JP4912117B2 - Imaging device with tracking function - Google Patents

Description

  The present invention relates to an imaging apparatus having a function of tracking a specific tracking target.

  When taking a still image or a moving image using an imaging device, the composition is usually adjusted while checking the subject with a finder or an attached small display. However, since the subject displayed on the viewfinder and the attached small display is small, it is difficult to sufficiently check the subject's reflection. In consideration of this, Japanese Patent Application Laid-Open No. 2004-228561 discloses a technique for enlarging and displaying a human face as a subject at the time of shooting.

  However, when shooting a moving image, it may be difficult to confirm the position of the subject because the subject of interest and other objects move within the shooting region. In such cases, the subject may be missed and out of frame. Alternatively, in order to prevent this, it is necessary for the photographer to carefully track the subject visually, which places a great burden on the photographer.

JP 2005-318515 A

  An automatic tracking technique based on image analysis has been developed as a technique for substituting visual tracking. This can be used to prevent frame out of the subject and reduce the burden on the photographer, but there are often multiple candidates to be tracked in the shooting area. In some cases, the subject to be identified is unknown and tracking that the photographer intended is not performed.

  Further, when the display screen for displaying the photographed image is small, there is a problem that it is difficult to check the appearance of the subject simply by automatically tracking.

  When the subject to be automatically tracked out of the frame, conventionally, the photographer visually confirms the position of the subject in the real space, and pans the imaging device 1 based on the result of the visual inspection. Then I had to try again. In this case, there is a problem that the photographer's observation target goes back and forth between the display screen and the real space, and the composition is disturbed during this time.

In view of the above problems, an object of the present invention is to provide an imaging device with a tracking function that allows a tracking process to function effectively even when there are a plurality of tracking target candidates.
Another object of the present invention is to contribute to facilitating confirmation of a tracking target.
Another object of the present invention is to contribute to facilitating readjustment of the composition when the tracking target is out of the imaging region.

  The imaging device with a tracking function according to the present invention sequentially captures an image capturing unit that obtains captured images arranged in time series, a display unit that can display the captured image, and one or two of the captured images. Tracking target candidate detecting means for detecting the above tracking target candidates, and tracking target selection for selecting one of the two or more tracking target candidates as a tracking target when two or more tracking target candidates are detected And tracking means for tracking the tracking target between the captured images arranged in time series after the tracking target is selected.

  By providing the tracking target selection unit, even when there are a plurality of tracking target candidates, one tracking target is selected, and the tracking target can be tracked.

  Specifically, the tracking target may be specified by an external operation or by face recognition processing when the selection target candidate is a person.

  Further, for example, the display means provides an entire image display area on the display screen, displays the entire image of the captured images arranged in time series in the entire image display area as a moving image, and on the display screen, Separately, a tracking target display area is provided, and an image including the tracking target is enlarged and displayed in the tracking target display area.

  Thereby, it is possible to confirm in detail and easily the appearance of the tracking target while confirming the entire image.

  Further, specifically, for example, it further includes a face detection unit that detects a human face from the captured image, and the tracking target candidate detection unit is configured to detect the captured image based on the detection result of the face detection unit. When each person is detected as the tracking target candidate and the person selected as the tracking target is called a tracking target person, the tracking unit tracks a region including a part or all of the tracking target person. The tracking object is tracked by setting as a region and tracking the tracking region.

  More specifically, for example, the face detection unit extracts an area including the face of the person to be tracked from the captured image as a face area, and the tracking area includes first, second,. And the n-th element tracking area (n is an integer equal to or greater than 2), the first element tracking area is the face area, and the tracking means is on the captured image of the face of the tracking target person. Based on the size and position of the other element tracking area, another element tracking area is set with reference to the face area as the first element tracking area, thereby setting the tracking area.

  Further, for example, the tracking means includes not only the size and position but also the inclination of the face of the tracking target person in the captured image, the orientation of the face of the tracking target person in the captured image, and the imaging apparatus. The tracking area is set with reference to at least one of the inclinations.

  By setting the tracking area in consideration of the inclination of the face and the like, the tracking area is optimized and the tracking is expected to be stabilized.

  Further, for example, after the tracking target is selected, the tracking unit automatically sets a tracking parameter necessary for tracking, displays information according to the set tracking parameter on the display unit, and performs the imaging The apparatus further includes an operation unit that accepts an external operation, and the tracking parameter automatically set by the tracking unit can be changed by a predetermined operation on the operation unit, and the tracking unit When the change is made by the operation, the tracking target is tracked according to the tracking parameter after the change.

Further, for example, after the tracking target is selected, the tracking unit automatically sets a tracking parameter necessary for tracking, causes the display unit to display information according to the set tracking parameter, and the tracking unit The parameter for use includes information defining the tracking area, and the imaging apparatus further includes an operation unit that accepts an external operation, and the tracking parameter that is automatically set by the tracking unit corresponds to the operation unit. It can be changed by a predetermined operation,
When the change is made by the predetermined operation, the tracking unit tracks the tracking target according to the changed tracking parameter.

  Further, for example, the display means displays a predetermined tracking mark at a predetermined position on the basis of the display position of the tracking target in the entire image display area.

  Displaying the tracking mark facilitates confirmation of the position of the tracking target in the imaging region.

  Further, for example, the tracking unit obtains and stores a movement trajectory of the tracking target from each captured image, and when the tracking target goes out of the imaging area, the tracking unit determines a direction in which the tracking target is located based on the moving trajectory. It estimates and performs notification according to the estimated direction.

  This facilitates readjustment of the composition when the tracking target goes out of the imaging area.

  Further, for example, the tracking unit obtains and stores a movement trajectory of the tracking target from each captured image, and when the tracking target goes out of the imaging area, the tracking unit determines a direction in which the tracking target is located based on the moving trajectory. Then, a search area corresponding to the estimated direction is defined in each captured image, and the tracking target is searched in the search area.

  Thereby, the calculation load of the search process after the tracking target has moved out of the imaging region is reduced.

  According to the present invention, effective tracking is possible even when there are a plurality of tracking target candidates.

  Hereinafter, embodiments of the present invention will be specifically described with reference to the drawings. In each of the drawings to be referred to, the same part is denoted by the same reference numeral, and redundant description regarding the same part is omitted in principle.

  FIG. 1 is an overall block diagram of an imaging apparatus 1 according to an embodiment of the present invention. The imaging device 1 is a digital video camera that can capture moving images (and still images).

  The imaging device 1 includes an imaging unit 11, an AFE (Analog Front End) 12, a control unit 13, a face detection unit 14, a display unit 15, a recording medium 16, an operation unit 17, an inclination sensor 18, It has.

  The imaging unit 11 includes an optical system, an aperture, an imaging device such as a CCD (Charge Coupled Devices) or a CMOS (Complementary Metal Oxide Semiconductor) image sensor, and a driver (all not shown) for controlling the optical system and the aperture. And have. The driver controls the zoom magnification and focal length of the optical system and the aperture of the diaphragm based on a control signal from the control unit 13. The image sensor photoelectrically converts an optical image representing a subject incident through the optical system and the diaphragm, and outputs an electrical signal obtained by the photoelectric conversion to the AFE 12.

  The AFE 12 amplifies the analog signal output from the imaging unit 11 (imaging device), and converts the amplified analog signal into a digital signal. The AFE 12 sequentially outputs this digital signal to the control unit 13.

  The control unit 13 includes a CPU (Central Processing Unit), a ROM (Read Only Memory), a RAM (Random Access Memory), and the like, and also functions as a video signal processing unit. Based on the output signal of the AFE 12, the control unit 13 generates a video signal representing an image captured by the imaging unit 11 (hereinafter also referred to as “captured image”).

  The imaging unit 11 sequentially captures images in a predetermined frame cycle (for example, 1/60 second cycle), and a moving image is generated by still images (that is, captured images) sequentially obtained in a predetermined frame cycle. It is formed.

  The face detection unit 14 detects a person's face from each captured image, and extracts a face area including the face. Various methods are known as methods for detecting a face included in an image, and the face detection unit 14 can employ any method. For example, a face (face area) may be detected by extracting a skin color area from a photographed image as in the technique described in Japanese Patent Application Laid-Open No. 2000-105819, or Japanese Patent Application Laid-Open No. 2006-21139 and Japanese Patent Application Laid-Open No. 2006. A face (face area) may be detected using the technique described in Japanese Patent No. -72770 or the above-mentioned Patent Document 1.

  Typically, for example, the similarity between both images is determined by comparing the image of the region of interest set in the input image (that is, the captured image) with a reference face image having a predetermined image size. Based on this, it is detected whether or not a face is included in the region of interest (whether or not the region of interest is a face region). The similarity determination is performed by extracting a feature amount effective for identifying whether the face is a face. The feature amount is a horizontal edge, a vertical edge, a right diagonal edge, a left diagonal edge, or the like.

  In the input image, the region of interest is shifted in the horizontal direction or the vertical direction pixel by pixel. Then, the image of the region of interest after the shift is compared with the reference face image, the similarity between both images is determined again, and the same detection is performed. In this way, the region of interest is updated and set, for example, while being shifted pixel by pixel from the upper left to the lower right of the input image.

  Further, the input image (that is, the photographed image) is reduced at a certain rate, and the same face detection process is performed on the reduced image. By repeating such processing, a face of any size can be detected from the input image.

  Further, the face detection unit 14 is configured to be able to detect the inclination of the face in each captured image. For example, by rotating an input image (that is, a photographed image) and performing face detection processing similar to the above on the rotated image, a tilted face can be detected and the tilt (tilt angle) of the face can be detected. Can be detected. The face inclination in this case means the inclination of the face with respect to the vertical direction of the captured image (details will be described later).

  The face detection unit 14 further detects the orientation of the face in each captured image. That is, for example, the face detection unit 14 can detect whether a face detected in each captured image is a front face (face viewed from the front) or a side face (face viewed from the side). It is. Various methods have been proposed for detecting the orientation of the face, and the face detection unit 14 can employ any method.

  For example, as in the technique described in Japanese Patent Laid-Open No. 10-307923, face parts such as eyes, nose and mouth are found in order from a photographed image, and the position of the face in the image is detected. The face orientation is detected based on the projection data of the part.

  Alternatively, for example, a method described in JP 2006-72770 A may be used. In this method, one front face is divided into a left half (hereinafter referred to as a left face) and a right half (hereinafter referred to as a right face), and parameters related to the left face and right face are generated through a learning process. Keep it. At the time of face detection, the attention area in the captured image is divided into left and right, and the similarity between each divided area and the corresponding parameter of the two parameters is calculated. Then, when one or both of the similarities are equal to or greater than the threshold, it is determined that the attention area is a face area. Furthermore, the orientation of the face is detected from the magnitude relationship of the similarity to each divided region.

  The face detection result by the face detection unit 14 is transmitted to the control unit 13. The face detection result includes “face size, face position, face tilt, and face orientation” on each captured image.

  The display unit 15 is a display device composed of a liquid crystal display panel or the like, and displays an image taken in the current frame (or immediately preceding frame) or an image recorded on the recording medium 16 under the control of the control unit 13. indicate. The recording medium 16 is a non-volatile memory such as an SD (Secure Digital) memory card, and stores captured images and the like under the control of the control unit 13. The operation unit 17 includes a shutter button, a so-called cross key (both not shown), and the like, and accepts an operation from the outside. The operation content for the operation unit 17 is transmitted to the control unit 13.

  The tilt sensor 18 detects the tilt of the imaging device 1 with respect to the vertical line. For example, the state where the horizontal line on the captured image when the horizontal line is captured matches the horizontal direction (horizontal line) on the captured image is set as the reference state. In this reference state, the imaging apparatus 1 is not inclined (that is, the inclination is 0 degree), and the inclination sensor 18 detects the inclination of the imaging apparatus 1 from this reference state. The inclination data representing the inclination angle is transmitted to the control unit 13. Note that a horizontal line in the captured image may be detected by extracting an edge component from the captured image, and the inclination of the image capturing apparatus 1 may be detected from the detection result of the horizontal line.

  The imaging device 1 includes a tracking imaging function that performs imaging while tracking a tracking target as a characteristic function. The tracking imaging function is realized in a tracking imaging mode that is one of operation modes of the imaging apparatus 1. The transition from the other operation mode to the tracking shooting mode is realized by an operation on the operation unit 17.

  In the tracking shooting mode, shooting is sequentially performed in a predetermined frame period (for example, 1/60 second period), and each captured image sequentially obtained in the predetermined frame period is provided in the operation unit 17. It is recorded on the recording medium 16 in response to an operation on a recording button (not shown). The frames for obtaining each photographed image are visited in the order of the first, second,..., (N−1) th, nth frame,. (N is an integer of 2 or more). Hereinafter, the captured image in each frame is also referred to as a “frame image”. Frame image obtained in the first frame, frame image obtained in the second frame,..., Frame image obtained in the (n−1) th frame, in the nth frame The obtained frame images are arranged in time series.

  Hereinafter, the tracking shooting function will be described in detail. FIG. 2 is a functional block diagram of the tracking processing unit 20 for realizing the tracking imaging function. However, the tracking imaging function is not realized only by the tracking processing unit 20 shown in FIG. 2, and the functions of other parts shown in FIG. 1 are also used in realizing the tracking imaging function. The tracking processing unit 20 automatically tracks a tracking target candidate detecting unit 21 that detects a tracking target candidate to be automatically tracked, a tracking target selecting unit 22 that selects one tracking target from the tracking target candidates, and a tracking target. The tracking unit 23 is provided, and these are realized by the control unit 13. The tracking unit 23 includes a parameter setting unit 24 that sets parameters for tracking necessary for automatic tracking, and a movement locus storage unit 25 that stores a movement locus of a tracking target. The face detection result by the face detection unit 14 is transmitted to each part shown in FIG.

  FIG. 3 shows an operation flow in the tracking imaging mode. Operations in the tracking shooting mode are roughly classified into a tracking setting operation, a tracking operation, and a tracking object search operation.

  First, a tracking setting operation is performed in step S1, and the tracking operation in step S2 is executed after the tracking setting operation is completed. When the tracking target is out of frame during the tracking operation, the process proceeds to step S4 via the branching process of step S3, and the tracking target search operation is executed. If the tracking target is not out of frame, the tracking operation in step S2 is continued. Once the tracking target is out of the frame and then framed in again, when the tracking target is found by the tracking target search operation in step S4, the tracking operation in step S2 is performed again.

  In the case where attention is paid to the tracking target, the frame out means that the tracking target goes out of the shooting area from the shooting area. On the contrary, when the tracking target enters the imaging area from outside the imaging area is called frame-in. The imaging unit 11 captures a subject that falls within the imaging area.

  FIG. 4 illustrates a display area division example of the display screen of the display unit 15 in the tracking shooting mode. Reference numeral 50 represents a display screen of the display unit 15. More specifically, a solid square frame denoted by reference numeral 50 represents the entire display area on the display screen of the display unit 15. The entire display area is divided into an entire image display area AR1, a tracking target display area AR2, an additional information display area AR3, and other areas. The entire image display area AR1, the tracking target display area AR2, and the additional information display area AR3 are hereinafter abbreviated as a display area AR1, a display area AR2, and a display area AR3, respectively.

  The display area AR1 is a rectangular area, and the rectangular area is hatched in FIG. The display area AR2 is a rectangular area adjacent to the display area AR1. The display area AR3 is a donut-shaped region provided so as to surround the display area AR1.

  The control unit 13 in FIG. 1 or the tracking processing unit 20 in FIG. 2 also has a function as a display control unit that controls the display content of the display unit 15, and is an area for displaying an image on the display screen of the display unit 15. Control necessary for display, such as the definition of the image and the process of displaying an image in that area.

[Setting operation for tracking]
First, the tracking setting operation will be described. A period during which the tracking setting operation is executed is referred to as a tracking setting period. FIG. 5 shows a display example of the display screen 50 of the display unit 15 in the tracking setting period. In the tracking setting period, the entire image of each frame image that is sequentially generated is displayed as a moving image in the display area AR1. In addition, in FIG. 5 and each drawing described later showing an image including a person, illustration of the lower half of the person may be omitted for simplification of illustration. Further, the display area AR3 (see FIG. 4) is not used during the tracking setting period.

  The face detection unit 14 in FIG. 1 performs the above-described face detection on each frame image, and the tracking target detection unit 21 in FIG. 2 detects a tracking target candidate from each frame image based on the face detection result. To do. A person located in the shooting area is a tracking target candidate. Now, as shown in FIG. 5, it is assumed that three persons are located in the imaging region. In this case, face areas for three persons are specified by face detection, and the three persons become first, second, and third tracking target candidates.

  The tracking target selection unit 22 in FIG. 2 displays square frames 61, 62, and 63 surrounding the first, second, and third tracking target candidates in the display area AR1. When there are a plurality of tracking target candidates as in this example, one tracking target candidate is first enlarged and displayed in the display area AR2 in accordance with a predetermined rule. Here, “enlarged display in display area AR2” means that when a common image is displayed in display area AR1 and display area AR2, the display size of the image in display area AR2 is displayed in display area AR1. It means to be bigger than that.

  For example, first, an image in the square frame 61 surrounding the first tracking target candidate is enlarged and displayed in the display area AR2. In this state, when a predetermined target switching operation is performed on the operation unit 17, the image displayed in an enlarged manner in the display area AR2 is switched to an image in the square frame 62 surrounding the second tracking target candidate. Similarly, every time a predetermined target switching operation is performed, an image that is enlarged and displayed in the display area AR2 is an image within the rectangular frame 63 that surrounds the third tracking target candidate, and a square that surrounds the first tracking target candidate. The image in the frame 61 is switched to. The photographer performs the above-described target switching operation until the tracking target candidate enlarged and displayed in the display area AR2 matches the person to be tracked by the photographer.

  When a predetermined tracking target determination operation is performed on the operation unit 17 in a state where the image in the square frame 61 surrounding the first tracking target candidate is enlarged and displayed in the display area AR2, the tracking target selection in FIG. The unit 22 selects the first tracking target candidate as the tracking target. Similarly, when a predetermined tracking target determination operation is performed on the operation unit 17 in a state where the image in the square frame 62 surrounding the second tracking target candidate is enlarged and displayed in the display area AR2, FIG. The tracking target selection unit 22 selects the second tracking target candidate as a tracking target. The same applies to the third tracking target candidate.

  In addition, although the case where there are a plurality of tracking target candidates is illustrated, when there is only one person in the imaging region, the number of tracking target candidates detected is, of course, one.

  In addition, an example in which one tracking target is selected from a plurality of tracking target candidates by an operation on the operation unit 17 has been described. However, a tracking target is automatically selected from a plurality of tracking target candidates using a person specifying unit such as a face recognition process. You may make it select. Various methods are known as face recognition methods, and any of them can be used.

  A general face recognition method will be briefly described. In this method, a face of a person to be selected as a tracking target is photographed in advance and the face of the person is registered. Specifically, face dictionary data is created from the face image of the person. Then, each face area is cut out from the frame image in the tracking setting period, and pattern matching is performed between each of the cut out face area images and the face image represented by the face dictionary data. It is determined which face is a registered person's face. Based on the determination, a tracking target candidate corresponding to the registered person's face is selected as a tracking target.

  FIG. 6 shows a display example of the display screen 50 immediately after the tracking target is selected. A tracking target frame 64 surrounding the tracking target is displayed in the display area AR1, and an image in the tracking target frame 64, that is, an image including the tracking target is enlarged and displayed in the display area AR2. The display contents in the display area AR3 will be described later together with the description of the tracking operation and the tracking target search operation.

  Now, assume that the person (first tracking target candidate) displayed in the square frame 61 of FIG. 5 is selected as the tracking target. The person selected as the tracking target is hereinafter referred to as a tracking target person. In the following description, all the descriptions regarding the face or the human body such as the face, the orientation of the face, the inclination of the face, the upper body, and the lower body are descriptions regarding the tracking target person unless otherwise specified.

  When the tracking target is selected, the parameter setting unit 24 in FIG. 2 reads “the size of the face, the tilt of the face, and the orientation of the face” of the tracking target person detected by the face detection unit 14 on the captured image. Based on the inclination data from the inclination sensor 18, tracking parameters necessary for automatically tracking the tracking target are automatically set. In specifying the “face size, face inclination, and face orientation”, the position of the face on the captured image is also referred to. The contents of the set tracking parameters are reflected in the display area AR2. The automatically set tracking parameters can be changed by a parameter selection operation on the operation unit 17. Until the change is made, a tracking operation is performed using the tracking parameters before the change.

A method for automatically setting tracking parameters by the parameter setting unit 24 will be described. In the present embodiment, a case where there are eight types of tracking parameters is illustrated. For the sake of convenience, the eight types of tracking parameters are represented as tracking parameters PR ₁ , PR ₂ , PR ₃ , PR ₄ , PR ₅ , PR ₆ , PR ₇ and PR ₈ in order to distinguish between different types of tracking parameters. To distinguish.

First, an explanation will be given focusing on the tracking parameter PR ₁ . The tracking parameter PR ₁ corresponds to “a state in which the person to be tracked stands upright with respect to the imaging apparatus 1 without tilting his / her face and the imaging apparatus 1 is not tilted”. It is assumed that the person to be tracked is located on the ground parallel to the horizontal line.

7 (a) is, in the case where the tracking parameter PR ₁ is set as a tracking parameter, representing a display image of the display area AR2. FIG. 7B is a diagram illustrating region setting corresponding to the tracking parameter PR ₁ .

  Now, the width of the face and the height of the face on the captured image of the person to be tracked are represented by Wf and Hf, respectively. The face width Wf is, for example, the distance between both ends of the left and right cheeks, and the face height Hf is, for example, the distance from the lower end of the jaw of the face to the upper end of the eyebrows. The face width Wf and the face height Hf are calculated from the face detection result of the face detection unit 14.

The width direction of the face and the height direction of the face are orthogonal to each other, and a rectangular area represented by “Wf × Hf” is defined as the face area. An XY coordinate system in which the width direction of the face is taken as the X axis and the height direction of the face is taken as the Y axis is defined in the photographed image, and one corner of the rectangular area as the face area is defined as the origin of the XY coordinate system. Think of it as O. The X-axis direction in the tracking parameter PR ₁ matches the horizontal direction of the captured image. In this case, in the XY coordinate system, the face area of the tracking target person is a rectangular area surrounded by four points (0, 0), (Wf, 0), (0, −Hf), and (Wf, −Hf). It becomes. In FIG. 7B, reference numeral 71 represents the face area of the person to be tracked.

Then, an upper face area which is a rectangular area is defined in the positive direction of the Y axis adjacent to the face area. In FIG. 7B, the upper side of the drawing coincides with the positive direction of the Y axis. In FIG. 7B, reference numeral 72 represents an upper face area of the person to be tracked. The width and height of the rectangular area as the upper face area are represented by α ₁ · Wf and α ₂ · Hf, respectively. α ₁ and α ₂ are predetermined constants. In addition, the upper side of the rectangular area as the face area (parallel to the X axis direction and the positive side of the Y axis) and the lower side of the rectangular area as the upper face area (parallel to the X axis direction and Y axis) The negative side of) matches.

In addition, an upper body region that is a rectangular region is defined in the negative direction of the Y axis adjacent to the face region. In FIG. 7B, reference numeral 73 represents the upper body area of the person to be tracked. The width and height of the rectangular area as the upper body area are represented by β ₁ · Wf and β ₂ · Hf, respectively. β ₁ and β ₂ are predetermined constants. The lower side of the rectangular area as the face area matches the upper side of the rectangular area as the upper body area.

Further, a lower body region that is a rectangular region is defined adjacent to the upper body region in the negative direction of the Y axis. In FIG. 7B, reference numeral 74 represents a lower body area of the person to be tracked. The width and height of the rectangular region as the lower body region are represented by γ ₁ · Wf and γ ₂ · Hf, respectively. γ ₁ and γ ₂ are predetermined constants. The lower side of the rectangular area as the upper body area matches the upper side of the rectangular area as the lower body area.

  Further, the centers of the face area 71, the upper face area 72, the upper body area 73, and the lower body area 74 are on a straight line 75 parallel to the Y axis, as shown in FIG.

When the tracking parameter PR ₁ is applied, as shown in FIG. 7A, the tracking target person is enlarged and displayed in the display area AR2, and the face area 71, the upper face area 72, the upper body area 73, and the lower body area 74 are displayed. Are displayed, and four tracking reference marks M1 to M4 are further displayed. The tracking reference mark M1 is arranged in the approximate center of the face area 71, the tracking reference mark M2 is arranged in the approximate center of the upper face area 72, and the tracking reference mark M3 is arranged in the approximate center of the upper body area 73. The tracking reference mark M4 is disposed from above the center of the lower body region 74.

  In FIG. 6 and some of the drawings described later (FIG. 18, etc.), the lower body and lower body region of the person to be tracked and the tracking reference mark corresponding thereto are not shown. Further, whether or not to display the outer shapes of the face area, the upper face area, the upper body area, and the lower body area as shown in FIG. 7A is arbitrary in the display area AR2. FIG. 6 and some drawings described later (FIG. 18 and the like) exemplify a case where these external shapes are not displayed.

Parameter setting unit 24, the inclination of the orientation and the face of the face of the tracking target person, and, depending on the inclination of the imaging apparatus 1, automatically one track among the eight tracking parameters PR ₁ to PR ₈ Select the parameters. When the orientation of the face with respect to the imaging device 1 is the front, the face is not tilted, and the imaging device 1 is not tilted, the eight types of tracking parameters PR _{1 to} PR ₈ are automatically selected. The tracking parameter PR ₁ is selected, and the region setting as described above is performed. When the face orientation with respect to the imaging device 1 is the front, the face appears as a front face on the captured image, and when the face orientation with respect to the imaging device 1 is the landscape orientation, the face appears as a profile on the captured image.

When the face is tilted, different types of tracking parameters are selected and set. FIG. 9 shows the characteristics of the eight types of tracking parameters PR _{1 to} PR ₈ as a table. In FIG. 9, the tilt of the imaging device 1 is expressed as camera tilt.

A orientation front of the face with respect to the imaging apparatus 1, and is inclined face, and, when the imaging apparatus 1 is not inclined, automatically tracking parameters PR ₂ is selected.
A orientation front of the face with respect to the imaging apparatus 1, and is inclined face, and, when even the imaging device 1 is inclined in the same direction, automatically tracking parameter PR ₃ is selected.
When the orientation of the face with respect to the imaging device 1 is horizontal, the face is not tilted, and the imaging device 1 is not tilted, the tracking parameter PR ₄ is automatically selected.
When the orientation of the face with respect to the imaging device 1 is landscape, the face is tilted, and the imaging device 1 is not tilted, the tracking parameter PR ₅ is automatically selected.
When the orientation of the face with respect to the imaging device 1 is horizontal, the face is tilted, and the imaging device 1 is also tilted in the same direction, the tracking parameter PR ₆ is automatically selected.

  Here, the tilt of the face means the tilt of the face with respect to the vertical direction of the captured image. Therefore, when the width direction of the face matches the horizontal direction of the captured image, the face is not inclined, and when the width direction of the face does not match the horizontal direction of the captured image, the face is inclined.

The tracking parameter PR ₇ or PR ₈ is not automatically selected but can be selected by a parameter selection operation on the operation unit 17.
The tracking parameter PR ₇ is suitable when the face is in front and the face is not inclined with respect to the vertical direction of the photographed image, but the face is inclined with respect to the upper body.
The tracking parameter PR ₈ is suitable when the person to be tracked is sitting sideways with the legs extended with respect to the imaging apparatus 1.

The tracking parameter PR ₇ can be said to be suitable when the orientation of the face with respect to the imaging apparatus 1 is the front, the face is not tilted, and the imaging apparatus 1 is tilted. The tracking parameter PR ₇ may be automatically selected.

FIGS. 10 (a), 11 (a), 12 (a), 13 (a), 14 (a), 15 (a), and 16 (a) are tracked as tracking parameters, respectively. in the case of use parameter _{PR 2, PR 3, PR 4} , PR 5, PR 6, PR 7 and PR ₈ are set, representing a display image of the display area AR2. FIG. 10 (b), the FIG. 11 (b), the FIG. 12 (b), the FIG. 13 (b), the FIG. 14 (b), the FIG. 15 (b) and FIG. 16 (b), respectively, tracking parameters PR ₂ , PR ₃ , PR ₄ , PR ₅ , PR ₆ , PR _7, and PR ₈ are diagrams representing region settings.

Each shape of the face region, the upper face region, the upper body region, and the lower body region is common among the tracking parameters PR _{1 to} PR ₈ . The tracking parameters PR _{1 to} PR ₈ are also common in that the outlines of the face area, the upper face area, the upper body area, the lower body area, and the tracking reference marks corresponding thereto are displayed in the display area AR2. . However, the tracking parameters PR _{2 to} PR ₈ are different from the tracking parameter PR ₁ mainly in the following points (unless otherwise described, they are basically the same as the tracking parameter PR ₁ ).

In FIG. 10 (a) and (b) corresponding to the tracking parameters PR _2, in accordance with the inclination angle of the face, upper body region and the lower body region is inclined with respect to the face region. As a result, the straight line connecting the centers of the upper face region and the face region and the straight line connecting the centers of the upper body region and the lower body region do not match and are not parallel.

Further, the display position of each tracking reference mark in the display area AR2 is determined according to the positional relationship between the face area, the upper face area, the upper body area, and the lower body area. For this reason, the display position of each tracking reference mark in the tracking parameter PR ₁ is different from that in the tracking parameter PR ₂ (see FIG. 7A and FIG. 10A). The same applies to other tracking parameters.

In the tracking parameter PR ₃ corresponding to FIGS. 11A and 11B, the X axis and the Y axis defined in the captured image are tilted according to the tilt angle of the imaging apparatus 1. As a result, the X-axis direction is not parallel to the horizontal direction of the captured image.

In the tracking parameters PR _{4 to} PR ₆ and PR ₈ corresponding to the side face, the definition of the face width is different, and the face width is generally the distance from the apex of the nose to the back of the head. In addition, the values of the constants α ₁ , α ₂ , β ₁ , β ₂ , γ _1, and γ _{2 in} the tracking parameters PR _{4 to} PR ₆ and PR ₈ corresponding to the side face are set as the tracking parameter PR ₁ corresponding to the front face. It may be different from those in etc.

In the tracking parameter PR ₅ corresponding to FIGS. 13A and 13B, the upper body region and the lower body region are tilted with respect to the face region in accordance with the tilt angle of the face (face depression angle).

In the tracking parameter PR ₆ corresponding to FIGS. 14A and 14B, the X axis and the Y axis defined in the captured image are tilted according to the tilt angle of the imaging apparatus 1.

In the tracking parameter PR ₇ corresponding to FIGS. 15A and 15B, the upper body region and the lower body region are tilted with respect to the face region according to the tilt angle of the face with respect to the upper body.

In the tracking parameter PR ₈ corresponding to FIGS. 16A and 16B, the lower body region is inclined 90 degrees with respect to the upper body region.

  As described above, the parameter setting unit 24 uses the face area extracted by the face detection unit 14 based on the size and position of the face of the person to be tracked on the captured image as a reference, the upper face area, the upper body area, and the lower body area. Set the area. These settings are part of the tracking parameters. The tracking area to be tracked by the tracking operation is a combination of the set face area, upper face area, upper body area, and lower body area.

  Further, as described above, the tracking area (in particular, the upper body area and the lower body area included in the tracking area) depends not only on the size and position of the face, but also on the face inclination, the face direction, and the inclination of the imaging device 1. Is set. As a result, ideally, the upper body and lower body (and upper face) on the photographed image are accommodated in the set upper body area and lower body area (and the upper face area), respectively. Stable tracking is realized.

  Although eight types of tracking parameters are illustrated, it is possible to subdivide the tracking parameters in more detail according to “face inclination, face orientation, and imaging apparatus 1 inclination”. In this case, there are nine or more types of tracking parameters. However, the number of tracking parameters can be seven or less. In addition, it is desirable to set the tracking area by referring to all of “face inclination, face orientation, and imaging apparatus 1 inclination”, but for the purpose of simplifying the processing, a part or all of them are referred to. Can be omitted.

When the photographer determines that the tracking parameter automatically set by the parameter setting unit 24 is not appropriate, the tracking parameter can be changed by the parameter selection operation on the operation unit 17 as described above. For example, the tracking parameter PR ₃ is automatically selected even though the face direction with respect to the imaging device 1 is the front, the face is not tilted, and the imaging device 1 is not tilted. When the display as shown in (a) is made, the photographer may perform a parameter selection operation. As a result, information corresponding to other tracking parameters (such as the outer shape of the upper body region and the tracking reference mark) is displayed in the display area AR2. This operation is repeated, and when information corresponding to an appropriate tracking parameter (in this case, PR ₁ ) is displayed, the photographer performs a predetermined selection determination operation on the operation unit 17. Thereafter, a tracking operation is performed according to the tracking parameters at the time when the selection determination operation is performed.

[Tracking operation]
Next, the tracking operation is set. When the tracking parameter automatically set by the parameter setting unit 24 is not changed, the tracking operation according to the tracking parameter is started from the time when the tracking parameter is set. When the selection determination operation is performed through the change of the tracking parameter by the parameter selection operation, the tracking operation according to the changed tracking parameter is started from the time when the selection determination operation is performed.

  In the tracking operation, a tracking area (an image in the tracking area) determined by the tracking parameters is tracked. More specifically, the tracking unit 23 regards each of the four regions (upper face region, face region, upper body region, and lower body region) forming the tracking region as a tracking block, and the tracking block (tracking) for each tracking block. Track the image in the block). Note that a part of the upper face area, a part of the face area, a part of the upper body area, and a part of the lower body area may each be regarded as a tracking block.

  Various methods are known or known as a method for tracking one tracking block, and the tracking unit 23 can employ any of these methods. A general method will be briefly described with reference to FIG. This method is a kind of image matching method and is also called a block matching method.

  In FIG. 17A, reference numeral 100 represents an (n−1) th frame image, and reference numeral 101 represents a tracking block of interest in the (n−1) th frame image. In FIG. 17B, reference numeral 110 represents an nth frame image, reference numeral 111 represents a candidate block of interest in the nth frame image, and reference numeral 112 represents a search block in which the candidate block 111 can be located. The (n-1) th frame image and the nth frame image are a frame image obtained by photographing the (n-1) th frame and a frame obtained by photographing the nth frame, respectively. Refers to the image.

  The tracking unit 23 calculates a correlation value between the tracking block 101 and the candidate block 111. At this time, the candidate block 111 is moved one pixel at a time in the horizontal direction or the vertical direction in the search block 112, and a correlation value is calculated for each movement. The correlation value is, for example, the sum of absolute values of the luminance differences between the pixels between the tracking block 101 and the candidate block 111. This correlation value is generally called SAD (Sum of Absolute Difference). Of course, the correlation value may be obtained from the sum of squares of luminance difference (Sum of Squared Differece) or the like.

  The correlation value decreases as the correlation between the image of the tracking block 101 and the image of the candidate block 111 increases. Accordingly, if the position of the candidate block 111 having the smallest correlation value is obtained, it can be determined where the tracking block 101 is located in the nth frame image, and the (n−1) th and nth frames are obtained. A motion vector of the tracking block 101 between images is obtained. By repeatedly obtaining a motion vector between adjacent frames and sequentially moving the tracking block according to the motion vector, it is possible to track a moving object that falls within the tracking block.

  By the way, as described above, the tracking unit 23 regards each of the four regions (upper face region, face region, upper body region, and lower body region) forming the tracking region as a tracking block. For this reason, the correlation value calculation for tracking a tracking block is performed for every tracking block. Then, the effectiveness of each tracking block is determined based on the result of the correlation value calculation. For example, when a bird crosses the face of a person to be tracked in a certain period, the minimum correlation value calculated with the face area as a tracking block during that period takes a relatively large value (or the correlation value distribution is Abnormal). In such a case, the tracking block for the face area is invalidated, and the position of the face area is estimated from the motion vectors calculated for other effective tracking blocks, so that the tracking of the entire tracking area is continued. By processing in this way, stable tracking is possible even in a situation where a part of the tracking target person is temporarily blocked by another object.

  FIG. 18 shows the display content of the display screen 50 during the tracking operation. During the tracking operation, the entire image of each frame image generated sequentially is displayed as a moving image in the display area AR1. The tracking target frame 64 displayed so as to surround the tracking target in the display area AR1 moves in the display area AR1 following the movement of the tracking target in the image. During the tracking operation, an image including the tracking target, that is, an image including the tracking area is enlarged and displayed in the display area AR2.

  As described above, the tracking unit 23 in FIG. 2 tracks the tracking target by sequentially tracking where the tracking region is located in each frame image. Therefore, by continuously connecting a predetermined position of the tracking target (for example, the tracking reference mark (M3 in FIG. 7A) of the upper body region), the movement trajectory of the tracking target during the tracking operation is determined. The movement trajectory is sequentially updated and stored in the movement trajectory storage unit 25 of FIG. The direction of the arrow 65 displayed in the display area AR1 in FIG. 18 represents the direction of movement of the tracking target in the last several to several tens of frames based on this movement trajectory. By referring to this arrow 65 as well, the photographer performs a panning operation or the like, thereby preventing the tracking target person from being out of frame.

  The display area AR3 is divided into eight tracking support display areas 121 to 128, and the eight tracking support display areas 121 to 128 are respectively above, below, left, right, diagonally left above, and left of the display area AR2. It is arranged diagonally below, diagonally right above and diagonally below right. In principle, all the images in the eight tracking support display areas 121 to 128 are solid images of the reference color.

  When the tracking target is about to be out of frame during the tracking operation, the tracking unit 23 performs warning notification. Specifically, as shown in FIG. 19, the tracking unit 23 defines a predetermined frame warning area 132 in each frame image 131, and issues a warning notification when a part of the tracking area overlaps the frame warning area 132. To implement. The warning notification is performed by video output by the display unit 15 or audio output by an audio output unit (not shown). Give the photographer visual or auditory alerts. This prevents the tracking target from being out of the frame and reduces the burden on the photographer necessary to prevent the out of frame. In FIG. 19, a frame warning area 132 corresponds to a square-shaped hatched area, which is provided in the periphery of the frame image 131.

  FIG. 20 shows a display example of the display screen 50 during warning notification. As examples of warning notifications, first to fourth warning notifications are shown below. The tracking unit 23 performs part or all of the first to fourth warning notifications as warning notifications. Needless to say, these notification methods can be variously modified.

In the first warning notification, the display content in any of the tracking support display areas is changed according to the position of the tracking target on the image and the direction of movement. For example, when the tracking target is moving toward the left side of the captured image and is about to be out of the frame in the left direction of the captured image, as shown in FIG. 20, the tracking support display area 123 located to the left of the display area AR2 is displayed. The display color is made different from the reference color.
In the second warning notification, the direction in which the imaging apparatus 1 should be panned or tilted is displayed on the display screen 50 in accordance with the position of the tracking target on the image and the direction of movement. For example, when the tracking target is moving toward the left side of the captured image and the frame is about to be left out of the captured image, a left-pointing arrow 141 is displayed on the display screen 50 as shown in FIG.
In the third warning notification, the display color of the tracking target frame 64 is changed in comparison with before the warning notification is performed.
In the fourth warning notification, a predetermined warning sound is output from a sound output unit (not shown) provided in the imaging apparatus 1.

[Tracking target search operation]
When the tracking target tracked in the tracking operation is out of frame, the tracking target search operation is executed.

  In the tracking target search operation, the tracking unit 23 estimates the direction in which the tracking target is located with reference to the tracking track of the tracking target stored in the moving track storage unit 25 of FIG. 2, and according to the estimation result, Re-frame-in support notification (hereinafter simply referred to as “support notification”) is performed to inform the photographer of the direction. Thus, the second frame-in is supported, and the photographer can easily readjust the composition. Support notification is performed by video output by the display unit 15 or audio output by an audio output unit (not shown), similar to the warning notification.

  For example, when the tracking target moves toward the left side of the photographed image and frames out to the left of the photographed image, the tracking unit 23 determines that the tracking target is the left of the imaging device 1 based on the movement trajectory representing the content. It is assumed that it is located in the direction, and the support notification indicating the left direction is performed.

  Each of FIGS. 21 and 22 shows a display example of the display screen 50 during execution of the tracking target search operation. As examples of support notification, first to third support notifications are shown below. The tracking unit 23 performs part or all of the first to third support notifications as support notifications. Needless to say, these notification methods can be variously modified.

In the first support notification, the display content in one of the tracking support display areas is changed according to the estimated direction of the position of the tracking target. For example, when it is estimated that the tracking target is located in the left direction of the imaging apparatus 1, as shown in FIG. 21, the display color of the tracking support display area 123 located to the left of the display area AR2 is made different from the reference color.
In the second support notification, a direction in which the imaging device 1 should be panned or tilted to frame in the tracking target again is displayed on the display screen 50 in accordance with the estimated direction of the position of the tracking target. This direction coincides with the estimated direction of the position of the tracking target. For example, when it is estimated that the tracking target is located in the left direction of the imaging apparatus 1, a left-pointing arrow 142 is displayed on the display screen 50 as shown in FIG. 21, or in the tracking support display area 123 as shown in FIG. A leftward arrow 151 is displayed.
In the third support notification, a sound for transmitting the estimated direction of the position of the tracking target is output from a sound output unit (not shown) provided in the imaging device 1.

  In addition, in the display area AR2 of the display screen 50 shown in FIG. 21 or FIG. 22, an enlarged image of the tracking target tracked during the tracking operation is displayed as a still image. However, this display may not be performed.

  Further, in a period during which the tracking target search operation is performed (hereinafter referred to as a search period), the tracking unit 23 performs image matching between each frame image and the image of the tracking area stored during the tracking operation, thereby each frame image. Search for a tracking target that can be included again. At this time, a motion region in each frame image may be specified by calculating a motion vector, and a search may be executed only within the motion region.

  For each frame image in the search period, a search area corresponding to the estimated direction of the position of the tracking target is defined, and only the search area is searched (or the search area is searched intensively). You may do it. This reduces the amount of calculation processing required for the search.

  This will be described more specifically with reference to FIG. In FIG. 23, reference numeral 161 represents each frame image in the search period, and a rectangular area denoted by reference numeral 162 represents a search area defined in each frame image. The search area 162 is smaller than the entire area of the frame image 163 and is provided at a position corresponding to the estimated direction of the position of the tracking target. For example, when it is estimated that the tracking target is located in the left direction of the imaging apparatus 1, the tracking target is highly likely to be framed in again from the left side of the frame image due to a pan operation on the imaging apparatus 1 or the like. Therefore, in this case, as shown in FIG. 23, the search area 162 is provided on the left side of the frame image.

  In the search period, the tracking unit 23 performs image matching between the image in the search area of each frame image and the image of the tracking area stored during the tracking operation. That is, it is searched by image matching whether there is a tracking target in the search area (not searched outside the search area). As an image matching method, a method similar to the method described with reference to FIG. 17 may be used, and it is determined whether or not a tracking target exists in the search region based on the correlation value calculated by the correlation calculation. At the same time, when the tracking target exists, the position of the tracking target in the frame image is specified based on the correlation value. After the position of the tracking target is specified, the above tracking operation is resumed.

<< Deformation, etc. >>
As modifications or annotations of the above-described embodiment, notes 1 to 5 are described below. The contents described in each comment can be arbitrarily combined as long as there is no contradiction.

[Note 1]
When tracking the tracking target, each of the four areas (the upper face area, the face area, the upper body area, and the lower body area) forming the tracking area is regarded as a tracking block, and a tracking block (an image in the tracking block) is detected for each tracking block. In this case, the tracking process may be executed with reference to image data outside the tracking block in order to improve tracking accuracy. For example, two tracking reference areas are provided so as to sandwich the face area in the vicinity of the face area, and tracking is performed with reference to image data of these tracking reference areas. The positional relationship between the tracking area and the tracking reference area can change according to the inclination of the face.

[Note 2]
The tracking target frame 64 shown in FIG. 6 and the like is displayed as a tracking mark representing the tracking target, and the shape and display method can be variously changed. For example, an arrow or the like may be displayed as a tracking mark in the vicinity of the tracking target display position in the display area AR1. In short, what is necessary is just to display the tracking mark from a predetermined position in the display area AR1 based on the display position of the tracking target so that the tracking target is visually recognized separately from other subjects. Further, the display of the tracking mark (tracking target frame 64) can be erased by a predetermined operation on the operation unit 17.

[Note 3]
In the above-described embodiment, the entire human body of the tracking target person may be included in the tracking area, but it is not necessary that the entire human body of the tracking target person is included in the tracking area. That is, the tracking area includes all or part of the tracking target person.

[Note 4]
Although the tracking area is described as being formed of four areas (ie, the upper face area, the face area, the upper body area, and the lower body area), one or more of the four areas can be omitted from the tracking area. . For example, the lower body area may be omitted, and the tracking area may be formed by the upper face area, the face area, and the upper body area.

[Note 5]
In addition, the imaging apparatus 1 in FIG. 1 can be realized by hardware or a combination of hardware and software. In particular, the functions realized by the face detection unit 14 in FIG. 1 and the tracking processing unit 20 in FIG. 2 can be realized by hardware, software, or a combination of hardware and software.

  When the imaging apparatus 1 is configured using software, a block diagram of a part realized by software represents a functional block diagram of the part. Also, all or part of the functions realized by the face detection unit 14 in FIG. 1 and the tracking processing unit 20 in FIG. 2 are described as a program, and the program is executed on a program execution device (for example, a computer). May implement all or part of the functions.

1 is an overall block diagram of an imaging apparatus according to an embodiment of the present invention. It is a functional block diagram of the tracking process part for implement | achieving the tracking imaging | photography function which concerns on embodiment of this invention. It is a flowchart which shows the flow of operation | movement in the tracking imaging | photography mode in which the tracking process part of FIG. 2 functions effectively. It is a figure which shows the example of a display area division of the display screen of the display part of FIG. 1 in tracking imaging | photography mode. It is a figure which shows the example of a display screen displayed in the setting period for tracking. It is a figure which shows the example of a display of a display screen immediately after a tracking object is selected. Is a diagram for explaining the tracking parameters set by the parameter setting unit of FIG. 2 (PR _1). Is a diagram for explaining the tracking parameters set by the parameter setting unit of FIG. 2 (PR _1). It is a figure for demonstrating the kind of parameter for tracking set by the parameter setting part of FIG. It is a diagram for explaining the tracking parameters (PR ₂₎ set by the parameter setting unit of FIG. It is a diagram for explaining the tracking parameters (PR ₃₎ set by the parameter setting unit of FIG. Is a diagram for explaining the tracking parameters set by the parameter setting unit of FIG. 2 (PR _4). It is a diagram for explaining the tracking parameters (PR ₅₎ set by the parameter setting unit of FIG. It is a diagram for explaining the tracking parameters (PR ₆₎ set by the parameter setting unit of FIG. It is a diagram for explaining the tracking parameters (PR ₇₎ which is set by the parameter setting unit of FIG. It is a diagram for explaining the tracking parameters (PR ₈₎ set by the parameter setting unit of FIG. It is a figure for demonstrating the image tracking method by the tracking part of FIG. It is a figure which shows the example of a display of a display screen during tracking operation | movement. It is a figure which shows the frame warning area | region defined in each frame image. It is a figure which shows the example of a display of a display screen in the middle of implementing warning alerting | reporting. It is a figure which shows the example of a display screen during execution of tracking object search operation | movement. It is a figure which shows the example of a display screen during execution of tracking object search operation | movement. It is a figure which shows the search area | region defined in each frame image during execution of tracking object search operation | movement.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Imaging device 11 Imaging part 12 AFE
DESCRIPTION OF SYMBOLS 13 Control part 14 Face detection part 15 Display part 16 Recording medium 17 Operation part 18 Inclination sensor 20 Tracking process part 21 Tracking object candidate detection part 22 Tracking object selection part 23 Tracking part 24 Parameter setting part 25 Moving trace memory | storage part

Claims (8)

Imaging means for obtaining captured images arranged in time series by sequentially capturing;
Display means capable of displaying the captured image;
Face detection means for detecting a human face from the captured image;
Based on the detection result of the face detection means, tracking target candidate detection means for detecting one or more persons as tracking target candidates from the captured image;
A tracking target selection means for selecting one of the tracking target candidates as a tracking target person when two or more tracking target candidates are detected;
Tracking means for tracking the tracking target person between the captured images arranged in time series after the selection of the tracking target person,
The face detection means extracts an area including the face of the person to be tracked as a face area,
The tracking means sets an area including a part or all of the tracking target person as a tracking area,
The tracking region is formed of first, second,..., And nth (n is an integer of 2 or more) element tracking regions,
The tracking unit sets a first element tracking area as the face area, and sets the face area as the first element tracking area based on the size and position of the face area on the captured image. An imaging apparatus with a tracking function , wherein other element tracking areas are set as a reference, and the tracking target person is tracked by individually tracking these element tracking areas . The display means provides a whole image display area on the display screen, displays the whole image of the captured images arranged in time series in the whole image display area as a moving image, and separately tracks on the display screen. 2. The imaging device with a tracking function according to claim 1, wherein a target display area is provided, and an image including the tracking target is enlarged and displayed in the tracking target display area. The display means displays a predetermined tracking mark at a predetermined position on the basis of the display position of the tracking target in the entire image display area.
The imaging device with a tracking function according to claim 2. The tracking means includes not only the size and position, but also the inclination of the face of the tracking target person in the captured image, the orientation of the face of the tracking target person in the captured image, and the inclination of the imaging device, The tracking area is set with reference to at least one of
The imaging device with a tracking function according to any one of claims 1 to 3. The tracking unit automatically sets a tracking parameter necessary for tracking after selecting the tracking target, and causes the display unit to display information according to the set tracking parameter,
The imaging apparatus further includes an operation unit that receives an operation from the outside,
The tracking parameter automatically set by the tracking unit can be changed by a predetermined operation on the operation unit,
When the change is made by the predetermined operation, the tracking unit tracks the tracking target according to the changed tracking parameter.
The imaging device with a tracking function according to claim 1, wherein the imaging device has a tracking function. The tracking unit automatically sets a tracking parameter necessary for tracking after selecting the tracking target, and causes the display unit to display information according to the set tracking parameter,
The tracking parameter includes information defining the tracking area,
The imaging apparatus further includes an operation unit that receives an operation from the outside,
The tracking parameter automatically set by the tracking unit can be changed by a predetermined operation on the operation unit,
When the change is made by the predetermined operation, the tracking unit tracks the tracking target according to the changed tracking parameter.
The imaging device with a tracking function according to claim 1, wherein the imaging device has a tracking function. The tracking unit obtains and stores a movement trajectory of the tracking target from each captured image, and estimates the direction in which the tracking target is located based on the moving trajectory when the tracking target goes out of the imaging region. , Notification according to the estimated direction
The imaging device with a tracking function according to claim 1, wherein the imaging device has a tracking function. The tracking means obtains and stores a movement trajectory of the tracking target from each captured image, and when the tracking target goes out of the imaging area, estimates a direction in which the tracking target is located based on the moving trajectory, Thereafter, a search area corresponding to the estimated direction is defined in each captured image, and the tracking target is searched in the search area.
The imaging apparatus with a tracking function according to claim 1, wherein the imaging apparatus has a tracking function.

Images