JP2010230871A - Auto focus system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To reduce a photographer's load by searching for the next object to be focused and displaying the same in the case where a number of objects are photographed by a camera system having a face authentication function. <P>SOLUTION: The auto focus system includes: an auto focus means for adjusting the focus of an optical system to be focused on a predetermined object of photographing images; a focus object register means for previously registering a plurality of objects to be a focusing target together with information required for face authentication; an object specifying means for specifying at least one object among the previously registered objects; a face authentication means for performing face authentication for the object in process of photographing and the specified object; a display means for displaying a range of an AF frame set at present to be superposed on the photographing image; and an AF frame automatic tracking means. The system includes: a face authentication tracking mode of tracking a face of a previously registered object; and a face searching mode of only displaying at least one of the AF frame and a name frame and not performing AF frame tracking. <P>COPYRIGHT: (C)2011,JPO&INPIT

Description

  The present invention relates to an autofocus system, and more particularly to an autofocus system having a function of searching for a specific subject from a large number of subjects within a shooting range of a camera and showing it to a cameraman in a camera system having a face authentication function. .

  Conventionally, in an autofocus (AF) system that automatically adjusts the focus of a camera, the camera must be instructed where to focus. At this time, in a general camera or the like, the position to be focused is fixed at the center of the shooting range, and for example, the person in the center of the shooting range is focused.

  However, when shooting a moving subject, it is inconvenient if the focus position is fixed in this way. Therefore, for example, when shooting a scene where the subject moves rapidly, such as sports broadcasting, with a TV camera or the like, the AF area automatic tracking in which the autofocus area (AF area) follows the subject's movement for the purpose of focusing on the subject. A system is known (see, for example, Patent Document 1).

  In addition, an image representing a human face is detected from the captured image, and the face that is the subject is automatically focused, or the area representing the face in the detected image is enlarged. There is known a digital camera that automatically changes the zoom magnification (see, for example, Patent Document 2).

  In the present specification, the range of the subject to be AF in the shooting range of the camera or the image range of the subject to be AF in the shot image of the camera is referred to as an AF area, and indicates the outline of the AF area. The frame is referred to as an AF frame.

JP 2006-267221 A JP 2004-320286 A

  However, it is difficult for photographers (or program production staff) to remember the names of many performers in programs that have many performers, such as marathons and soccer broadcasts. It was a heavy burden on the photographer when switching the target to be adjusted immediately.

  For example, in a marathon broadcast, there are dozens of leading groups and the production staff wants to check the ranking of a specific player, or the photographer finds a specific person who is looking for from among many subjects on the screen In a scene where the person zooms in, there is a problem that the work is very troublesome.

  The present invention has been made in view of such circumstances. When a large number of subjects are photographed by a camera system having a face authentication function, the cameraman searches for and displays a target to be focused next. An object of the present invention is to provide an autofocus system that can reduce the burden on the camera.

  In order to achieve the above object, an invention according to claim 1 is directed to an imaging unit that images a subject image formed by an optical system, and a predetermined AF area of a captured image captured by the imaging unit. Auto focus means for adjusting the focus of the optical system so that the subject is in focus, a plurality of subjects to be focused, together with information necessary for face authentication, a focus target registration means for registering in advance, Subject designation means for designating at least one subject from a plurality of pre-registered subjects to be focused; face authentication means for face authentication of the subject being imaged and at least the designated subject; The captured image captured by the imaging unit is displayed on the image display screen, and the currently set AF frame range is superimposed on the captured image. Display means for displaying, and AF frame automatic tracking means for automatically tracking the AF frame to the subject to be tracked so that a predetermined subject to be tracked is in focus, and at least the face of the subject registered in advance is included. Face recognition tracking mode to track with the AF frame, and search for the specified subject from pre-registered subjects, and AF frame tracking only by displaying at least one of the AF frame and the subject name frame for that subject And an autofocus system characterized by having a face search mode that does not perform.

  Accordingly, when a large number of subjects are photographed by a camera system having a face authentication function, it is possible to reduce the burden on the photographer by searching for and displaying a target to be focused next.

  Further, according to a second aspect of the present invention, the face authentication unit authenticates the subject being imaged and the registered subject, and the display unit displays the subject in the captured image displayed on the image display screen. Of the registered subject and face-authenticated subject, an AF frame and a name frame for displaying the name of the subject are displayed. When at least one subject is designated from the subjects to be selected, the AF frame displayed for the designated subject among the subjects in the captured image displayed on the image display screen and the subject The name frame is displayed by changing the color of the name frame from the AF frame displayed for other subjects and the color of the name frame of the subject.

  Thus, even when the AF frame and the name frame of the subject are displayed for a large number of subjects in the captured image, the subject that the operator is looking for can be easily recognized.

  Further, as shown in claim 3, the autofocus system according to claim 1, further comprising a touch operation detection unit that detects an operator's touch operation on the image display screen of the display unit, The subject specifying means is constituted by the touch operation detecting means.

  As a result, the subject to be searched for by the operator can be easily specified.

  Further, according to a fourth aspect of the present invention, in the autofocus system according to the third aspect, a menu image for selecting the mode by a touch operation on the image display screen of the display unit is further displayed. And a menu display unit that is superimposed on the display unit and displayed on the image display screen of the display unit.

  Thereby, the operator can easily select the face recognition tracking mode and the face search mode.

  As described above, according to the present invention, when a large number of subjects are photographed by a camera system having a face authentication function, the burden on the photographer is reduced by searching for and displaying a target to be focused next. can do.

1 is an external view showing an embodiment of a television camera system to which an autofocus system of the present invention is applied. It is a block diagram which shows the whole structure of the AF frame automatic tracking system applied to a television camera system. It is explanatory drawing which shows the example of AF frame (AF area). It is explanatory drawing which shows an example of the screen displayed on the liquid crystal display with a touch panel in face recognition tracking mode. It is the flowchart which showed the process sequence of face recognition tracking mode. It is explanatory drawing which shows an example of the screen displayed on the liquid crystal display with a touch panel in face search mode. It is the flowchart which showed the processing procedure of face search mode.

  Hereinafter, an autofocus system according to the present invention will be described in detail with reference to the accompanying drawings.

  FIG. 1 is an external view showing an embodiment of a television camera system to which the autofocus system of the present invention is applied.

  As shown in FIG. 1, a television camera 10 is a television camera mainly used for broadcasting or business use. The television camera 10 includes a lens device 12 and a camera body 14 and is installed on a pedestal 16. 18 is supported.

  The pan head 18 has two left and right bread bars 22, 24 extending, and the grip demand 22 A of the right bread bar 22 is provided with a focus demand (focus controller) 26 by a mounting clamp 38. A zoom demand (zoom controller) 28 is installed in the grip portion 24A of the pan bar 24.

  The focus demand 26 is provided with a rotatable focus knob 30. When focus control is performed by manual focus (MF), when the focus knob 30 is rotated, a focus corresponding to the rotation position is obtained. A focus control signal for instructing movement of the focus (focus lens) with the position as the target position is given from the focus demand 26 to the lens device 12. As a result, the focus lens of the lens device 12 moves to the target position commanded by the focus control signal.

  The zoom demand 28 is provided with a rotatable thumb ring 34. When the thumb ring 34 is rotated in the left-right direction, the zoom (zoom lens) is moved with a zoom speed corresponding to the rotation position as a target speed. A zoom control signal to be commanded is given from the zoom demand 28 to the lens device 12. As a result, the zoom lens of the lens device 12 moves at the target speed commanded by the zoom control signal.

  Although not shown in the figure, the focus demand 26 is provided with various operation members related to autofocus (AF), and control of an AF frame indicating a subject range (AF target range) to be focused by AF ( An AF frame control device (AF frame automatic tracking device) for performing a change in position and the like is incorporated, and various operation members of the AF frame control device are also provided in the focus demand 26.

  Further, as shown in FIG. 1, a liquid crystal display (LCD) 40 with a touch panel is installed on the upper portion of the focus demand 26 as a constituent element of the AF frame control apparatus, and is connected to the focus demand 26 by a cable (not shown).

  In the following description, the LCD 40 is simply referred to as the liquid crystal display 40 with a touch panel. The LCD 40 can be installed at any position other than the upper part of the main body of the focus demand 26. For example, it may be installed beside the viewfinder 36.

  A viewfinder 36 that is a display device is installed on the camera body 14. Since the viewfinder 36 displays an image of the subject photographed by the television camera 10, the cameraman operates the focus demand 26 and the zoom demand 28 while viewing the image, thereby selecting the subject with a desired composition. You can shoot. In the following description, when referred to as a captured video or captured image, the video or image currently captured by the television camera 10 is indicated.

  In addition, an image of the AF frame indicating the position, size, and shape (aspect ratio) where the AF frame is currently set is superimposed on the captured image displayed on the viewfinder 36. When focus control is performed by AF, it is possible to know which range of subjects in the captured image can be focused. The focus control of MF and AF can be switched by a mode switch or the like provided in the focus demand 26.

  FIG. 2 is a block diagram showing the overall configuration of an AF frame automatic tracking system applied to the television camera system.

  In the AF frame automatic tracking system shown in FIG. 2, the lens device 12, the camera body 14, and the viewfinder 36 of the television camera 10 shown in FIG. Further, as components of the focus demand 26 in FIG. 1, a focus operation unit 50, an image processing unit 58 and an AF frame operation unit 60 constituting an AF frame control device (AF frame automatic tracking device) incorporated in the focus demand 26. It is shown.

  The television camera 10 includes a camera body 14 composed of an HD camera compatible with a high-definition television [HD (High Definition) TV] system, and a lens device 12 having a photographing lens (optical system) attached to a lens mount of the camera body 14. It consists of.

  The camera body 14 is equipped with an image sensor (for example, a CCD), a required signal processing circuit, and the like. The image formed by the photographing lens of the lens device 12 is photoelectrically converted by the image sensor and then subjected to signal processing. Necessary signal processing is performed by the circuit and output as an HDTV video signal (HDTV signal) from the video signal output terminal of the camera body 14 to the outside.

  In addition, as shown in FIG. 1, a video captured by the television camera 10 is displayed on the viewfinder 36 installed on the upper part of the camera body 14 or the like. Various information other than the captured video is displayed on the viewfinder 36. For example, an image indicating the currently set AF frame range (position, size, shape) is superimposed on the captured video. Has been displayed.

  The lens device 12 includes a photographic lens (zoom lens) 64 attached to a lens mount of the camera body 14, and the subject 56 forms an image on the imaging surface of the image sensor of the camera body 14 by the photographic lens 64. It is like that. Although not shown, the photographing lens 64 is provided with movable parts for adjusting photographing conditions such as a focus lens group, a zoom lens group, and a diaphragm as its constituent elements. Servo mechanism) is electrically driven. For example, the focus lens group and the zoom lens group move in the optical axis direction, the focus (subject distance) adjustment is performed by moving the focus lens group, and the focal length (zoom magnification) is adjusted by moving the zoom lens group. Adjustments are made.

  In the AF-related system, it is sufficient that at least the focus lens group can be driven electrically, and other movable parts may be driven only manually.

  The lens device 12 includes an AF unit 66 and a lens CPU (not shown). The lens CPU controls the entire lens device 12. The AF unit 66 is a processing unit for acquiring information necessary for performing AF focus control (automatic focus adjustment), and is configured from an AF processing unit, an AF imaging circuit, and the like, although not shown. Has been.

  The AF imaging circuit is disposed in the lens device 12 to acquire an AF processing video signal, and an output signal from an imaging device such as a CCD (referred to as an AF imaging device) or an AF imaging device is output in a predetermined format. A processing circuit for outputting as a signal is provided. The video signal output from the AF imaging circuit is a luminance signal.

  On the imaging surface of the AF imaging device, subject light branched from subject light incident on the imaging device of the camera body 14 is imaged by a half mirror or the like disposed on the optical path of the photographing lens 64. . The shooting range and subject distance (distance of the subject in focus) with respect to the imaging area of the AF imaging element are configured to match the shooting range and subject distance with respect to the imaging area of the imaging element of the camera body 14. The subject image captured by the image sensor coincides with the subject image captured by the image sensor of the camera body 14. It should be noted that the shooting ranges of the two do not need to be completely the same. For example, the shooting range of the AF imaging element may be a larger range including the shooting range of the imaging element of the camera body 14.

  The AF processing unit acquires a video signal from the AF imaging circuit, and based on the video signal, calculates a focus evaluation value indicating the level of contrast of the subject image within an AF area (AF frame) that is an AF target range. calculate. For example, a high frequency component signal is extracted from a video signal obtained from an AF image sensor by a high-pass filter, and then a range corresponding to an AF area set as described later in the high frequency component signal. Are integrated for each screen (one frame). The integrated value obtained for each screen in this manner indicates the level of contrast of the subject image in the AF area, and the integrated value is given to the lens CPU as a focus evaluation value.

  The lens CPU acquires AF frame information (AF frame information) indicating the range (contour) of the AF area from the image processing unit 58 as described later, and the range within the AF frame specified by the AF frame information is obtained. The AF area is designated as the AF area. Then, the focus evaluation value obtained from the image (video signal) in the AF area is acquired from the AF processing unit.

  In this way, every time a video signal for one screen is acquired from the AF imaging circuit (each time the focus evaluation value is obtained by the AF processing unit), the focus evaluation value is acquired from the AF processing unit, and the acquired focus is obtained. The focus lens group is controlled so that the evaluation value is maximum (maximum), that is, the contrast of the subject image in the AF frame is maximum. For example, a hill-climbing method is generally known as a control method for a focus lens group based on a focus evaluation value, and the focus evaluation value starts to decrease by moving the focus lens group in a direction in which the focus evaluation value increases. Is detected, the focus lens group is set at that position. Thereby, the subject in the AF frame is automatically focused.

  Note that the AF processing unit described above acquires a video signal from an AF image sensor mounted on the lens device 12 in order to calculate a focus evaluation value, but is captured by the image sensor of the camera body 14. The video signal of the obtained video may be obtained from the camera body 14. Also, any AF means for automatically focusing on the subject within the AF frame may be used.

  FIG. 3 shows an example of an AF frame (AF area). The AF area 200 is set as a rectangular area with respect to the imaging area 202 of the imaging device in the camera body 14 as shown in FIG. 3, and a frame 204 indicating its outline indicates an AF frame, and the AF area 200 of the imaging device. A subject to be photographed in the range (within the AF frame 204) is set to be focused by AF.

  Here, it is assumed that the range of the AF frame 204 (AF area 200) with respect to the imaging area 202 is determined by three elements of the position, size, and shape (aspect ratio) of the AF frame 204. The description to the effect that “changes” means that at least one of the three elements of the position, size, and shape of the AF frame is changed.

  The lens device 12 is connected to the camera body 14 via a cable or directly, and various kinds of information are transmitted through serial communication interfaces (SCI) 12a and 14a provided in the lens device 12 and the camera body 14, respectively. You can communicate. As a result, information on the AF frame currently set in the AF unit 66 is also transmitted to the camera body 14, and the position of the AF frame currently set in the captured image displayed on the viewfinder 36 by processing in the camera body 14. The image of the AF frame corresponding to the size and shape is superimposed and displayed.

  The focus operation unit 50 is a constituent element of the focus demand 26 and also shows constituent elements of a general focus demand. As the components of the focus operation unit 50, the focus knob 30 shown in FIG. 1, a mode switch (not shown) for switching between the AF mode and the MF mode and the AF mode type (continuous mode or momentary mode), An operation member relating to AF control contents and MF control, such as an AF start switch (not shown) for instructing the start of AF, is provided, and a setting state of these operation members is detected, and a control signal is based on the detected setting state The processing circuit etc. which send out are provided.

  The focus demand 26 is provided with an interface (I / F) 52 for connecting to the lens device 12 with a cable. The focus operation unit 50 is connected to the lens device 12 via the I / F 52 and the cable, and the SCI 12a. Various signals can be exchanged through serial communication with the lens CPU.

  Accordingly, various control signals sent from the focus operation unit 50 are given to the lens CPU, and processing according to the control signals is executed by the lens CPU. For example, when an instruction for focus control (AF mode) by AF is given, focus control by AF is performed based on the focus evaluation value obtained from the AF unit 66 as described above, and focus control by MF (MF When an instruction of (mode) is given, focus control by MF is performed according to a focus position command signal given from the focus operation unit 50 based on the operation of the focus knob 30.

  The image processing unit 58 is a processing unit incorporated in the focus demand 26 as a component of the AF frame control device, and the range (position, size, shape (vertical and horizontal) of the AF frame set in the AF unit 66 of the lens device 12. A ratio)) is designated by a manual operation or AF frame automatic tracking process described later.

  The image processing unit 58 includes an SCI 70a. The SCI 70a is connected to the lens device 12 through the I / F 52, and can exchange various signals with the lens CPU through the SCI 12a. Thereby, AF frame information for designating the range of the AF frame is given from the image processing unit 58 to the lens CPU of the lens device 12, and the range of the AF frame in the AF unit 66 is set based on the AF frame information.

  The focus demand 26 is provided with a video input connector for taking a video signal into the image processing unit 58, and the video output connector of the camera body 14 is connected to the video input connector via a down converter 68 with a cable. The As a result, the HDTV signal output from the video output connector of the camera body 14 is converted (down-converted) into a standard television [NTSC (National Television System Committee)] video signal (SDTV signal) by the down converter 68. Are input to the image processing unit 58.

  When executing the AF frame automatic tracking process, the image processing unit 58 sequentially captures one frame of the captured image from the video signal input from the camera body 14 and detects a predetermined subject to be tracked from the captured image. Perform the process. Then, the AF frame range is determined so that the subject can be focused by AF, and the determined AF frame range is transmitted to the lens CPU of the lens device 12.

  The AF frame operation unit 60 is integrally provided with the image processing unit 58 in the focus demand 26 as an AF frame control device, or a part or all of the AF frame operation unit 60 is a separate device from the focus demand 26, that is, image processing. The unit 58 is provided in a separate device and connected by a cable or the like. In the present embodiment, as shown in FIG. 1, the LCD 40 with a touch panel is provided separately from the focus demand 26 (image processing unit 58), and other components are provided on the focus demand 26 together with the image processing unit 58. ing.

  The AF frame operation unit 60 is an operation unit for mainly performing operations related to control of the AF frame, and an operation member for an operator to manually input an AF frame range or an AF frame to a desired subject. There is provided an operation member for performing an operation related to AF frame automatic tracking to be automatically tracked.

  As an operation member of the AF frame operation unit 60, a position operation member 100 (for example, a joystick or a trackball) for moving the position of the AF frame up and down and left and right by a user's manual operation, and the size of the AF frame are changed by a manual operation. A size operation member 102 (for example, a knob) for adjusting the shape, a shape operation member 104 (for example, a knob) for changing the shape of the AF frame by manual operation, a tracking start switch 108 for instructing the start of AF frame automatic tracking, AF A tracking stop switch 110 for instructing stop of frame automatic tracking is provided, and the setting states of these operation members 100, 102, 104, 108, 110 are set by the image processing unit 58 (CPU 78 of the main board 70 described later). It can be read.

  Further, the LCD 40 of the AF frame operation unit 60 is configured such that settings such as a mode related to AF frame automatic tracking can be input by a touch operation (tap operation), and an image displayed on the LCD 40 by the CPU 78 of the image processing unit 58 is displayed. It can be switched appropriately according to the setting contents.

  In the present embodiment, the AF frame control device including the image processing unit 58 and the AF frame operation unit 60 is incorporated in the focus demand 26. However, the AF frame control device is different from the focus demand 26. It may be configured as a body device. In this case, a part or all of the AF frame operation unit 60 may be provided in an apparatus integrated with the image processing unit 58, or may be provided in a separate apparatus.

  The image processing unit 58 mainly includes a main board 70, a pattern matching processing calculation board 72, and a face authentication processing calculation board 74. Each of the main board 70, the pattern matching processing calculation board 72, and the face recognition processing calculation board 74 is equipped with CPUs 78, 90, and 92. Individual calculation processing is performed for each board, and each of the CPUs 78 and 90 is performed. , 92 are connected by a bus or a control line so that data can be exchanged or arithmetic processing can be synchronized with each other.

  The processing in the image processing unit 58 is performed on the main board 70 in an integrated manner. In addition to the CPU 78 that performs arithmetic processing, the main board 70 is equipped with an SCI 70a, a decoder (A / D converter) 76, a superimposer 82, a RAM 80, and the like.

  The SCI 70a is an interface circuit for performing serial communication with the SCI 12a of the lens apparatus 12 as described above, and transmits the AF frame information and the like to the lens apparatus 12.

  The decoder 76 is a circuit for converting a video signal (SDTV signal) of a video image taken by the television camera 10 input from the down converter 68 to the image processing unit 58 into data that can be digitally processed by the image processing unit 58. A / D conversion processing for converting an analog SDTV signal into a video signal of digital data is performed.

  The superimposer 82 is a circuit that synthesizes the video signal of the captured video obtained by the decoder 76 and the image signal generated by the CPU 78 and outputs and displays the synthesized video signal on the LCD 40. As a result, the image captured by the television camera 10 is displayed on the LCD 40 in the same manner as the viewfinder 36 installed in the camera body 14, and the AF indicating the currently set AF frame range is superimposed on the image captured. An image of the frame, a menu screen (menu image) that allows input operations on the touch panel, and the like are displayed on the LCD 40. Of course, it is also possible to display only the image generated by the CPU 78 without being superimposed on the captured video.

  The RAM 80 is a memory that temporarily stores data used in the arithmetic processing of the CPU 78.

  On the other hand, the pattern matching processing calculation board 72 and the face recognition processing calculation board 74 are calculation boards for individually performing pattern matching and face detection / recognition processing. In addition to the CPUs 90 and 92 that perform calculation processing, image data VRAM 94, 98, etc. are temporarily stored.

  Further, the image processing unit 58 is provided with a slot 115 into which a data card 114 is loaded as an external memory such as an SD (Secure Digital) card or a USB memory, and when detecting a face of a specific person by face recognition. Authentication data indicating the face of the specific person is stored in the data card 114 in advance, and the data card 114 is loaded into the slot 115, whereby the CPU 78 can read the authentication data necessary for face recognition from the data card 114. It is like that.

  Next, control of the AF frame by the image processing unit 58 configured as described above will be described together with processing relating to display and operation of the LCD 40.

  First, processing when the face recognition tracking mode is selected will be described.

  FIG. 4 shows an example of a screen displayed on the liquid crystal display with a touch panel (LCD 40) in the face recognition tracking mode.

  As shown in FIG. 4, the screen 40a of the LCD 40 shows a menu screen (menu image) composed of various buttons 300 to 306 superimposed on the video image taken by the television camera 10 and the range of the AF frame currently set. An AF frame image 204 (204a to 204c) indicating the range of the AF frame is displayed. Further, on the screen 40a shown in FIG. 4, a registered face image display unit 316 (316a to 316c), selection buttons 318a and 318b, an edit button 320, and the like related to face recognition are displayed.

  Here, images to be superimposed on the photographed image such as various buttons and AF frames on the menu screen are generated by the CPU 78 of the main board 70 in the image processing unit 58 shown in FIG. Are superimposed on the video image taken by the TV camera 10 obtained from the decoder 76 and displayed on the LCD 40. Note that the CPU 78 controls the display (display contents) on the LCD 40.

  On the other hand, the LCD 40 is provided with a touch panel, and when a touch operation with which a fingertip or the like touches the screen 40a of the LCD 40 is performed, position information indicating the touched position (coordinates) is given to the CPU 78. Thus, the position of the touch operation performed on the screen 40a of the LCD 40 and the type of operation (tap operation, double tap operation, etc.) are detected by the CPU 78, and processing according to the operation is executed by the CPU 78. It has become.

  The menu screen displayed on the screen 40a of the LCD 40 will be described. In FIG. 4, a fixed mode selection button 300 displayed as “fixed”, an object tracking mode selection button 302 displayed as “object tracking”, and “face detection”. A face detection tracking mode selection button 304 displayed as "Face recognition" and a face recognition tracking mode selection button 306 displayed as "Face recognition" are buttons for selecting the control mode of the AF frame, and any one of these buttons 300 to 306 is selected. By tapping, a desired mode can be selected from the fixed mode, the object tracking mode, the face detection tracking mode, and the face recognition tracking mode.

  A reset button 310 displayed as “Reset” is used by the operator to instruct to stop AF frame automatic tracking.

  Each mode will be described. First, the fixed mode is a mode in which the operator manually designates the range (position, size, shape) of the AF frame, and fixes the AF frame at the designated position (manual mode). It is. This fixed mode is a mode useful for shooting a news program or the like that hardly moves the camera.

  The object tracking mode is one mode of AF frame automatic tracking, and is a mode for tracking an arbitrary type of object with the AF frame. This object tracking mode is a mode useful for shooting at a horse race relay, a car race relay, etc. for tracking other than a person's face.

  The face detection tracking mode is one mode for automatically tracking the AF frame, and is a mode for tracking the face of an arbitrary person using the AF frame. This face detection tracking mode is a mode useful for shooting in a song program or the like for detecting and tracking a person's face.

  Finally, the face recognition tracking mode is a mode for automatically tracking the AF frame, and is a mode for tracking the face of a person registered in advance as authentication data using the AF frame. This face recognition tracking mode is a mode useful for shooting in a song program or a sports broadcast in which a person to be shot is determined in advance.

  The AF frame automatic tracking starts when a desired position on the screen 40a is double-tapped (an operation for tapping the same position twice in succession), and the AF frame is set at a position centered on that position. AF automatic tracking is started. That is, the first tap operation of the double tap operation is an instruction operation to move the AF frame to the position where the AF frame is tapped, and the subsequent second tap operation is an operation to instruct the start of AF frame automatic tracking. Therefore, the AF button automatic tracking may be started only by a double tap operation, and the set button described above may be omitted.

  The screen 40a of the LCD 40 in FIG. 4 represents a screen when the face recognition tracking mode selection button 306 is tapped and the face recognition tracking mode is selected. That is, when the face recognition tracking mode is selected, the CPU 78 mounted on the main board 70 of the image processing unit 58 starts processing in the face recognition tracking mode. When the face recognition tracking mode is selected, the AF frame range (204a to 204c) is automatically set according to the face of the person as shown in FIG.

  The automatic AF frame tracking is automatically started when a face registered as authentication data is detected.

  FIG. 5 is a flowchart showing the processing procedure in the face recognition tracking mode. Hereinafter, the processing in the face recognition tracking mode will be described with reference to this flowchart.

  When the face recognition tracking mode is selected, the CPU 78 of the main board 70 first performs processing for setting a tracking target face (AF frame initial setting processing). First, in step S100 of FIG. 5, a person who recognizes a face and is to be tracked is designated. That is, the authentication data of the face of one or more persons who are candidates for tracking is registered in the data card 114 loaded in the slot 115 shown in FIG. 2, and the CPU 78 stores the authentication data in the data card. 114. Then, it instructs the CPU 92 of the face authentication processing calculation board 74 to start face recognition processing. Here, the authentication data is obtained from a plurality of data such as different face images such as a different face per day, front face, left face or right face, distance between eyes, distance between eyes and nose, ratio of these, etc. It is configured.

  When the start of face recognition processing is instructed, in step S102, the CPU 92 of the face recognition processing calculation board 74 captures image data of one frame of captured images from the decoder 76. Then, an arbitrary face (face image) included in the captured image is detected by face detection processing.

  In step S104, face recognition processing is performed. That is, the authentication data is obtained from the CPU 78 of the main board 70, and whether or not the face image detected by the face detection process is a face image of a specific person registered in advance as authentication data is used. Judgment.

  Note that the face detection process performed in this face recognition tracking mode is a part of the face recognition process, and in the face recognition process of step S114 described later, an arbitrary face image is detected by the face detection process, and then authentication Matching with the face of the data is performed.

  When the face recognition process ends, the CPU 92 notifies the CPU 78 of the main board 70 of the result. Thereby, the CPU 78 detects the range of the face image when a face of a specific person registered as authentication data is detected, and the face image when a face of a person not registered as authentication data is detected. Get range and.

  Next, as shown in FIG. 4, the CPU 78 displays face frames 204 a and 204 b in the range of the face image in which a human face is detected on the screen 40 a of the LCD 40. When the face of a person registered as authentication data is detected by the face recognition process in step S104, the name of the person is also displayed in the face frame. Further, the face image of the person registered as the authentication data as described above is displayed on the registered face image display unit 316 (316a to 316c).

  Here, the number of face images displayed on the registered face image display unit 316 is also changed according to the number of faces registered as authentication data.

  The operator selects a face image to be tracked from the face images displayed on the registered face image display unit 316 by tapping the selection button 318a or 318b. Each time the upper selection button 318a is tapped, the selected face image is changed to the face image one level above the currently selected face image, and the selection is performed every time the lower selection button 318b is tapped. The face image to be changed is changed to a face image one level lower than the currently selected face image. Note that, as indicated by reference numeral 316b in FIG. 4, the face image currently selected in the registered face image display unit 316 is displayed in an enlarged manner as compared with other face images.

  When the edit button 320 is tapped, the order of face images displayed on the registered face image display unit 316 can be edited. Thus, for example, when the faces of a plurality of persons registered as authentication data are set as tracking targets in a predetermined order, the order of the face images displayed on the registered face image display unit 316 can be set according to the order. For example, the face to be tracked can be switched in a predetermined order each time the selection button 318a or 318b is tapped once.

  Subsequently, in step S106, the CPU 78 determines whether or not the tracking target face set as described above is detected in step S104.

  If this determination is NO, the process returns to step S102 and the above process is repeated. That is, the processes in steps S102 to S106 are repeated until the tracking target face is detected in the captured image by the face recognition process in step S104.

  On the other hand, if YES is determined in step S106, that is, if a tracking target face is detected in the captured image, the process proceeds to the next step S108 to start the tracking process. That is, the range of the face image is set as the AF frame range (AF frame initial setting process), and the CPU 78 (and the CPU 92 of the face recognition processing calculation board 74) performs AF frame automatic tracking processing by the face recognition processing (step S112 to S124) are started, and a process (AF frame information transmission) for designating the range of the AF frame determined by the AF frame automatic tracking process to the lens CPU of the lens device 12 is started.

  In step S110, a reference pattern is set. As in the object tracking mode and face detection tracking mode, when AF control is not performed when AF frame automatic tracking frame automatic tracking is started (when AF mode is not set), AF frame automatic The start of AF is also instructed in conjunction with the start of tracking.

  When the AF frame automatic tracking process is started, in the next step S112, the CPU 92 of the face recognition processing calculation board 74 supports the execution of the face recognition process from the CPU 78, and the image of the captured image for one frame from the decoder 76. Capture data.

  In step S114, the tracking target face authentication data selected above is acquired from the CPU 78, and the tracking target face authentication data is used in the tracking target face identification data in the same manner as in step S104 to detect the tracking target face. And the CPU 78 notifies the CPU 78 of the range of the face image.

  In step S116, the CPU 78 determines whether or not the tracking target face set above is detected in step S114 in the same manner as in step S106.

  If YES in step S116, the process proceeds to step S124 to update the AF frame. On the other hand, if the determination in step S116 is NO, pattern matching processing is performed with the reference pattern set above in the next step S118.

  Then, in the next step S120, it is determined whether or not the object currently being tracked has moved based on the result of the pattern matching.

  If NO in step S120, that is, if the tracking target has not moved, the process returns to step S112 and the above process is repeated. On the other hand, if the determination in step S120 is YES, the tracking target has moved, so the reference pattern is updated in the next step S122.

  In the next step S124, the AF frame is updated in accordance with the moved tracking target. After that, it returns to step S112 again and repeats the said process.

  The above is the flow of processing in the face recognition tracking mode.

  Next, processing in the face search mode, which is a point of the present invention, will be described.

  FIG. 6 shows an example of a screen displayed on the liquid crystal display with a touch panel (LCD 40) in the face search mode.

  As shown in FIG. 6, various buttons are displayed on the screen 40 a of the LCD 40 so as to be superimposed on the captured video of the television camera 10 as in the case of FIG. 4 described above. In particular, in the face search mode display screen, a face search mode selection button 308 is displayed in addition to the fixed mode selection button 300, the object tracking mode selection button 302, the face detection tracking mode selection button 304, and the face recognition tracking mode selection button 306. Has been.

  Here, when the face search mode selection button 308 is tapped, the face search mode is selected.

  A screen 40a of the LCD 40 in FIG. 6 represents a screen when the face search mode selection button 308 is tapped and the face search mode is selected. That is, when the face search mode is selected, the CPU 78 mounted on the main board 70 of the image processing unit 58 starts the process of the face search mode.

  In the face search mode, “name and face” of a registered person is displayed in the registered face image display unit 316 (316a to 316c) as a list, and the person who searched for the face is selected from the list. Then, without AF frame tracking, the person's face is searched and displayed so that the photographer can understand it.

  FIG. 7 is a flowchart showing the processing procedure of the face search mode. Hereinafter, the process of the face search mode will be described with reference to this flowchart.

  First, in step S200 of FIG. 7, a recognized person is designated. That is, the person who searches for a face is designated. This is the same as the processing in step S100 of FIG.

  Next, in step S <b> 202, the CPU 92 of the face recognition processing calculation board 74 takes in image data of a captured image for one frame from the decoder 76. Then, an arbitrary face (face image) included in the captured image is detected by face detection processing.

  Next, in step S204, face recognition processing is performed. That is, the authentication data is obtained from the CPU 78 of the main board 70, and whether or not the face image detected by the face detection process is a face image of a specific person registered in advance as authentication data is used. Judgment.

  Next, in step S206, it is determined whether or not the face designated to be searched above is in the recognized face image.

  As a result, if the designated face is recognized, the face frame 204 is displayed for the person in the image and the name of the person (“ SATO ") frame is displayed.

  In this way, in the face search mode, the person who the operator wants to search for is searched from a large number of persons on the screen and displayed, and AF frame tracking is not performed. Therefore, if the operator wants to track this person, automatic tracking is started by operating the tracking start switch 108.

  Normally, AF frames and name frames are displayed for all registered persons on the screen, but if there are many people on the screen, if name frames are displayed for all persons, Since the person being searched for is difficult to understand, only the name frame of the person being searched for may be displayed when the face being searched for is found in the face search mode. In addition, when the number of people is small, even if the name frame is displayed for all persons, it is possible to immediately know which person is looking for, so the name frame may be displayed for all persons. .

  Also, when displaying name frames for all people, the name frame of the person you are looking for is displayed in a different color from the name frame of other people. It is preferable to display in an easy-to-understand manner.

  As described above, in this embodiment, in addition to the face recognition tracking mode in which the face of a specific person is authenticated and automatically tracked by face authentication, the face of the specific person is searched for and the person is assigned to the operator. By providing a face search mode that displays where you are in the screen, when the operator is shooting a large number of subjects with a camera system that has a face authentication function, the operator can select the target to be focused next. It can be easily confirmed and the burden on the operator is reduced.

  The autofocus system of the present invention has been described in detail above, but the present invention is not limited to the above examples, and various improvements and modifications may be made without departing from the scope of the present invention. Of course.

  DESCRIPTION OF SYMBOLS 1 ... AF frame automatic tracking system, 10 ... Television camera, 12 ... Lens apparatus, 14 ... Camera body, 26 ... Focus demand, 36 ... Viewfinder, 40 ... Liquid crystal display (LCD) with a touch panel, 50 ... Focus operation part, 58 ... Image processing unit, 60 ... AF frame operation section, 66 ... AF unit, 68 ... Down converter, 70 ... Main board, 72 ... Pattern matching processing calculation board, 74 ... Face recognition processing calculation board, 76 ... Decoder, 78, 90 , 92 ... CPU, 82 ... Superimposer, 114 ... Data card, 115 ... Slot, 200 ... AF area, 204 ... AF frame, 306 ... Face recognition tracking mode selection button, 308 ... Face search mode selection button, 316 ... Registration Face image display

Claims (4)

Imaging means for imaging a subject image formed by an optical system;
Auto focus means for adjusting the focus of the optical system so that a subject in a predetermined AF area out of the captured image captured by the imaging means is in focus;
Focus target registration means for registering a plurality of subjects to be focused together with information necessary for face authentication;
Subject designation means for designating at least one subject out of the plurality of pre-registered subjects to be focused;
Face authentication means for performing face authentication on the subject being imaged and at least the specified subject;
Display means for displaying a captured image captured by the imaging means on an image display screen, and displaying a currently set AF frame range superimposed on the captured image;
AF frame automatic tracking means for automatically tracking the AF frame to the tracking target subject so as to focus on a predetermined tracking target subject;
At least a face recognition tracking mode in which the face of the subject registered in advance is tracked with an AF frame, a designated subject is searched from the subjects registered in advance, and the AF frame and the subject name frame are searched for the subject. And a face search mode that only displays at least one of them and does not perform AF frame tracking.   The face authentication means performs face authentication of the subject being imaged and the registered subject, and the display means performs face authentication with the registered subject among the subjects in the captured image displayed on the image display screen. When an AF frame and a name frame for displaying the name of the subject are displayed for the subject that has been selected, at least one subject out of the plurality of pre-registered subjects to be selected by the subject specifying means Is specified, among the subjects in the captured image displayed on the image display screen, the AF frame displayed for the specified subject and the color of the name frame of the subject are changed to other subjects. The autofocus system according to claim 1, wherein the autofocus system displays the AF frame displayed in a different manner from the color of the AF frame displayed on the subject and the name frame of the subject.   3. The autofocus system according to claim 1, further comprising touch operation detection means for detecting an operator's touch operation on the image display screen of the display means, wherein the subject designating means detects the touch operation detection. An autofocus system characterized by comprising means.   4. The autofocus system according to claim 3, further comprising: a menu image for selecting the mode by a touch operation on the image display screen of the display unit is superimposed on the captured image, and the image display of the display unit is performed. An autofocus system comprising a menu display means for displaying on a screen.

Images