quality image can be automatically captured.

  Another aspect of the present invention is an automatic imaging method. In this method, when a face area is detected from a pre-captured image and a predetermined condition is satisfied, automatic imaging is executed.

  According to this aspect, not only the face area is detected but also the imaging failure can be reduced by executing the automatic imaging when a predetermined condition is satisfied.

  It should be noted that any combination of the above-described constituent elements and a conversion of the expression of the present invention between a method, an apparatus, a system, a recording medium, a computer program, etc. are also effective as an aspect of the present invention.

  According to the present invention, automatic imaging with few imaging failures is possible.

  FIG. 1 is a configuration diagram of an imaging apparatus 100 according to the embodiment. The imaging apparatus 100 according to the embodiment includes a control unit 10, an imaging unit 20, a distance measuring unit 30, a focus / exposure adjustment unit 40, a face detection unit 50, a motion detection unit 60, an operation unit 70, a display unit 80, and a recording unit 90. Is provided. These configurations can be realized in hardware by any computer's CPU, memory, and other LSIs, and in software, they are realized by programs loaded into the memory. Draw functional blocks. Therefore, those skilled in the art will understand that these functional blocks can be realized in various forms by hardware only, software only, or a combination thereof.

  The control unit 10 controls the entire imaging apparatus 100. In the present embodiment, the following processing is mainly performed. The control unit 10 sets the number of faces to be detected in the image as a set value in the face detection unit 50, and receives from the face detection unit 50 as a detection result whether or not the set number of faces have been detected. In addition, the control unit 10 sets an allowable value of the amount of motion generated in the image as a set value in the motion detection unit 60, and determines whether the detected motion amount is smaller than the set value from the motion detection unit 60 as a detection result. receive. The control unit 10 determines whether to record the image data received from the imaging unit 20 in the recording unit 90. For example, image data obtained by preliminary imaging described later is basically not recorded. In addition, the control unit 10 compresses and encodes the image data received from the imaging unit 20 using a JPEG (Joint Photographic Expert Group) format or the like.

  The imaging unit 20 includes an imaging device such as a CCD (Charge Coupled Devices) sensor and a CMOS (Complementary Metal-Oxide Semiconductor) image sensor, an optical system, a zoom mechanism, a diaphragm mechanism, and the like. Convert and output to the control unit 10. The imaging unit 20 performs preliminary imaging when an automatic imaging mode described later is selected. The imaging unit 20 continuously captures images at a predetermined interval during preliminary imaging. Further, when the imaging apparatus 100 is equipped with a moving image imaging mode, that mode may be used. Note that the pre-captured image is used to determine the timing for automatic imaging, and is deleted when the timing determination processing ends.

  The distance measuring unit 30 measures a distance to an area to be focused (hereinafter referred to as an adjustment target area). The focus / exposure adjustment unit 40 performs focus adjustment by controlling the lens mechanism based on the distance measured by the distance measurement unit 30. Further, the focus / exposure adjustment unit 40 performs exposure adjustment by controlling the aperture mechanism and the shutter speed so that the adjustment target region has a suitable brightness. Note that focus adjustment may be performed based on the contrast of the captured image. In other words, the focus may be changed so that the focus with the highest contrast in the adjustment target region may be selected. In this case, the distance measuring unit 30 is not necessary.

  The face detection unit 50 detects the face of a person from the input image. If there are multiple faces in the input image, all of them are detected. It is determined whether the number of faces set from the control unit 10 matches the number of faces detected from the input image, and the determination result is output to the control unit 10. In addition, when the number of faces increases, such as a class photo, it may be substantially coincident. The face detection may be performed by a known method and is not particularly limited. For example, a face detection method based on edge detection or shape pattern detection, or a face detection method based on hue extraction or skin color extraction can be used.

  Hereinafter, a specific example in the case of using edge detection will be described. In this method, various edge features are extracted from the face area including the face, eyes, nose, mouth, face outline, etc. of the face image in which the face size and tone value are normalized in advance, and the face image is identified. A face discriminator is constructed by learning feature quantities that are effective for learning based on statistical methods.

  In order to detect a face from the input image, similar feature amounts are extracted while performing raster scanning from the end of the input image with the face size normalized during learning. From the feature amount, the discriminator determines whether the region is a face. As the feature amount, for example, a horizontal edge, a vertical edge, a right oblique edge, a left oblique edge, or the like can be used. If no face is detected, the input image is reduced at a certain rate, and the face is searched for the reduced image while performing raster scanning in the same manner as described above. By repeating such processing, a face of any size can be found in the image.

  The following methods may be used as other face detection methods. A method for extracting a face candidate area, dividing the face candidate area into small areas, comparing the feature amount of each area with a preset face area pattern, and extracting a face area from the accuracy, or a face candidate A method may be used in which a region is extracted and the face region is extracted by evaluating the accuracy from the degree of overlap of each candidate region. Furthermore, when face candidate areas are extracted and the density of each candidate area is a value corresponding to a predetermined threshold, the body candidate areas are extracted, and accuracy is determined using the density or saturation contrast of the face and body candidate areas. May be used to extract a face region.

  The motion detection unit 60 detects the amount of motion in the input image by calculating the difference between the pre-captured frames. It is determined whether or not the amount of movement is smaller than a set value set by the control unit 10, and the determination result is output to the control unit 10. The pre-captured frame is temporarily stored in a work area such as a RAM. The motion detector 60 calculates the difference between the current frame and the previous frame. In addition, the difference between the current frame and a plurality of frames two or more frames before may be calculated. If the pre-captured image is MPEG (Moving Picture Experts Group) format data, a motion vector may be used as the motion amount.

  The operation unit 70 includes various buttons such as a shutter button. The user can instruct the control unit 10 to transition to the automatic imaging mode by operating the operation unit 70. At the same time, a condition for triggering automatic imaging can be set in the control unit 10. First, the number of faces detected in a frame can be set as the above condition. For example, when taking a group photo of three people, the number of faces is set to three.

  In addition, the amount of motion to be set as a set value in the motion detector 60 can be set as the above condition. The design may be such that the user does not directly set the motion amount, but the user selects one from a plurality of modes corresponding to a plurality of candidates for the motion amount. Note that the amount of movement may not be set by the user, but may be registered in advance in the control unit 10 and used.

  The display unit 80 displays a captured image, a setting screen for the above conditions, and various other information. The recording unit 90 includes a memory card slot, a DVD, or an HDD, and records captured images on a recording medium.

  Next, the automatic imaging mode in the imaging apparatus 100 according to the present embodiment will be described. In the following example, it is assumed that a two-shot photograph is taken with a lover or a friend. The user sets 2 from the operation unit 70 as the number of faces to be detected by the face detection unit 50. Further, a desired amount of movement is set from the operation unit 70.

  2 (a)-(b) and FIGS. 3 (a)-(b) show images preliminarily captured during the automatic imaging mode. Only one person is detected in the image shown in FIG. 2A, and the number of faces detected from the image is also one. Therefore, the automatic imaging function is not activated. Two people are detected in the image shown in FIG. 2B, but one person is moving. This situation is assumed when the user who has set the automatic imaging mode is moving in front of the imaging apparatus 100 so that he / she can fit in the frame. Although the number of faces detected from within this image is two, since the detected amount of motion is larger than the set value, the automatic imaging function is not activated.

  Two persons are detected in the image shown in FIG. 3A, and the two persons are stationary. The amount of motion detected from within the image is also smaller than the set value. Therefore, the automatic imaging function is activated. Three persons are detected in the image shown in FIG. Moreover, one person is moving. This situation occurs when a passerby or the like who is not involved in shooting enters the frame. Since three faces are detected and the detected amount of motion is larger than the set value, the automatic imaging function is not activated.

  FIG. 4 is a flowchart for explaining the operation of the imaging apparatus 100 according to the present embodiment. First, the user operates the operation unit 70 to change the imaging apparatus 100 to the automatic imaging mode, and sets the number of subjects and the allowable amount of movement. The control unit 10 refers to the control signal input from the operation unit 70, sets the number of faces to be detected in the face detection unit 50, and sets a motion amount serving as a threshold value in the motion detection unit 60 (S10). . The imaging unit 20 starts preliminary imaging in accordance with an instruction from the control unit 10 (S12).

  The face detection unit 50 detects a face from the preliminary captured image (S14). The control unit 10 compares the number of faces detected from the pre-captured image with the set number of faces (S16). If they do not match (N in S16), the process proceeds to step S12, and the preliminary imaging is continued (S12). If they match (Y in S16), the motion detector 60 detects the amount of motion in the pre-captured image (S18). For example, the difference between the pre-captured frames is calculated.

  The control unit 10 compares the detected amount of motion with the set amount of motion (S20). If the detected amount of motion is equal to or greater than the set amount of motion (N in S20), the process proceeds to step S12, and preliminary imaging is continued (S12). When the detected amount of motion is less than the set amount of motion (Y in S20), the control unit 10 instructs the imaging unit 20 to perform actual imaging (S22).

  As described above, according to the present embodiment, automatic imaging with few imaging failures is possible. For example, when taking a human photo automatically, when all the subjects are not ready, while the subject is posing, or when a person, animal or object that is not the subject of shooting enters the imaging spot It is possible to reduce the situation where the image is captured. As a result, re-shooting can be reduced, leading to a reduction in power consumption. In addition, the usage amount of the recording medium is reduced.

  It is also possible to use a remote control, but many people lose or misplace the remote control and often do not have it when they want to shoot. In this regard, according to the present embodiment, it can be used anytime when automatic imaging is desired. In addition, it is possible to appropriately cope with the occurrence of an imaging interruption cause that is difficult for the remote control operator to enter the field of view, such as a person passing behind the remote control operator.

  The present invention has been described based on some embodiments. It should be understood by those skilled in the art that these embodiments are exemplifications, and that various modifications can be made to combinations of the respective components and processing processes, and such modifications are within the scope of the present invention. is there.

  In the above embodiment, the user sets the number of subjects and the allowable amount of movement from the operation unit 70. In this regard, the following conditions may be set instead of the allowable motion amount or in addition to the above two setting items. It may be set as a condition whether or not the face is in focus. The control unit 10 acquires a focus position from the focus / exposure adjustment unit 40 and acquires a face position from the face detection unit 50, thereby determining whether or not the face is in focus. When the face is in focus and the other setting conditions are satisfied, the control unit 10 instructs the image capturing unit 20 to capture an image. As a result, an image in which the face is in focus can be automatically captured.

  Further, the following conditions may be set instead of the allowable movement amount or in addition to the above two or three setting items. The amount of change in luminance value in the pre-captured image may be set as a condition. Images captured when the brightness changes suddenly, such as when the sun comes out of the clouds or when the sun is hidden in the clouds, tend to be of poor quality. The control unit 10 instructs the imaging unit 20 to capture an image when a change amount exceeding the set change value of the luminance value is not detected and when other setting conditions are satisfied. The amount of change in the luminance value to be set may be a value obtained by the designer through experiments or simulations, or a value set by the user from the operation unit 70. Thereby, a high quality image can be automatically captured.

  Further, the following conditions may be set instead of the allowable motion amount or in addition to the two, three, or four setting items. It may be set as a condition whether or not there is a point having an extremely high luminance value in the face area. When a point having an extremely high luminance value exists in the face area, the glasses may reflect light, and the quality of an image captured in this state tends to deteriorate. The control unit 10 instructs the imaging unit 20 to take an image when a luminance value exceeding the set luminance value is not detected from the face area and when other setting conditions are satisfied. The luminance value to be set may be a value obtained by the designer through experiments or simulations, or a value set by the user from the operation unit 70. Thereby, a high quality image can be automatically captured.

  Further, when the motion detection unit 60 detects the amount of motion in the pre-captured image, the detection range in the image may be limited, or weighting may be performed according to the region. For example, the face area and the area adjacent to the face area may be set as the detection range, and other areas may be outside the detection range. In this case, the automatic imaging mode can be used even when there is movement in the background, such as when there is a fountain in the background. Also, the weight of the face area may be set higher than other areas. In this case, the blink detection accuracy can be increased.

  In the above-described embodiment, a human face is assumed, but an animal face such as a dog or a cat may be used. The imaging apparatus 100 may be equipped with a dog automatic imaging mode or a cat automatic imaging mode. By constructing a dog face discriminator and a cat face discriminator, respectively, the same principle as in the case of a human face can be implemented.

It is a block diagram of the imaging device which concerns on embodiment. FIGS. 2A to 2B show images preliminarily captured during the automatic imaging mode. 3A and 3B show images preliminarily captured during the automatic imaging mode. It is a flowchart for demonstrating operation | movement of the imaging device which concerns on embodiment.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 10 Control part, 20 Imaging part, 30 Distance measuring part, 40 Focus and exposure adjustment part, 50 Face detection part, 60 Motion detection part, 70 Operation part, 80 Display part, 90 Recording part, 100 Imaging device

Claims (6)

A face detection unit for detecting a face region from the pre-captured image;
A control unit that executes automatic imaging when a face region is detected by the face detection unit and a predetermined condition is satisfied;
An imaging apparatus comprising: A reception unit for receiving the condition;
The reception unit receives the number of face areas to be detected,
The said control part performs the said automatic imaging, when the number of the face areas detected by the said face detection part and the number of the face areas received from the said reception part correspond. Imaging device. A motion detector for detecting motion in the image from a plurality of pre-captured pictures;
The said control part performs the said automatic imaging, when the number of the said face area | region respond | corresponds and the motion amount detected by the said motion detection part is smaller than predetermined | prescribed motion amount. Imaging device.   The imaging apparatus according to claim 3, wherein the reception unit receives information for setting the predetermined movement amount.   The imaging apparatus according to claim 1, wherein the control unit executes the automatic imaging when the face area detected by the face detection unit is in focus.   An automatic imaging method, wherein a face area is detected from a pre-captured image and automatic imaging is executed when a predetermined condition is satisfied.

Images