JP2011114673A - Imaging apparatus and posture control program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a technology by which a subject image is picked up in desired composition without using a posture control apparatus. <P>SOLUTION: The imaging apparatus includes: an imaging part which picks up the subject image to generate an image; a recognition part which recognizes first and second feature parts of the subject image from the picked up image; an extraction part which extracts feature quantities of the first and second recognized feature parts; an operation part which calculates a correction amount for correcting a posture of the imaging apparatus to a predetermined posture based on the feature quantities of the first and second feature parts and an index showing the predetermined posture of the imaging apparatus; and a control part which instructs posture control of the imaging apparatus according to the correction amount. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to an imaging apparatus and a posture control program that can be controlled to a desired posture.

  2. Description of the Related Art Conventionally, in order to capture a subject image with a desired composition, various techniques have been developed to let a user know and control the attitude of a digital camera, a digital video camera, or the like.

  For example, Japanese Patent Laid-Open No. 2004-151867 provides an intuitive view of the attitude of a digital camera on a monitor screen of a digital camera according to angle data detected by an attitude detection device such as a gyro sensor or a gravity sensor. The technology to display in a way that can be grasped is disclosed.

JP 2002-271654 A

  However, in the conventional technology, since the control of the posture of the digital camera according to the angle data from the posture control device is based on the direction of gravity, for example, when the heights of the eyes of the subject and the photographer are different from each other, It is difficult to shoot with matching. In such a case, the photographer shoots the subject from bottom to top (tilting) or from top to bottom (overhead shooting).

  SUMMARY OF THE INVENTION In view of the above-described problems of the related art, an object of the present invention is to provide a technique that can capture a subject image with a desired composition without using an attitude control device.

  In order to solve the above-described problems, an imaging apparatus according to the present invention recognizes a first feature part and a second feature part of a subject image from the imaged unit that captures the subject image and generates the image. A recognition unit, an extraction unit for extracting feature amounts of the recognized first feature portion and second feature portion, a feature amount of the first feature portion and the second feature portion, and a predetermined posture of the imaging device. And a control unit that calculates a correction amount for correcting the posture of the imaging apparatus to a predetermined posture based on the indicated index, and a control unit that instructs posture control of the imaging device according to the correction amount.

  In addition, a display unit that displays an instruction for attitude control of the imaging apparatus by the control unit may be provided.

  In addition, an audio output unit that outputs an instruction to control the attitude of the imaging apparatus by the control unit to the outside may be provided.

  In addition, the calculation unit may further include a changing unit that changes the index according to the recognition result of the recognition unit.

  In addition, the calculation unit calculates a correction image when the imaging apparatus is controlled in a predetermined posture according to the correction amount and captures a subject image, and the control unit superimposes the correction image on the image obtained by capturing the correction image. May be displayed to instruct posture control of the imaging apparatus.

  In addition, when the recognition unit recognizes a plurality of subject images, the recognition unit includes a selection unit that selects at least one subject image, and the calculation unit includes a first feature portion and a second feature of the subject image selected by the selection unit. The correction amount and the correction image may be calculated based on the feature amount of the part.

  In addition, when there are a plurality of selected subject images, the calculation unit obtains an average value of the feature amounts of the first feature portion and the second feature portion of the plurality of selected subject images, and based on the average value A correction amount and a corrected image may be calculated.

  The posture control program of the present invention causes a computer to recognize a first feature part and a second feature part of a subject image from an image obtained by capturing the subject image, and the recognized first feature part and second feature part. The posture of the imaging device is set to a predetermined posture based on the extraction procedure for extracting the feature amount of the feature portion, the feature amounts of the first feature portion and the second feature portion, and an index indicating the predetermined posture of the imaging device A calculation procedure for calculating a correction amount for correction and a control procedure for instructing attitude control of the imaging apparatus according to the correction amount are executed.

  According to the present invention, it is possible to capture a subject image with a desired composition without using an attitude control device.

The block diagram which shows an example of a structure of the digital camera 1 of one Embodiment. Figure about height ratio A: B 5 is a flowchart showing an operation example of the digital camera 1 according to the embodiment. The figure which shows the positional relationship of the digital camera 1 of 1 embodiment and a to-be-photographed object. Illustration about keystone correction The figure which shows the example of a display in the digital camera 1 of one Embodiment. The block diagram which shows an example of a structure of the digital camera 1 'of other embodiment. Flow chart showing an operation example of a digital camera 1 ′ according to another embodiment. The figure which shows the through image 30 imaged with the digital camera 1 'of other embodiment. The figure which shows the example of a display in the digital camera 1 'of other embodiment.

<< Description of One Embodiment >>
FIG. 1 is a block diagram illustrating an example of a configuration of a digital camera 1 according to an embodiment.

  The digital camera 1 according to the present embodiment includes an imaging optical system 11, an imaging element 12, a DFE 13, a CPU 14, a memory 15, a speaker 16, a monitor 17, a media I / F 18, and an operation unit 20. Here, the DFE 13, the memory 15, the speaker 16, the monitor 17, the media I / F 18, and the operation unit 20 are connected to the CPU 14, respectively.

  The image pickup device 12 is a device that picks up an image of an object formed by a light beam that has passed through the image pickup optical system 11. The output of the image sensor 12 is connected to the DFE 13. Note that the image sensor 12 of the present embodiment may be a progressive scanning solid-state image sensor (CCD or the like) or an XY address type solid-state image sensor (CMOS or the like).

  A plurality of light receiving elements are arranged in a matrix on the light receiving surface of the imaging element 12. In each light receiving element of the image sensor 12, red (R), green (G), and blue (B) color filters are arranged according to a known Bayer array. Therefore, each light receiving element of the imaging element 12 outputs an image signal corresponding to each color by color separation in the color filter. Thereby, the image sensor 12 can acquire a color image at the time of imaging. The image sensor 12 outputs image signals to all the light receiving elements to pick up still images and the like, and outputs image signals to some of the thinned light receiving elements to output moving images and low resolution images for composition confirmation ( Through image).

  The DFE 13 is a digital front-end circuit that performs signal processing such as A / D conversion of image signals input from the image sensor 12 and correction of defective pixels. In this embodiment, the DFE 13 constitutes an image pickup unit together with the image pickup device 12 and outputs an image signal input from the image pickup device 12 to the CPU 14 as image data.

  The CPU 14 is a processor that comprehensively controls each unit of the digital camera 1. For example, the CPU 14 performs autofocus (AF) control by known contrast detection, known automatic exposure (AE) calculation, and the like based on the output of the image sensor 12. Further, the CPU 14 performs digital processing on the image data from the DEF 13. As an example, the digital processing includes interpolation processing, white balance processing, gradation conversion processing, noise removal processing, contour enhancement processing, color conversion processing (such as calculation using a color conversion matrix), and the like. Further, the CPU 14 operates as a subject recognition unit 21, a subject extraction unit 22, a calculation unit 23, and a change unit 24 by executing the program.

  The subject recognition unit 21 recognizes the face of the subject from the captured image using a known face recognition method. The subject recognition unit 21 recognizes the whole body of the subject from the image based on known edge detection.

  The feature amount extraction unit 22 obtains a face size A ′ and a height B ′, which are feature parts of the subject recognized by the subject recognition unit 21 (FIG. 2). As shown in FIG. 2A, the face size A ′ in the present embodiment is the length from the head to the lower jaw, and the height B ′ is the length B ′ from the head to the feet. is there. 2A is a view of the person in FIG. 2B from the top to the bottom, and FIG. 2B is a view of the person from the front at the same eye level. is there. In the present embodiment, the face size A ′ and the height B ′ are obtained in units of pixels, but may be obtained as relative values with respect to the angle of view.

  The calculation unit 23 performs known trapezoidal correction such as keystone correction using the ratio between the face size A ′ and the height B ′ and the height ratio A: B set based on the height ratio table described later. The tilt amount or overhead view amount of the digital camera 1 is calculated. The calculation unit 23 calculates a correction amount for correcting the posture of the digital camera 1 in accordance with the obtained tilt amount or overhead view amount so that the person who is the subject is imaged with the height ratio A: B.

  Here, the height ratio A: B is a ratio between the face size A and the height B when a person is viewed from the front with the same height as the person as shown in FIG. . That is, when the height ratio of the subject is A ′: B ′ = A: B, it indicates that the digital camera 1 is disposed at the position of the line of sight that is the same height as the subject. In the present embodiment, the height ratio A: B is used as an index indicating a predetermined posture of the digital camera 1. The height ratio table is a list of the height ratios A: B according to the age of the person who is the subject. As an example of the data of the height ratio table, infant height ratio A: B = 1: 3, infants 3:10, elementary school students 2: 9, junior high school students 1: 5, and adults 1: 6.

  It is preferable that the data of the height ratio table can be set / changed by the user who is the photographer in accordance with the operation of the operation unit 20. In the present embodiment, when the subject recognition unit 21 recognizes that only the upper body of the person has been imaged, a height ratio table in which the height B is the length of the upper body from the head to the lower end of the image is also stored in the memory 15. Shall. When the change unit 24 receives the result of recognizing the upper body of the subject from the subject recognition unit 21, the change unit 24 reads the height ratio table with the face size: the upper body length as the height ratio A: B. The ratio A: B is set / changed from 1: 6 to 1: 3.

  The memory 15 is a non-volatile flash memory that stores the height ratio table together with various programs and image files executed by the CPU 14.

  The speaker 16 outputs a voice control instruction of the digital camera 1 by the CPU 14 according to the correction amount obtained by the calculation unit 23 and notifies the user.

  The monitor 17 displays an instruction for attitude control of the digital camera 1 by the CPU 14 according to the correction amount obtained by the calculation unit 23 together with the captured image and the like.

  A non-volatile storage medium 19 can be detachably connected to the media I / F 18. The media I / F 18 executes data writing / reading with respect to the storage medium 19. The storage medium 19 includes a hard disk, a memory card incorporating a semiconductor memory, or the like. In FIG. 1, a memory card is illustrated as an example of the storage medium 19.

  The operation unit 20 receives, for example, a recording mode switching input or a still image capturing instruction accompanying recording in the storage medium 19 from the user. For the operation unit 20, a touch panel or the like disposed on the front surface of the monitor 17 can be appropriately selected and used.

  Next, an operation example of the digital camera 1 in the present embodiment will be described with reference to the flowchart of FIG. It is assumed that the digital camera 1 is initially in a bird's-eye posture as shown in FIG. 4A, and the case where the posture of the digital camera 1 is controlled to the same eye level as the subject will be described. Further, it is assumed that the subject is an adult, and the adult height ratio A: B = 1: 6 is set in advance by the operation of the operation unit 20 by the user.

  Step S101: The CPU 14 turns on the power of the digital camera 1 when the user presses the power button of the operation unit 20 or presses the release button halfway. The CPU 14 reads and executes a control program from the memory 15 to initialize the digital camera 1. The CPU 14 causes the imaging device 12 to capture and acquire the through image 30 at a predetermined frame rate (for example, 30 fps). The CPU 14 displays the through image 30 on the monitor 17 (FIG. 4B).

  Step S102: The subject recognition unit 21 recognizes the face of the subject from the through image 30 by a known face recognition method. The CPU 14 determines whether or not the subject recognition unit 21 has recognized the face of the subject. When the face is recognized, the CPU 14 proceeds to step S103 (YES side). If the face is not recognized, the CPU 14 proceeds to step S101 (NO side) and acquires the next through image 30.

  Step S103: The feature amount extraction unit 22 detects the edge between the lower jaw and the head in the image region of the through image 30 in which the face is recognized in Step S102, and extracts the face size A ′.

  Step S104: The subject recognition unit 21 recognizes the whole body of the subject from the through image 30 based on known edge detection. Specifically, the subject recognizing unit 21 searches for the edge of the foot toward the lower end of the through image 30 on the assumption that the foot is immediately below the image area whose face is recognized in step S102. The subject recognition unit 21 recognizes that the entire body of the subject has been detected when the edge of the foot is detected before reaching the lower end of the through image 30. On the other hand, the subject recognizing unit 21 recognizes that the upper body of the subject has been detected when it reaches the lower end of the through image 30 before detecting the bottom edge.

  Step S105: When the subject recognition unit 21 recognizes the whole body of the subject, the CPU 14 proceeds to step S106 (YES side). When the whole body is not recognized, the CPU 14 proceeds to step S107 (NO side).

  Step S106: The feature amount extraction unit 22 extracts the height A 'based on the positions of the head edge detected in step S103 and the foot edge detected in step S104.

  Step S107: The feature amount extraction unit 22 extracts the length from the position of the head edge detected in step S103 to the lower end of the through image 30 as the height A ′ (= the length of the upper body). The changing unit 24 receives a result indicating that the upper body of the subject has been recognized from the subject recognizing unit 21. The changing unit 24 reads the height ratio table having the height B as the upper body length from the memory 15, and sets / changes the adult height ratio A: B from 1: 6 to 1: 3.

  Step S108: The calculation unit 23 performs known trapezoidal correction such as keystone correction using the height ratio A ′: B ′ of the subject obtained from the through image 30 and the height ratio A: B from the height ratio table, and digitally The overhead view amount (or tilt amount) of the camera 1 is calculated. That is, the calculation unit 23 sets the upper base of the length U ′, the lower base of the length D ′, and the height ratio A: B from the height ratio table to the height ratio A: B from the height ratio table. Calculation coefficients for converting a trapezoid having a height B ′ to an upper base having a length U, a lower base having a length D, and a trapezoid having a height B are obtained. The computing unit 23 obtains an overhead amount (or tilt amount) based on the obtained computation coefficient.

  Step S109: The computing unit 23 calculates an angle Θ with respect to the subject of the digital camera 1 based on the horizontal direction from the obtained overhead view amount (or tilt amount). The calculation unit 23 calculates a movement amount X that is a correction amount of the attitude of the digital camera 1 from the angle Θ and the distance L between the digital camera 1 and the subject calculated by the CPU 14 based on the AF control.

  Step S110: The CPU 14 superimposes an instruction to the user to move the digital camera 1 by the movement amount X obtained in Step S109 on the through image 30, and displays it on the monitor 17. FIG. 6 shows a display example of the instruction. FIG. 6A is a display example in which the moving direction is indicated by only an arrow 40 and is indicated. 6B superimposes on the through image 30 a correction image 50 indicating the contour of the subject obtained by the keystone correction by the calculation unit 23 based on the overhead view amount (or the tilt amount) together with the arrow 40. Is a display example instructed. FIG. 6C shows a display example in which the movement amount X and the same trapezoidal lattice pattern 60 as in FIG.

  It should be noted that the arrow 40 and the movement amount X are preferably displayed blinking in order to call the user's attention. In addition, the CPU 14 outputs an instruction to the user to move the digital camera 1 by the movement amount X obtained in step S109, for example, from the speaker 16 by voice as “Please lower the camera a little more”. You may give instructions.

  Step S111: The CPU 14 determines whether or not the height ratio A ′: B ′ matches the height ratio A: B. If they match (YES side), the CPU 14 ends the series of operations. If not, the CPU 14 proceeds to step S101 (NO side). The CPU 14 acquires the next through image 30 and performs the operations in steps S101 to S110 until the height ratio A ': B' and the height ratio A: B match.

  As described above, in this embodiment, since the posture of the digital camera 1 is corrected and controlled to a predetermined posture based on the photographed subject, the subject can be picked up with a desired composition without using a gyro sensor or the like. .

Further, since no gyro sensor or the like is used, the circuit scale of the digital camera 1 can be reduced, and the cost can be reduced.
<< Description of Other Embodiments >>
FIG. 7 shows a configuration diagram of a digital camera 1 ′ according to another embodiment.

  In the case of the same components as those of the digital camera 1 according to the embodiment, the same reference numerals are given to the respective components of the digital camera 1 ′ of the present embodiment, and the description thereof is omitted.

  The difference between the digital camera 1 ′ according to the present embodiment and that of the first embodiment is that, as shown in FIG. 9, when a plurality of subjects are imaged, the correction amount of the posture of the digital camera 1 ′ is calculated. The object selection unit 25 has a subject selection unit 25 for selecting a reference person.

  An operation example of the digital camera 1 ′ in this embodiment will be described with reference to the flowchart of FIG. 8. As in the case of the first embodiment, it is assumed that the digital camera 1 ′ is initially in an overhead view as shown in FIG. 4A, and the digital camera 1 ′ has the same eye level as the subject. Next, the case of attitude control will be described. Further, it is assumed that the subject is an adult, and the adult height ratio A: B = 1: 6 is set in advance by the operation of the operation unit 20 by the user.

  Step S201: The CPU 14 turns on the power of the digital camera 1 'when the power button of the operation unit 20 is pressed by the user or the release button is pressed halfway. The CPU 14 reads and executes the control program from the memory 15 to initialize the digital camera 1 ′. The CPU 14 causes the imaging device 12 to capture and acquire the through image 30 at a predetermined frame rate (for example, 30 fps). The CPU 14 displays the through image 30 on the monitor 17 (FIG. 9).

  Step S202: The subject recognition unit 21 recognizes the face of the subject from the through image 30 by a known face recognition method. In the present embodiment, since the subject recognition unit 21 recognizes a plurality of faces, the subject selection unit 25 displays an instruction to the user to select any person as a correction reference subject. . The subject selection unit 25 receives the selection of the person by the user via a touch panel (not shown) that is arranged on the front surface of the monitor 17 and constitutes the operation unit 20, and sets it as a correction reference subject. The CPU 14 preferably displays the frame 70 superimposed on the through image 30 on the monitor 17 so as to surround the face of the correction reference subject selected by the user (FIG. 9). The CPU 14 determines whether or not the subject recognition unit 21 has recognized the face of the subject. When the face is recognized, the CPU 14 proceeds to step S203 (YES side). If the face is not recognized, the CPU 14 proceeds to step S201 (NO side) and acquires the next through image 30.

  Step S203: The feature amount extraction unit 22 detects the edge between the lower jaw and the head in the image area of the through image 30 in which the face of the correction reference subject is recognized in Step S202, and determines the face size A ′. Extract.

  Step S204: The subject recognition unit 21 recognizes the whole body of the correction reference subject from the through image 30 based on known edge detection. Specifically, the subject recognizing unit 21 searches for the edge of the foot toward the lower end of the through image 30 on the assumption that there is a foot just below the image area where the face of the correction reference subject is recognized in step S202. The subject recognition unit 21 recognizes that the whole body of the correction reference subject has been detected when the bottom edge is detected before reaching the lower end of the through image 30. On the other hand, when the subject recognition unit 21 reaches the lower end of the through image 30 before detecting the bottom edge, the subject recognition unit 21 recognizes that the upper body of the correction reference subject has been detected.

  Step S205: When the subject recognition unit 21 recognizes the whole body of the correction reference subject, the CPU 14 proceeds to step S206 (YES side). When the whole body is not recognized, the CPU 14 proceeds to step S207 (NO side).

  Step S206: The feature amount extraction unit 22 extracts the height A ′ of the correction reference subject based on the positions of the head edge detected in step S203 and the foot edge detected in step S204. .

  Step S207: The feature amount extraction unit 22 extracts the length from the position of the head edge detected in step S203 to the lower end of the through image 30 as the height A ′ (= the length of the upper body). The changing unit 24 receives a result indicating that the upper body of the subject has been recognized from the subject recognizing unit 21. The changing unit 24 reads the height ratio table having the height B as the upper body length from the memory 15, and sets / changes the adult height ratio A: B from 1: 6 to 1: 3.

  Step S208: The calculation unit 23 performs known trapezoidal correction such as keystone correction using the height ratio A ′: B ′ of the correction reference subject obtained from the through image 30 and the height ratio A: B from the height ratio table. And calculate the overhead view amount (or tilt amount) of the digital camera 1 ′.

  Step S209: The computing unit 23 calculates an angle Θ with respect to the correction reference subject of the digital camera 1 'with respect to the horizontal direction from the obtained overhead view amount (or tilt amount). The calculation unit 23 calculates the movement amount X, which is a correction amount of the attitude of the digital camera 1 ′, from the angle Θ and the distance L between the digital camera 1 ′ calculated by the CPU 14 based on the AF control and the correction reference subject. Is calculated.

  Step S210: The CPU 14 superimposes an instruction to the user to move the digital camera 1 'by the movement amount X obtained in step S209 on the through image 30 and displays it on the monitor 17. FIG. 10 shows a display example of instructions. In FIG. 10A, the moving direction is indicated by an arrow 40, and the correction image 50 showing the outline of only the correction reference subject obtained by the keystone correction by the calculation unit 23 based on the overhead view amount (or the tilt amount). In this example, the movement amount X is indicated by being superimposed on the through image 30. FIG. 10B shows not only the correction reference subject but also corrected images 51 and 52 of the contours of other subjects obtained by the keystone correction by the calculation unit 23 based on the overhead amount (or the tilt amount). It is an example of a display instructed by being superimposed on the through image 30. This makes it possible to determine whether or not a subject that has not been selected as a correction reference subject is also captured with a desired composition.

  It should be noted that the arrow 40 and the movement amount X are preferably displayed blinking in order to call the user's attention. In addition, the CPU 14 gives an instruction to the user to move the digital camera 1 ′ by the movement amount X obtained in step S209, for example, from the speaker 16 by voice as “Please lower the camera a little more”. It may be output and instructed.

  Step S211: The CPU 14 determines whether or not the height ratio A ': B' and the height ratio A: B match. If they match (YES side), the CPU 14 ends the series of operations. If not, the CPU 14 proceeds to step S201 (NO side). The CPU 14 acquires the next through image 30 and performs the operations in steps S201 to S210 until the height ratio A ': B' and the height ratio A: B match.

  As described above, in this embodiment, since the posture of the digital camera 1 ′ is corrected and controlled to a predetermined posture based on the photographed subject, the subject is picked up with a desired composition without using a gyro sensor or the like. it can.

Further, since no gyro sensor or the like is used, the circuit scale of the digital camera 1 ′ can be reduced, and the cost can be reduced.
<< Additional items of embodiment >>
(1) In the above embodiment, an example in which the CPU 14 implements each process of the subject recognition unit 21, the feature amount extraction unit 22, the calculation unit 23, the change unit 24, and the subject selection unit 25 of the digital camera in software is described. However, it goes without saying that each of these processes may be realized by hardware using an ASIC.

  (2) In the above embodiment, the subject is a person, but the present invention is not limited to this and can be applied to animals such as dogs and cats.

  (3) In the above embodiment, the value of the height ratio A: B is selected and set by the user in advance from the height ratio table according to the subject before imaging by the digital camera. It is not limited. For example, the CPU 14 may select and set the height ratio A: B from the height ratio table according to the recognition result of the subject recognition unit 21, or the change unit 24 may change the value of the height ratio A: B. Good.

  (4) In the above embodiment, the value of the height ratio A: B in the height ratio table is the ratio between the face size A and the height B when the person is viewed from the front at the same height as the person. The attitude of the digital camera is controlled so that the subject is imaged from the front, but the present invention is not limited to this. For example, even if the subject is an adult, the height ratio A: B of junior high school students other than adults may be set to control the posture of the digital camera. Thereby, not only from the front but also from the front or the overhead view with the desired tilt amount or the overhead view amount.

  Further, as the data of the height ratio table, data having a predetermined tilt amount or a bird's-eye view amount as well as from the front may be created in advance and stored in the memory 15 of the digital camera.

  (5) In the above embodiment, the tilt amount or the overhead view amount is calculated to control the attitude of the digital camera. However, the present invention is not limited to this, and is applied to the attitude control when panning the digital camera. Also good.

  (6) In the above-described other embodiments, when there are a plurality of subjects, one subject is selected by the user as the correction reference subject in step S202. However, the present invention is not limited to this, and a plurality of subjects are corrected. It may be selected as a reference subject. In this case, in step S208, it is preferable that the calculation unit 23 calculates the tilt amount or the overhead amount for each of the selected subjects to obtain an average value. In step S209, the calculation unit 23 calculates the movement amount X and the corrected image using the average value.

  From the above detailed description, features and advantages of the embodiments will become apparent. It is intended that the scope of the claims extend to the features and advantages of the embodiments as described above without departing from the spirit and scope of the right. Further, any person having ordinary knowledge in the technical field should be able to easily come up with any improvements and modifications, and there is no intention to limit the scope of the embodiments having the invention to those described above. It is also possible to use appropriate improvements and equivalents within the scope disclosed in.

DESCRIPTION OF SYMBOLS 1, 1 '... Electronic camera, 11 ... Imaging optical system, 12 ... Imaging element, 13 ... DEF, 14 ... CPU, 15 ... Memory, 16 ... Speaker, 17 ... Monitor, 18 ... Media I / F, 19 ... Storage medium , 21 ... Subject recognition unit, 22 ... Feature extraction unit, 23 ... Calculation unit, 24 ... Change unit, 25 ... Subject selection unit

Claims (8)

An imaging unit that captures a subject image and generates an image;
A recognition unit for recognizing a first feature portion and a second feature portion of the subject image from the captured image;
An extraction unit for extracting feature amounts of the recognized first feature portion and second feature portion;
An operation for calculating a correction amount for correcting the posture of the imaging device to the predetermined posture based on the feature amounts of the first and second characteristic portions and an index indicating the predetermined posture of the imaging device. And
A control unit that instructs posture control of the imaging apparatus according to the correction amount;
An imaging apparatus comprising: The imaging device according to claim 1,
An image pickup apparatus comprising: a display unit that displays an instruction for attitude control of the image pickup apparatus by the control unit. In the imaging device according to claim 1 or 2,
An image pickup apparatus comprising: an audio output unit that outputs an instruction for posture control of the image pickup apparatus by the control unit to the outside. The imaging apparatus according to any one of claims 1 to 3,
The said calculating part is further provided with the change part which changes the said parameter | index according to the recognition result of the said recognition part, The imaging device characterized by the above-mentioned. In the imaging device according to any one of claims 2 to 4,
The computing unit is
According to the correction amount, the imaging device is controlled to the predetermined posture to calculate a correction image when the subject image is captured,
The controller is
An imaging apparatus, wherein the display unit superimposes the corrected image on the captured image and displays the corrected image to instruct posture control of the imaging apparatus. The imaging apparatus according to claim 5,
A selection unit that selects at least one subject image when the recognition unit recognizes a plurality of the subject images;
The computing unit is
An imaging apparatus, wherein the correction amount and the correction image are calculated based on the feature amounts of the first feature portion and the second feature portion of the subject image selected by the selection unit. The imaging device according to claim 6,
The computing unit is
When there are a plurality of the selected subject images, an average value of the feature amounts of the first feature portion and the second feature portion of the plurality of the selected subject images is obtained, and the correction is performed based on the average value. An imaging apparatus characterized by calculating a quantity and a corrected image. On the computer,
A recognition procedure for recognizing a first feature portion and a second feature portion of the subject image from an image obtained by capturing the subject image;
An extraction procedure for extracting feature quantities of the recognized first and second feature parts;
An operation for calculating a correction amount for correcting the posture of the imaging device to the predetermined posture based on the feature amounts of the first and second characteristic portions and an index indicating the predetermined posture of the imaging device. Procedure and
A control procedure for instructing attitude control of the imaging device according to the correction amount;
A posture control program characterized by causing

Images