JP2019201387A - Tracking controller - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a tracking control device capable of easily and continuously tracking a subject without switching a tracking target. SOLUTION: In a frame image, a CPU configures at least one of a face portion 62, which is a characteristic portion that constitutes a part of a subject and characterizes the subject, and a head portion 61, which is a peripheral portion located around the characteristic portion. What is possessed is set as a tracking target. The frame 30a encloses the face portion 62 and the head portion 61 together as one tracking target. The dictionary data is updated by adding the feature amount of the subject to the dictionary data. [Selection diagram] Fig. 6

Description

  The present invention relates to a tracking control device.

  Some imaging devices such as electronic cameras have a so-called tracking function for automatically tracking and photographing a moving subject. Patent Document 1 is known as a technique related to such a tracking function.

  Specifically, Patent Document 1 discloses a tracking control device including a face tracking unit that tracks a face part of a subject and a peripheral part tracking unit that tracks a peripheral part of the face part of the subject such as a chest. Yes. This tracking control device tracks the subject with the face tracking unit, and switches to track the subject with the peripheral part tracking unit when the face cannot be tracked.

JP 2013-12941 A

  In Patent Document 1, when the face portion cannot be tracked, a relatively high-load process such as a tracking target switching process is required.

  Therefore, an object of the present invention is to enable easy and continuous tracking of a subject without switching the tracking target.

  According to a first aspect of the present invention, an acquisition unit that acquires a plurality of continuous frame images including a specific subject from an imaging unit of an imaging device, and tracking control so that the tracking unit including the subject is tracked by the imaging unit. A tracking control unit comprising: a tracking control unit configured to perform a tracking control unit, wherein the tracking control unit forms a part of the subject and characterizes the subject in the frame image; and a periphery located around the feature unit A tracking control device is characterized in that a device having at least one of the units is set as the tracking target.

  According to the first invention, for example, even when the feature portion cannot be detected, the subject can be tracked if the peripheral portion is detected on the frame image. For this reason, the subject can be tracked continuously. In addition, since the feature portion and the peripheral portion can be combined into one tracking target, the subject can be easily tracked without switching the tracking target.

  In a second aspect based on the first aspect, the characteristic portion is a face portion of the subject, and the peripheral portion is a head portion of the subject, and head color information indicating a color of the head is provided. A head color information detecting unit for detecting, the first frame image included in the plurality of frame images has a first face range in which the face is located, and the head color information detecting unit includes: When color information similar to the color of the head is detected from within a second face range corresponding to the first face range included in a second frame image after the first frame image, the tracking control is performed. The tracking control device is characterized in that it determines that the face part is within the second face part range.

  According to the second invention, even when the face portion of the subject cannot be recognized, the subject can be tracked based on the color of the hair, the hat, or the like. For example, the orientation of the face portion of the subject may change, making it impossible to detect the face portion, and the color of the subject's head may be detected within the range in which the face portion has been located. Even in this case, even if the face portion itself cannot be recognized, it is determined that there is a face portion, so that the subject can be tracked continuously.

  According to a third invention, in the second invention, a face part detection unit that detects the face part from the frame image, and the frame image that is located above the face part and has similar color information predetermined. A tracking control device further comprising: a head detecting unit that detects the head having an area equal to or larger than the area.

  According to the third invention, the accuracy of detecting the head can be improved.

  According to a fourth aspect of the present invention, in the second or third aspect of the present invention, the display control unit further displays a frame image on the display unit of the imaging device, and the display control unit is configured to 1 for one subject. One frame is displayed on the display unit, and the frame collectively surrounds the face and the head as one tracking target.

  According to the fourth aspect of the present invention, it is possible to suppress the difficulty in seeing the frame image captured due to an increase in the number of frames displayed on the display unit.

  According to a fifth aspect, in the first aspect, the frame image includes a peripheral color information detection unit that detects peripheral color information indicating a color of the peripheral portion, and the tracking control unit is similar to the peripheral color information. It is a tracking control device characterized in that it is determined that the peripheral portion has the color information of at least a predetermined area.

  According to the fifth aspect, it is possible to improve the accuracy of detecting the peripheral portion.

  In a sixth aspect based on the fifth aspect, the feature portion is the face portion of the subject, and the peripheral portion is the torso portion of the subject, and the face portion detection detects the face portion from the frame image. And a torso detecting unit for detecting the torso from the frame image, wherein the torso detecting unit determines that the part below the face is the torso. Is a tracking control device.

  According to the sixth aspect, even when the face portion of the subject cannot be recognized, the subject can be tracked based on the color of clothes or the like on the torso.

  A seventh invention further includes a display control unit that displays the frame image on the display unit of the imaging device according to the fifth or sixth invention, and the display control unit includes a first frame surrounding the feature unit. And a second frame that surrounds the characteristic portion and the peripheral portion as a single tracking target on the display portion.

  According to the seventh aspect, it becomes easy to confirm the entire tracking target and the face in the display unit.

  According to the present invention, it is possible to easily and continuously track a subject without requiring a relatively high load process such as a tracking target switching process.

FIG. 1 is a block diagram schematically illustrating the configuration of an imaging apparatus including an image processing apparatus that is a tracking control apparatus. FIG. 2 is an illustrative view showing an example of blocks formed in an image. FIG. 3 is an explanatory diagram of the concept of dictionary data. FIG. 4 is an explanatory diagram of the concept of evaluation value data. FIG. 5 is a diagram showing the flow of the setting / registration operation of the tracking target. FIG. 6 is a screen example showing a state when the tracking target is selected from the image displayed on the monitor. FIG. 7 is a diagram illustrating a flow of a tracking target detection operation. FIG. 8 is a diagram showing the flow of the tracking shooting control operation. FIG. 9 is a diagram corresponding to FIG. 6 when a person who is the subject looks back. FIG. 10 is a view corresponding to FIG. 6 according to the second embodiment. FIG. 11 is a view corresponding to FIG. 9 according to the second embodiment. FIG. 12 is a view corresponding to FIG. 6 according to another embodiment.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. The following embodiments are essentially preferable examples, and are not intended to limit the scope of the present invention, its application, or its use.

<< First Embodiment >>
<Overview>
The tracking control device according to the present embodiment is configured by an image processing device (100). The image processing apparatus (100) is provided in the imaging apparatus (10) that can capture an image in various shooting modes, and performs image processing on the captured image. Specific examples of the imaging device (10) include electronic cameras such as video cameras and digital cameras.

  In particular, the imaging apparatus (10) has a tracking mode function for tracking and imaging a subject with the imaging apparatus (10) being substantially fixed as one of the imaging modes. The image processing apparatus (100) also performs control processing for realizing the tracking function.

  When the imaging device (10) continues to capture the subject, the imaging device (10) is required to keep tracking without losing sight of the subject. However, there is a possibility that the imaging device (10) loses sight of the subject and cannot continue the tracking operation due to the movement of the subject itself or a change in environment.

  In contrast, the image processing apparatus (100) of the present embodiment performs tracking control so that the imaging apparatus (10) can track and image the subject even when the posture or environment of the subject changes.

  Note that the image captured by the imaging device (10) may be a plurality of continuously captured still images or a moving image, but a case where it is a moving image is illustrated below.

<Configuration of imaging device>
As shown in FIG. 1, the imaging device (10) includes an imaging unit (11) and a monitor (30) in addition to the image processing device (100) that is a tracking control device.

  The imaging unit (11) captures an image to obtain image data, and includes a driver (18a, 18b, 18c), a focus lens (12), an aperture unit (14), and an image sensor (20).

  The drivers (18a, 18b, 18c) are connected to the focus lens (12), the aperture unit (14), and the image sensor (20), respectively, and drive the connected functional units. The focus lens (12) is a lens for focusing on a subject, and is movably provided in a housing (not shown) of the imaging device (10). The aperture unit (14) is for adjusting the exposure amount. The image sensor (20) is an image sensor, and an optical image of a subject is incident on the light receiving surface of the image sensor (20) through the focus lens (12). The image sensor (20) generates a raw image signal corresponding to the optical image by performing photoelectric conversion on the optical image. Further, in the image sensor (20), noise removal and level adjustment are performed on the read raw image signal of each frame.

  The image pickup apparatus (10) including such an image pickup unit (11) has an autofocus function for automatically focusing on a main subject, and an automatic exposure for automatically controlling exposure (in other words, aperture opening amount and exposure period). It has a function. In order to realize these functions, the drivers (18a to 18c) of the imaging unit (11) are controlled by a CPU (32) of the image processing apparatus (100) described later.

  Although not shown, the monitor (30) is provided on the surface of the housing of the imaging device (10) at a position where the user can visually recognize it. The monitor (30) has a function as a display unit. The monitor (30) can be composed of a touch panel type liquid crystal display panel, and displays an image captured by the imaging device (10), a menu screen used for various settings of the imaging device (10), and the like.

<Configuration of image processing apparatus>
The configuration of the image processing apparatus (100) according to the present embodiment will be specifically described along with the operation at the time of shooting.

  As shown in FIG. 1, the image processing apparatus (100) includes a signal processing circuit (26), a memory control circuit (24), an SDRAM (38), a monitor driver (28), an I / F circuit (34), a memory A card (36), an MPEG codec (27), a storage unit (42), a CPU (32), and an imaging button (40) are provided.

  Among these, the signal processing circuit (26) has a function as an acquisition unit. The CPU (32) has functions as a tracking control unit, a head detection unit, a face detection unit, and a head color information detection unit.

  The signal processing circuit (26) sequentially acquires raw image signals (digital signals) of each frame output from the image sensor (20) included in the imaging unit (11). The signal processing circuit (26) has a pre-processing circuit (26a) and a post-processing circuit (26b).

  The preprocessing circuit (26a) performs processing such as digital clamping, pixel defect correction, and gain control on the obtained raw image data. The raw image data subjected to these processes is written into the raw image area (38a) of the SDRAM (38) via the memory control circuit (24).

  The post-processing circuit (26b) reads the raw image data stored in the raw image area (38a) via the memory control circuit (24), and performs color separation processing and white balance adjustment processing on the read raw image data. And YUV conversion processing. Further, the post-processing circuit (26b) executes the zoom process for display and the zoom process for search on the image data according to the YUV format in parallel. As a result, display image data and search image data according to the YUV format are individually created. The display image data is written into the display image area (38b) of the SDRAM (38) by the memory control circuit (24). The search image data is written into the search image area (38c) of the SDRAM (38) by the memory control circuit (24).

  By the way, as shown in FIG. 2, the object scene (that is, the screen) is divided into, for example, 16 in each of the vertical direction and the horizontal direction, and 256 blocks are formed on the screen. Each block is assigned a vertical position signal i (i is an integer from 0 to 15) and a horizontal position signal j (j is an integer from 0 to 15). In addition to the processing described above, the signal processing circuit (26) further performs processing for integrating the R component, G component, and B component relating to the image data for each block. As a result, 256 integral values r (i, j) relating to the R component, 256 integral values g (i, j) relating to the G component, and 256 integral values b (i, j) relating to the B component are obtained as a signal. Output from the processing circuit (26) every frame period. These integrated values r (i, j), g (i, j), and b (i, j) are obtained when the CPU (32) adjusts the exposure amount and exposure time by the aperture unit (14). Used as an evaluation value. The signal processing circuit (26) further performs processing for integrating the high frequency components of the R component, G component, and B component for each block. This integrated value is used as an AF evaluation value when the CPU (32) performs processing for optimizing the position of the focus lens (12) (that is, autofocus).

  Further, the signal processing circuit (26) integrates the Y component related to the image data for each block, and outputs 256 integral values y (i, j) related to the Y component to the CPU (32) every frame period. May be.

  Returning to FIG. 1, when the image data of each frame (that is, display image data) stored in the display image area (38b) of the SDRAM (38) is read by the memory control circuit (24), the function as a display control unit is achieved. The monitor driver (28) has a drive for the monitor (30) based on the image data. As a result, a real-time moving image (through image) of the subject is displayed on the monitor (30).

  When a moving image capturing start operation is performed by pressing the image capturing button (40), the CPU (32) sends a recording start command to the MPEG codec (27) and the I / F circuit (34) to start the moving image recording process. give. When a recording end operation is performed by the imaging button (40), the CPU (32) gives a recording end command to the MPEG codec (27) and the I / F circuit (34) in order to end the moving image recording process. During the period from the recording start command to the recording end command, the MPEG codec (27) responds to a vertical synchronization signal (not shown) and the YUV format image stored in the search image area (38c) of the SDRAM (38). Data (that is, search image data) is repeatedly read out via the memory control circuit (24), and the read image data is encoded according to a predetermined format. The I / F circuit (34) records the encoded image data on the memory card (36) in a file format during the period from the recording start command to the recording end command.

  The memory card (36) is provided detachably with respect to the housing (not shown) of the imaging device (10).

  A storage unit (42) composed of a flash memory or the like is electrically connected to the CPU (32). The storage unit (42) stores dictionary data (DB1) used when automatically recognizing a subject to be tracked and evaluation value data (DB2) used during tracking shooting control.

  FIG. 3 shows an example of the concept of dictionary data (DB1). In the dictionary data (DB1) shown in FIG. 3, the feature data (G1) of the person is registered. The feature amount includes subject brightness, brightness, saturation, hue, color component, shape (ie, contour, edge component), orientation, combinations thereof, and the like. In the present embodiment, the case where the feature amount registered in the dictionary data (DB1) is the color component of the subject is illustrated.

  Hereinafter, the color component feature amount of a subject that is a tracking target candidate included in the dictionary data (DB1) is referred to as “color information”.

  In the dictionary data (DB1), the feature amount for each subject may be registered, or a value obtained by averaging the feature amounts for each type of subject may be registered. For example, when the subject is a person, the face color is skin color, so the average value of the skin color can be registered in the data (G1) related to the person.

  FIG. 4 shows the concept of evaluation value data (DB2) as an example. In the evaluation value data (DB2) of FIG. 4, color evaluation values based on color component feature values are stored in association with each specific subject that is a tracking target. Specifically, in FIG. 4, the number “001” of the specific subject to be tracked and the color evaluation value “Clr1” are stored as one record, the number “002” of the specific subject, and the color evaluation value “Clr2” is stored as one record.

  The color evaluation value is a value representing a matching degree between the color component feature amount of the subject to be tracked and the color information in the dictionary data (DB1).

  The color evaluation value calculated for each frame image is constantly updated for each frame image in the evaluation value data (DB2).

  The CPU (32) includes the drivers (18a to 18c), the signal processing circuit (26), the memory control circuit (24), the monitor driver (28), the MPEG codec (27), the I / O of the imaging unit (11) described above. It is electrically connected to the F circuit (34) via a bus. In addition to the various processes described above, the CPU (32) determines a shooting scene (such as a night scene) using each integrated value from the signal processing circuit (26), and sets shooting conditions according to the shooting scene determination result. Processing, exposure adjustment command output based on AE evaluation value under set photographing conditions, autofocus adjustment command output based on AF evaluation value, hue adjustment command output to signal processing circuit (26), and the like are performed.

  In particular, the CPU (32) according to the present embodiment performs tracking target setting / registration processing, tracking target detection processing, and tracking shooting control processing as processing related to tracking shooting.

  The tracking target setting / registration process means that the user directly touches the screen projected on the monitor (30) and selects the subject desired to be tracked and photographed. (32) is the process of writing to the dictionary data (DB1).

  The tracking target detection process refers to the tracking target stored in the dictionary data (DB1) from the search image data in the search image area (38c) when the imaging device (10) is set to the tracking mode. This is a process in which the CPU (32) automatically searches for the presence of a subject.

  The tracking imaging control process is an imaging unit so that the imaging unit (11) can track and capture a specific subject determined as a tracking target when the imaging device (10) is set to the tracking mode. This is a process for controlling the tracking operation of (11).

<Operations in tracking mode>
In the following, the tracking target setting / registration operation, tracking target detection operation, and tracking shooting control operation will be described in detail as operations performed by the image processing apparatus (100) regarding the tracking mode.

-Tracking target setting / registration operation-
FIG. 5 is a diagram illustrating the flow of the setting / registration operation of the tracking target.

  First, an image relating to the display image data is displayed on the monitor (30) so that a subject in the image can be selected (step S11).

  When the subject to be tracked is selected by the user from the screen in step S11 (Yes in step S12), the CPU (32) includes a feature that forms part of the subject and characterizes the subject, And a peripheral part located in the vicinity of (step S13). For example, when the subject is a person, the CPU (32) detects the face portion (62) of the subject from the frame image and sets the face portion (62) as a feature portion. The CPU (32) detects a cluster of colors located above the face (62) and having similar color information more than a predetermined area as the head (61), and moves the head (61) around Set the part. The CPU (32) detects head color information indicating the color of the head (61). As the head color information, for example, the color of the hair or hat is detected.

  The CPU (32) displays a screen in a state where the frame (30a) surrounds the selected subject (that is, displays the frame (30a) so as to overlap the screen of step S11). The driver (28) is driven (step S14). Specifically, the CPU (32) causes the monitor (30) to display one frame (30a) for one subject as shown in FIG. In FIG. 6, as an example, the monitor (30) represents a screen example in which a human face (62) and head (61) are selected as tracking targets. In this case, the frame (30a) collectively surrounds the face (62) and the head (61) as one tracking target.

  When the user performs an operation for registering the subject surrounded by the frame (30a) as the subject to be tracked (Yes in step S15), the CPU (32) sets the subject in the frame (30a) as the subject to be tracked. At the same time, the dictionary data (DB1) is updated by adding the feature amount of the subject to the dictionary data (DB1). (Step S16). Specifically, the CPU (32) sets an object having at least one of the face part (62) and the head part (61) as a tracking target. In addition, in FIG. 6, the case where the face part (62) and the head part (61) are collectively set as one tracking object is illustrated as an example.

  When the registration operation is not performed in step S15 (No in step S15), the series of operations in FIG. 5 ends without setting the tracking target and updating the dictionary data (DB1).

-Tracking target detection operation-
FIG. 7 is a diagram illustrating a flow of a tracking target detection operation.

  First, it is assumed that the tracking mode is set in the imaging device (10) (Yes in step S21). In this state, when the image pickup button (40) is pressed (Yes in step S22), the CPU (32) is in the current search image area (38c) unless the tracking target is already set (No in step S23). The feature amount of the subject in the detected image data stored in is calculated (step S24). The feature amount calculated here includes a color component of the subject. Note that the feature amount calculation is not particularly limited, and a conventionally known method can be used.

  Next, the CPU (32) reads the feature amount of each subject registered in the dictionary data (DB1) (step S25), and collates the feature amount calculated in step S24 with the read feature amount (step S26). . As a result of the collation, if the CPU (32) determines that there is a high possibility that the feature amounts match (Yes in step S26), the subject in the image data stored in the search image area (38c) is tracked. The target is set (step S27).

  In step S26, when there is no subject in the dictionary data (DB1) that is highly likely to match the feature amount calculated in step S24 (No in step S26), the CPU (32) tracks the search image data. The monitor driver (28) is driven so that information indicating that the target does not exist and information indicating that tracking target setting registration is recommended are displayed on the monitor (30) (step S28). In this case, the operation of FIG. 5 is performed depending on the user's operation.

  If the tracking mode is not set in step S21 (No in step S21), if the tracking target has already been set in step S23 (Yes in step S23), steps S27 and S28 are performed. The tracking target detection operation ends.

-Tracking shooting control operation-
FIG. 8 is a diagram showing the flow of the tracking shooting control operation.

  As shown in FIG. 8, this operation is performed after the tracking target detection operation shown in FIG. 7 (step S31) and after the tracking target is set (Yes in step S32). Therefore, when the tracking target has not been set (No in step S32), this operation is not performed.

  Note that the image captured in this operation is a moving image in which a specific subject that is a tracking target is captured. Therefore, the signal processing circuit (26) acquires a plurality of continuous frame images including a specific subject from the imaging unit (11). Using the frame image, the CPU (32) performs tracking control of the specific subject described below so that the imaging unit (11) tracks the tracking target including the specific subject.

  The CPU (32) causes the imaging unit (11) to start tracking shooting (step S33). As a result, the drivers (18a to 18c) of the imaging unit (11) operate the focus lens (12) and the like so as to automatically track and capture a specific subject that has been set.

  During moving image shooting, the signal processing circuit (26) sequentially acquires a plurality of consecutive frame images from the imaging unit (11) and sequentially performs processing. The CPU (32) starts processing for detecting color information for each successive frame image (step S34).

  When the pressing of the imaging button (40) is released (Yes in step S35), a series of operations according to FIG. 8 ends.

-Concrete example-
A specific example of the tracking shooting control operation will be described with reference to FIGS. 6 and 9.

  Here, as shown in FIG. 6, the case where the face (62) and head (61) of a person as a subject are set as tracking targets by the user is illustrated. FIG. 6 shows a first frame image (51) in which the face (62) and head (61) of the subject are detected from among a plurality of frame images. As described above, the face (62) and head (61) of the subject are surrounded by one frame (30a). The CPU (32) detects the first face range (31) where the face (62) is located in the first frame image (51). Note that the first face range (31) is not displayed on the monitor (30).

  When the direction of the subject changes, the face (62) of the subject may not be detected. FIG. 9 shows the second frame image (52) after the first frame image (51). The CPU (32) detects a second face range (33) corresponding to the first face range (31) in the second frame image (52). The second face range (33) is not displayed on the monitor (30). When the CPU (32) detects color information similar to the color of the head (61) in the second face range (33), the face (62) is in the second face range (33). Determine (estimate) and continue tracking of the tracking target. In the second frame image (52), the frame (30a) surrounds the head (61) and the second face range (33).

  Note that, as described above, the CPU (32) sets an object having at least one of the face (62) and the head (61) as a tracking target. For this reason, even when the face (62) or head (61) of the subject cannot be detected, the tracking of the tracking target is continued.

<Effect>
The image processing apparatus (100), which is the tracking control apparatus of the present embodiment, detects the head (61) as the peripheral part on the frame image even when the face (62) as the characteristic part cannot be detected, for example. Track the subject. For this reason, the subject can be tracked continuously. In addition, since the face (62) and the head (61) can be combined into one tracking target, the subject can be easily tracked without switching the tracking target.

  Even when the face part (62) of the subject cannot be recognized, the subject can be tracked based on the color of the hair, hat, or the like. As described above, the orientation of the face part (62) of the subject changes, the face part (62) cannot be detected, and the head part (61) is within the range where the face part (62) has been located so far. May be detected. Even in this case, even if the face (62) itself cannot be recognized, it is determined (estimated) that the face (62) is present, so that the subject can be tracked continuously. Therefore, even if the head (61) is not detected before and after the face (62) cannot be detected, such as when the face (62) is zoomed, the subject is continuously tracked. can do.

  Further, the CPU (32) detects a cluster of colors having the same color information as a predetermined area or more as the head (61). For this reason, the precision which detects a head (61) can be improved.

  One frame (30a) collectively surrounds the face (62) and head (61) as one tracking target. For this reason, it can suppress that the frame image imaged by the number of the frames displayed on the monitor (30) becoming difficult to see.

<< Second Embodiment >>
In the first embodiment, the case where the peripheral portion is the head portion (61) of the subject has been described. However, in this embodiment, the case where the peripheral portion is the trunk portion (63) of the subject will be described. Here, with respect to the image processing apparatus (100) of the present embodiment, differences from the first embodiment will be described based on FIG. 10 and FIG.

  The CPU (32) has a function as a body part detection part and a surrounding color information detection part in addition to the function as the face part detection part described above.

-Tracking target setting / registration operation-
In the tracking target setting / registration operation of the present embodiment, the CPU (32) sets the face (62) of the subject as the feature. The CPU (32) detects a cluster of colors located below the face (62) and having similar color information over a predetermined area as the body (63), and surrounds the body (63). Set the part. The CPU (32) detects peripheral color information indicating the color of the trunk (63). As the peripheral color information, for example, the color of clothes is detected. As shown in FIG. 10, the CPU (32) combines the first frame (30b) surrounding the head and face (62), and the head, face (62) and torso (63) together. A second frame (30c) enclosed as a tracking target is displayed.

  When the user performs an operation of registering the subject surrounded by the frames (30b, 30c) as the subject to be tracked, the CPU (32) sets the subject as the subject to be tracked and sets the feature amount of the subject. Update dictionary data (DB1) by adding to dictionary data (DB1). Specifically, the CPU (32) sets an object having at least one of the face part (62) and the trunk part (63) as a tracking target.

<Tracking control operation>
A specific example of the tracking shooting control operation in this embodiment will be described with reference to FIGS. 10 and 11.

  Here, FIG. 10 shows the first frame image (51) in which the face part (62) and the torso part (63) of the subject are detected among the plurality of frame images. As described above, the face (62) and head of the subject are surrounded by the first frame (30b). The head, face (62), and body (63) of the subject are surrounded by the second frame (30c).

  When the direction of the subject changes, the face (62) of the subject may not be detected. FIG. 11 shows the second frame image (52) after the first frame image (51). When the CPU (32) detects the torso (63) in the second frame image (52), it determines that the face (62) is above the torso (63) and continues to track the tracking target. To do. In the second frame image (52), the frame (30a) surrounds the trunk (63) and the upper part of the trunk (63).

<Effect>
This embodiment has the following effects different from those of the first embodiment.

  According to the present embodiment, even when the face part (62) of the subject cannot be recognized, the subject can be tracked based on the color of clothes or the like in the trunk part (63) corresponding to the peripheral part of the face part (62). it can.

  The monitor (30) includes a first frame (30b) surrounding the face (62) and head of the subject, and a second frame surrounding the head, face (62) and torso (63) of the subject. (30c) is displayed. For this reason, on the monitor (30), it becomes easy to confirm the entire tracking target and the face part (62) which is a characteristic part.

<< Other Embodiments >>
In the first and second embodiments, one person has been described as a tracking target. However, a plurality of subjects may be combined into one tracking target. For example, as shown in FIG. 12, one person (65) and one dog (66) located around the person (65) can be collectively set as one tracking target. In this case, in the tracking target setting / registration operation, the CPU (32) sets the person (65) as the characteristic part and the dog (66) as the peripheral part. The CPU (32) displays a first frame (30b) surrounding the person (65) and a second frame (30c) surrounding the person (65) and the dog (66) as one tracking target. Thus, the peripheral part may not be limited to the part related to the human body.

  The image processing apparatus (100), which is a tracking control apparatus, can be applied not only when a moving image is captured, but also when a plurality of still images are captured continuously.

  In FIG. 1, the tracking control device can be configured to include only the signal processing circuit (26), the CPU (32), and the storage unit (42).

  Dictionary data (DB1) update operation is not essential.

  The shape threshold value and the color threshold value may be appropriately corrected based on the evaluation value instead of the fixed values.

  The present invention is useful as a tracking control device capable of continuously tracking a specific subject.

DESCRIPTION OF SYMBOLS 10 Imaging device 11 Imaging part 26 Signal processing circuit (acquisition part)
28 Monitor driver (display controller)
30 Monitor (display unit)
30a Frame 30b First frame 31 First face range 32 CPU (tracking control unit, head color information detection unit, face detection unit, head detection unit, peripheral color information detection unit, trunk detection unit)
33 Second face range 42 Storage unit 51 First frame image (frame image)
52 Second frame image (frame image)
61 head (peripheral)
62 Face (Characteristics)
63 trunk (peripheral part)
DB1 Dictionary data 100 Image processing device (tracking control device)

Claims (7)

An acquisition unit that acquires a plurality of continuous frame images including a specific subject from the imaging unit of the imaging device, and a tracking control unit that performs tracking control so that the imaging unit tracks a tracking target including the subject. A tracking control device comprising:
In the frame image, the tracking control unit includes at least one of a feature part that constitutes a part of the subject and characterizes the subject and a peripheral part located around the feature part as the tracking target. A tracking control device characterized by setting. In claim 1,
The characteristic part is a face part of the subject, and the peripheral part is a head part of the subject;
A head color information detection unit for detecting head color information indicating the color of the head;
A first frame image included in the plurality of frame images has a first face range in which the face is located;
The head color information detection unit has a color similar to the color of the head from the second face range corresponding to the first face range, which the second frame image after the first frame image has When the information is detected, the tracking control unit determines that the face part is within the second face part range. In claim 2,
A face detection unit for detecting the face from the frame image;
A tracking control, further comprising: a head detection unit that detects the head image that is located above the face and has similar color information having a predetermined area or more in the frame image. apparatus. In claim 2 or 3,
A display control unit for displaying the frame image on the display unit of the imaging device;
The display control unit displays one frame on the display unit for one subject,
The tracking control device according to claim 1, wherein the frame surrounds the face and the head together as one tracking target. In claim 1,
The frame image includes a peripheral color information detection unit that detects peripheral color information indicating the color of the peripheral part,
The tracking control unit, wherein the tracking control unit determines that the color information similar to the peripheral color information has a predetermined area or more is the peripheral unit. In claim 5,
The characteristic portion is a face portion of the subject, and the peripheral portion is a torso portion of the subject;
A face detection unit for detecting the face from the frame image;
A torso detecting unit for detecting the torso from the frame image;
The tracking control apparatus according to claim 1, wherein the trunk detection unit determines that the part below the face is the trunk. In claim 5 or 6,
A display control unit for displaying the frame image on the display unit of the imaging device;
The display control unit causes the display unit to display a first frame that surrounds the characteristic part and a second frame that collectively surrounds the characteristic part and the peripheral part as the tracking target. Control device.