JPH09322178A - Method for recognizing object for automatic photographic camera system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To stably recognize the object of target of automatic tracking regardlessly of photographic conditions such as weather by previously setting plural colors constituting the surface part of the object as extract colors. SOLUTION: A video signal VD 1 photographed by a sensor camera 100 is inputted to a three-dimensional position measuring instrument 300, digitized and sent to a color space converting circuit 311 inside an object recognizing part 310. The object recognizing agent 310 is composed of the color space converting circuit 311 for receiving digitized image data (R, G and B) and converting these data to a color space of HSI system suitable for color extraction, color setting circuit 313 for setting the plural colors consisting of the surface part of the object as the extract colors, and color extracting circuit 312 for extracting the image data of image parts corresponding to the extract colors from the wide angle image of the sensor camera. At the color extracting circuit 312, the color information of respective picture elements in the image data is compared with the threshold values of respective extract colors and the part having the big pixel area of continuous extract colors is recognized as the object of photographing target.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an automatic photographing camera capable of measuring the three-dimensional position of a subject to be photographed from an image photographed by using a television camera and automatically tracking the subject for unmanned photographing. The present invention relates to a method of recognizing a subject in a system.

[0002]

2. Description of the Related Art Conventionally, in a camera system which allows a camera operator to automatically track and photograph a subject without directly operating a television camera, the camera system can be rotated in horizontal and vertical directions, and can be rotated from the outside. A shooting camera that can be controlled by a control signal is used, and the shooting camera is driven and controlled according to the movement of the subject. As a method of recognizing a subject, for example, a detection mark is previously attached to a subject (or an object that moves with the subject), and a captured image is processed to recognize the detection mark. Has been adopted.
Then, by driving and controlling the photographing camera so that the recognized subject is located at a predetermined position within the frame of the screen, the subject is tracked and photographed.

[0003]

However, the method of recognizing a subject by previously attaching a detection mark has a problem that the range of automatic recognition is narrow and the recognition target is too small for stable recognition. . On the other hand, the method of recognizing a specific one color as a subject has a problem that it cannot be applied to a place where the object to be photographed cannot be specified such as when the same color exists. In addition, when shooting in a place exposed to sunlight or lighting, a shadow portion is formed on the subject, so the color portion to be recognized becomes small, and stable recognition cannot be performed regardless of which method is used. was there. Further, there is a problem that the subject may not be recognized in some cases because the color changes depending on shooting conditions such as weather and magnification. For example, if the color to be recognized is red, the color seen when it is snowing will be pink, and with clothing composed of red and white, it will be pink when reflected in a small size. As a result, it may become unrecognizable.

The present invention has been made under the circumstances as described above, and an object of the present invention is to stabilize a stationary or moving subject, which is an object of automatic tracking, regardless of shooting conditions such as weather. An object of the present invention is to provide a method of recognizing a subject in an automatic photographing camera system that can recognize the subject.

[0005]

According to the present invention, a subject to be photographed is recognized from a stationary body or a moving body in a photographed image of a sensor camera for photographing a wide-angle image, and the photographing direction is determined by a control signal from the outside. The present invention relates to a method for recognizing a subject in an automatic photographing camera system for driving and controlling a photographing camera capable of controlling camera operation, including automatic tracking of the subject. A plurality of colors forming a part are set in advance as extraction colors, and an image part of each color corresponding to the extraction color or its designated color is extracted from the wide-angle image of the sensor camera, based on the image information of the extraction part. This is achieved by recognizing the subject to be photographed.

Alternatively, a plurality of colors forming the surface portion of the subject are set in advance as extraction colors, and the extraction colors or their designated colors are obtained from the wide-angle image of the sensor camera, and the positional relationship between them is This is achieved by extracting the image portion of each color that satisfies the condition and recognizing the subject to be photographed based on the image information of the extraction portion. Further, the condition of the positional relationship is more effective if the corresponding color part is magnified at a predetermined magnification and whether another corresponding color part is included in the range of the magnifying part. Will be achieved.

Alternatively, a plurality of colors forming the surface of the subject are set in advance as extracted colors, and the extracted color and its mixed color or the designated color of the extracted color and its mixed color are set from the wide-angle image of the sensor camera. This is achieved by extracting the image portion of each corresponding color and recognizing the subject to be photographed based on the image information of the extracting portion.

Further, the set color includes a color which changes depending on the photographing condition;

[0009]

BEST MODE FOR CARRYING OUT THE INVENTION In the present invention, a subject to be photographed is automatically recognized from a wide-angle image photographed by a sensor camera corresponding to the eyes of a camera operator, and the position of the subject in a three-dimensional space is measured. Then, the photographing camera is driven and controlled according to the movement of the subject, so that the subject is automatically photographed. As a method of recognizing a subject, a plurality of colors forming the surface of the subject are used as recognition elements, preset as extraction colors, and all or all extraction colors are specified in advance from the wide-angle image of the sensor camera. The image portion of each color corresponding to the designated color is extracted, and the subject to be photographed is recognized based on the image information of the extraction portions of a plurality of colors. It also corresponds to the extracted color or its designated color,
In addition, by extracting image portions of each color that satisfy the positional relationship with each other, more stable recognition can be performed. Furthermore, by extracting the image part of each applicable color including the mixed color of the extracted color or its designated color, it is possible to cope with the change of color due to the change of environmental conditions only by setting the basic color. There is.

Hereinafter, a preferred embodiment of the present invention will be described in detail with reference to the drawings. First, the overall configuration of the automatic photographing camera system according to the present invention will be described with reference to specific examples.

FIG. 1 shows a schematic structure of an automatic photographing camera system according to the present invention. Two cameras 100 (hereinafter referred to as "sensor cameras") for capturing an object moving in a three-dimensional space are provided. 1 shows an example of a system including two photographing cameras 200. Sensor camera 100
Is a camera corresponding to both eyes of the camera operator, and captures a wide-angle image including the subject 1 to be captured as shown in FIG. Two sensor cameras 100 are used to obtain the three-dimensional position (three-dimensional coordinates) of the subject by the principle of triangulation. For example, when the subject 1 that moves beyond the field of view of the sensor camera 100 is tracked and photographed, a plurality of sensor cameras 100 are used, and in that case, the photographing range (measurement range) is divided and each of them is predetermined. Two units are arranged at the position. The photographing camera 200 includes a drive mechanism unit (pan head) 210 and an image pickup unit 2 capable of adjusting the pan, tilt, zoom, focus, etc. of the camera by a control signal from the outside.
Reference numeral 20 is a camera integrally configured, and by controlling the rotation of the pan axis and the tilt axis, it is possible to take an image of almost the entire space except directly below.

The three-dimensional position measuring apparatus 300 recognizes a subject 1 to be photographed from a stationary body or a moving body in the wide-angle image VD1a (VD1b) photographed by the sensor camera 100 by a recognition method described later. In addition, it is a device that sequentially measures the current position of the subject 1, and indicates the current position (three-dimensional coordinate information) of the subject 1 in the three-dimensional space with the viewpoint of the photographing camera 200 as the origin, and the size of the subject 1. Information (area information of the image extraction portion) and the like are output as measurement information PD. This measurement information PD is input to the data analysis device 500 via the input / output interface.

The data analysis device 500 is a device that analyzes the movement of the subject 1 based on the measurement information PD from the three-dimensional position measuring device 300 and controls the camera work of the photographing camera 200 according to the movement of the subject 1. Yes, drive control unit 400
A drive signal MS is sent out via the to control the camera work of the photographing camera 200. That is, the data analysis device 5
In 00, the current position of the subject 1 is recognized based on the measurement information PD of the three-dimensional position measuring device 300, and
Of the shooting camera 200 (position, azimuth angle, acceleration, etc.) is predicted to predict the movement at the next moment, and the shooting camera 200 is based on this prediction information and information indicating the current direction of the shooting camera 200. Of the pan / tilt angle deviation and the amount of adjustment of the zoom and the like, and outputs drive control data (speed command) Vcom to move to the next operation position of the subject 1.
By controlling the driving of the subject 1, the subject 1 is automatically tracked and photographed.

Further, the data analysis device 500 has a plurality of camera work control modes, and is provided with a function of dynamically switching each control mode according to a change in the situation during photographing, so that the optimum camera work according to the situation is obtained. I am able to shoot at. For example, the size of the visual field is changed according to the position of the subject in the three-dimensional space, or the position of the subject on the screen is changed according to the speed of the subject,
By changing the iris adjustment amount according to the time of day, the camera work control mode can be dynamically switched to take pictures. In addition, when the course in which the subject moves is determined in advance such as athletic competition or automobile competition, the shooting area where the control mode of the camera work is different (for example, the start point of the ski jump competition → the jump point → the landing point). By setting the control parameters for each camerawork and automatically switching the control parameters according to the position of the subject in the shooting space, you can shoot with the optimal camerawork according to the shooting area. I have to.

FIG. 2 shows an example of the arrangement of the sensor camera 100 and the photographing camera 200 in the above-described automatic photographing system. When photographing a ski jumping competition as shown in the same figure, a player who is a subject. The area where 1 moves is the area 2a of the runway from the start point to the jump point at the tip of the jump base, the area 2b from the jump to the landing point, and the area of the slope from the landing point to the stop. 2c, and each moving area portion becomes an imaging area portion (three-dimensional space area). In this system, the entire area can be the target of the automatic shooting, but in FIG. 2, for convenience, a part of the space area portion 2b during the jump is the target of the automatic shooting, and the visual field area of the sensor camera 100 is set to two measurement ranges. The sensor camera 101 (10
1A, 101B) is in charge of three-dimensional measurement of measurement range 1.
An example of the arrangement configuration in the case where the sensor camera 102 (102A, 102B) is in charge of three-dimensional measurement of the measurement range 2 is shown.

Here, even one sensor camera 101 and one sensor camera 102 each have a three-dimensional position (3
However, in this case, for example, the three-dimensional coordinates indicating the position of the subject 1 are calculated based on the detection values of the movement amount and the change amount of the subject 1 when moving between two points. Therefore, there is a drawback that three-dimensional coordinates cannot be obtained at each measurement time point and measurement information cannot be provided in real time. Therefore, in terms of the above points and the processing load of the measuring device, as in this example, 2 in 1 measuring range.
It is preferable to use a single sensor camera.

FIG. 3 shows an example of an apparatus that realizes the present invention. In the above-described automatic photographing camera system, the object is recognized and the three-dimensional position is measured in the three-dimensional position measuring apparatus 300. ing. In FIG. 3, sensor cameras 100 (101A, 101B, 102A, 102)
2) is installed in each measurement range as in the configuration example of FIG. Video signals VD1 (VD1a, VD1b, VD2a, VD taken by each sensor camera 100)
2b) is input to the three-dimensional position measuring device 300, and A / D
It is digitized via the conversion unit 301. The digitized image data is sent to the color space conversion circuit 311 in the subject recognition unit 310.

The subject recognition unit 310 receives the digitized image data (R, G, B) and performs a conversion process on the HSI system color space suitable for color extraction, and a color space conversion circuit 311. A color setting circuit 313 for setting a plurality of colors forming the surface portion of the subject 1 as extraction colors, and image data of the image portion of each color corresponding to the extraction color (or its designated color) from the wide-angle image of the sensor camera. Color extraction circuit 3 for extraction
The image portion of the color is extracted from the wide-angle image of the sensor camera 100. The details of the color extraction method will be described later, and here, the color extraction circuit 312 will be described.
An example of the basic operation of will be described. The color extraction circuit 312 recognizes the subject 1 to be photographed from the digitized image data of the two-dimensional coordinate system for one frame. The object 1 is recognized by, for example, color information (H, S, I) of each pixel of image data.
And thresholds (H, S, I ranges: lower limit threshold to upper limit threshold) of extracted colors (or designated colors set by the numerical values) set by the color setting circuit 313 as subject recognition data. The values are compared and binarized on a pixel-by-pixel basis with "1" inside the threshold and "0" outside the range. At that time, the two-dimensional coordinate system (X,
Pixels of the relevant color are extracted and counted in the Y coordinate system), and the counted value is set as the area S. When there are a plurality of portions of the color, for example, the portion having a large area S is recognized as the subject 1 to be photographed. Here, the above-mentioned extraction processing is performed by the two sensor cameras 100 that image the measurement range.
Of the image data VD1a and VD1b.

In the coordinate calculation circuit 321 in the three-dimensional coordinate measuring section 320, from the area S obtained by the object recognizing section 310,
The center position C of the subject 1 is calculated by calculating the position of the center of gravity of the extracted portion.
(X, y). This center position is calculated from the image data VD1a and VD1b of the two sensor cameras 100, respectively. In the three-dimensional coordinate calculation circuit 322, the position of the subject 1 in the three-dimensional space is calculated from the two center positions C1 (x, y) and C2 (x, y) and the position information of the sensor camera 100 and the photographing camera 200. (3D coordinates of the subject 1 with the viewpoint of the photographing camera 200 as the origin) is calculated by the principle of triangulation, and the calculated 3D position information C (x, y,
z) and information indicating the size of the subject 1 (the above area S) are output as the measurement information PD. This measurement information PD
Is input to the data analysis device 500.

Next, a method of recognizing a subject in the above-described automatic photographing camera system will be described in detail by showing a concrete example. Hereinafter, each of the following first to third embodiments will be described separately.

In the first embodiment, a plurality of colors forming the surface of the object to be photographed are preset as extracted colors including, for example, colors that change depending on the photographing conditions, and the wide-angle image of the sensor camera 100 is used. The image portion of each color corresponding to the extracted color or the designated color thereof is extracted.
That is, the subject to be photographed is recognized by a combination of a plurality of colors. Further, in the second embodiment, the subject to be photographed is recognized based on the positional relationship of a plurality of colors, such as the color b existing near the color a. Further, in the third embodiment, by extracting the set extracted color and its mixed color as the target, the color changing depending on the imaging conditions such as weather and magnification is recognized and recognized. In this case, even if the mixed color is not set as the extraction color in advance, it is automatically (or by command) extracted.

First, the first embodiment will be described.
For example, when the object to be photographed is a skier, the uniform worn by the skier can be recognized. That is, the subject to be photographed can be recognized by recognizing the uniform color composed of a plurality of colors. By the way, in the case of photographing a subject outdoors, such as in a ski competition, the colors of the sunlit part and the shadowed part often differ. Similarly, when photographing indoors, the color of the illuminated portion and the shaded portion often differ. Therefore, in the present invention, each color that is different depending on the light irradiation condition is set separately, and by taking the logical sum thereof, the extraction part is targeted up to the shadow part, so that stable recognition can be performed. ing.

FIG. 4 shows an example of a uniform (recognition target portion) 10 having different colors in the upper part and the lower part. For example, as shown in the same figure, the skier is facing diagonally forward right with respect to the line of sight of the camera, and when the skier 1 is illuminated by light from the rear side (direction of arrow R in the figure) of the uniform 10, In the upper part, the shaded A and shaded B parts are formed, and in the lower part of the uniform 10, the shaded C and shaded D parts are formed. In this example, a total of four colors, namely, two colors A and C of the sun and two colors B and D of the shade are the areas to be recognized. In this case, as shown in FIG.
It is set by the setting means 13 and registered in a table or the like, and the portion of the color is extracted at the time of image extraction and is output as recognition data. Further, as in the example of FIG. 5, by setting attribute information (color of the sun, color of the shade, positional relationship, etc.) together with information indicating the color, mode designation (for example, sunset, clear, cloudy) By specifying a mode such as), it becomes possible to process the color belonging to the mode as an extraction target. For example, as in an example of a first color extraction circuit described later, m (m ≧ 1) patterns are selected and extracted from expected n (n ≧ 2) color combination patterns. By being configured so that it can be made general-purpose.

FIG. 6 shows the extraction result by the conventional color extraction method in the same figure (A), and the extraction result by the color extraction method of the present invention in the same figure (B). Figure 4
If the uniform 10 of the
Although only the color part can be extracted, in the present invention, the entire uniform 10 can be extracted even if the color changes depending on the shooting conditions, and stable object recognition and three-dimensional position measurement can be performed. Become.

FIG. 7 shows an example of a color extracting circuit (first color extracting circuit: hereinafter referred to as "extracted color logical sum circuit") used in the first embodiment, and an extracted color logical sum circuit 312a.
Inputs the signals of the extracted colors (A, B, C, D) set by the color setting circuit 313 together with the image signals, and outputs the command colors (A, B, C, d) by the control signals (a, b, c, d) CS1. C,
The image data of the color corresponding to the (D combination) is output. Here, for simplification of description, a circuit is configured to select and output one pattern designated by the control signal CS1 from the combination patterns of four colors (A, B, C, D). An example is shown. Each bit (a, b, c, d) of the control signal CS1 corresponds to each extraction color (A, B, C, D), and as shown in FIG. 8, "1" is the extraction target, “0” is designated as an extraction target. For example, the recognition target (Uniform 1
In the case of 0), when extracting without including the shaded colors, the control signal in which the value of each bit corresponding to those colors is “1” (in this case, A and C are “1010”) CS1 is input to the extracted color logical sum circuit 312a. The extracted color logical sum circuit 312a calculates the logical sum of the extracted colors according to the value of the control signal CS1 and outputs the image extraction data of the corresponding color (A + C).

Next, a second embodiment will be described.
In the second embodiment, from the wide-angle image of the sensor camera 100, the condition of the mutual positional relationship (for example, those having a close positional relationship or attribute information indicating the positional relationship as shown in FIG.
An image part of a color satisfying the positional relationship (upper, lower, left, right, etc.) is extracted and made a recognition target. Here, in order to simplify the description, a case will be described as an example in which only objects having a close positional relationship between two colors are recognized. For example, as shown in FIG. 9A, the recognition target 10 is composed of an A-color portion 10a and a B-color portion 10b, and the A-color objects 11a and B, which are not recognition targets, are formed around the recognition target 10. The case where the colored object 11b exists is taken as an example. In this example,
In order to detect whether or not there is a B color (A color) around the A color (B color), the extracted regions of the respective colors A and B are magnified by k (k
Is a magnification for obtaining the closeness of the positional relationship), and if there is another color in the expanded area, the area within the expanded range of the other color area is set as the effective area, and the image of the effective area is displayed. I am trying to output the data.

This processing is performed for each set color,
In the example of FIG. 9 (A), as shown in FIGS. 9 (B) and 9 (C), other colors are present in the enlarged range (broken line portion in the figure) of the A-color object 11a and the B-color object 11b. No image data is output because there is no. On the other hand, as shown in FIG.
Since the B-colored portion exists within the enlarged range of the A-colored object 10a, the image data of the B-colored portion within the enlarged range is output. On the other hand, as shown in FIG. 9C, the B-colored object 10b
Since there is an A-colored portion within the enlarged range, the image data of the A-colored portion within the enlarged range is output. Then, the logical sum is calculated, and as shown in FIG. 9D, the image data of the effective portion of A + B is output as the color extraction data. By adopting such a color extraction method, it is possible to extract only the recognition target 10 composed of a plurality of colors such as a uniform pattern, and even if there is an obstacle in the background, the subject is not affected. You will be able to recognize.

FIG. 10 is a circuit for realizing the above-described color extraction method, that is, a color extraction circuit for extracting and outputting a plurality of colors whose positional relationships are close to each other (second color extraction circuit: hereinafter referred to as "neighboring color"). (Referred to as an “extraction circuit”). In order to simplify the description, here, the color data of the recognition target composed of two colors having a close positional relationship is extracted and output. An example is shown. In this case, the color setting circuit 31
By the setting means of 3, the A color and the B color to be extracted and the value indicating the peripheral area of the area of each color, that is, the above-mentioned magnification k,
It is registered in a table or the like as a color extraction parameter.

In FIG. 10, the neighboring color extraction circuit 312b
Input the image data of extraction color A (B),
An enlarging circuit 1a (1b) for enlarging the range of (B) by a magnification k and outputting data (all "1") of the enlarging range;
The image data of the extraction color A (B) is input, and the enlargement circuit 1b is input.
The delay circuit 2a (2 that outputs the image data of the extracted color A (B) with a delay corresponding to the processing time in (1a) (however, outputs "0" when no image data is input))
b), the expansion circuit 1a (1b) and the other delay circuit 2b
An AN which inputs the output data of (2a) and outputs a logical product
It is composed of a D circuit 3a (3b) and an OR circuit 4 which outputs the logical sum of the outputs of the AND circuits 3a and 3b.

An operation example of such a configuration will be described. The image data is subjected to area extraction for each extracted color in advance by a method similar to that of the extracted color logical sum circuit 312a. The data (coordinate information) of the extracted color A is input to the enlarging circuit 1a, the area of the extracted color A is enlarged by the enlarging circuit 1a at the magnification k specified by the color extraction parameter, and the data of the enlarging range (all "1"). ") Is input to the AND circuit 3a. On the other hand, the data of the extracted color B is input to the enlarging circuit 1b, and similarly, the area of the extracted color B is enlarged by the enlarging circuit 1b at the magnification k, and the data of the enlarged range is AND circuit 3b.
Is input to On the other hand, the data of the extracted color A input to the delay circuit 2a is held until the end of the enlargement processing operation in the enlargement circuit 1b, and then input to the AND circuit 3b. The data of the extracted color B input to the delay circuit 2b is held until the end of the enlargement processing operation in the enlargement circuit 1a, and then input to the AND circuit 3a.

Enlargement circuit 1a input to AND circuit 3a
The output data of the delay circuit 2b is input to the OR circuit 4 when the logical product of the output data of the delay circuit 2b and the output data of the delay circuit 2b is true, that is, when the data of the extracted color B exists. Similarly, the AND circuit 3b causes the expansion circuit 1b and the delay circuit 2 to operate.
The output data of a is ANDed, and when true, the output data of the delay circuit 2a is input to the OR circuit 4. And
The OR circuit 4 takes the logical sum of the outputs of the AND circuits 3a and 3b, and in this example, the image data of the effective portion of A + B is output as color extraction data.

Next, a third embodiment will be described.
In the third embodiment, the set extraction color and the mixed color thereof are extracted as a target, and the color that changes depending on the imaging conditions such as weather and magnification is recognized and recognized. For example, when the color of the recognition target is red, the color seen when it is snowing becomes pink. If the color set as the recognition target is used as it is, the subject cannot be recognized in some cases. In the first or second embodiment, there is no problem when pink, which is a mixed color, is set as the extraction color, but the setting process becomes complicated. Therefore, in the third embodiment, the set extraction colors are set to A, B,
In the case of C and D, the extracted colors A, B, C and D (or their designated colors) and their mixed colors C1 to Cn (2 of A, B, C and D)
A combination of four colors) is automatically set as an extraction target (or is additionally set in a table or the like by automatic setting), and the mixed colors are set as A, B, and C1 to Cn as recognition target colors.

Further, by arranging such that an arbitrary pattern can be selected and designated from the combination color mixture patterns by an external control signal, only the color estimated to have changed is automatically designated and extracted. It becomes possible to do. For example, the recognition targets C1 to Cn according to the magnification and time at the time of color extraction
By selecting and deciding the extracted color from among the above, and sending the control signal of the pattern to the color extracting circuit, only the color is extracted.

FIG. 11 is a circuit for realizing the above-described color extraction method, that is, a set extraction color (or its designated color) and its mixed color (or its designated color) are extracted, and an image of the color is extracted. Color extraction circuit that outputs data (third color extraction circuit: hereinafter referred to as "extracted color / mixed color extraction circuit")
An example is shown. In FIG. 11, the extracted color / mixed color extraction circuit 312c includes a color setting circuit 313 together with an image signal.
The signals of the extraction colors (A, B, C, D) set in step 3 are input, and the command colors (A, B, c, d) based on the control signals (a, b, c, d) are input.
The image data of the color corresponding to the combination of B, C, and D) is output. For example, the control signal CS1
A, b, and c of each bit are on, and m of the control signal CS2
When each bit of a and mc is on, image data of each color of A, B and C and the color corresponding to the color mixture of A and C are output. The degree of color mixture may be commanded. Here, what is meant by the color mixture of the A color and the B color will be described. The color A by the value of HSI system _{(H A, S A, I} A) to. Let B color be the value of HSI system (H _B , S _B , I _B ). At this time, the color mixture of the colors A and B (H _C , S _C , I _C ) is H _C = pH _A + (1-
p) H _B , S _C = pS _A + (1-p) S _B , I _C = pI
_{A + (1-p) I} B becomes, and 0 ≦ p ≦ 1. This p
Is called a value representing the degree. In this case, the internal division point in the HSI color space of two colors is used as the color mixture, but it is also possible to measure the mixed color of the implementation with a camera and create a table to create a unique nonlinear internal division equation.

In the above-described embodiment, the case where the invention is applied to the automatic photographing camera system equipped with the sensor camera has been described as an example, but a general system such as a system for tracking an object using only the photographing camera is used. The present invention can be applied as a method of recognizing a subject in the system.

[0036]

As described above, according to the object recognition method in the automatic photographing camera system of the present invention,
A plurality of colors forming the surface part of the subject are set as recognition elements in advance as extraction colors, and the image part of each color corresponding to the extraction color or its designated color is extracted from the wide-angle image of the sensor camera to extract the plurality of colors. Since the subject to be photographed is recognized based on the image information of the part, the range of application of automatic recognition is widened, and the recognition target part can be made larger than the conventional method, which is stable. You will be able to recognize. Further, since it is possible to target the extracted colors including the color that changes depending on the shooting conditions such as the weather, the magnification, and the time, it is possible to stably recognize the colors regardless of the shooting conditions such as the weather. Further, by extracting the image portion of each color corresponding to the extracted color or the designated color thereof and satisfying the positional relationship with each other, more stable recognition can be performed. Furthermore, by extracting the image part of each applicable color including the extracted color (or its designated color) and its mixed color (or its mixed color), it is possible to set the basic color just by setting the basic color. Will be able to respond to changes in.

[Brief description of drawings]

FIG. 1 is a block diagram showing a schematic configuration example of an automatic photographing camera system according to the present invention.

2 is a diagram showing a sensor camera 100 and a photographing camera 20 of FIG.
It is a figure which shows an example of an arrangement configuration of 0.

FIG. 3 is a block diagram showing an example of an apparatus that realizes the present invention.

FIG. 4 is a diagram showing an example of a recognition target in the present invention.

FIG. 5 is a diagram for explaining a setting example of colors forming a recognition target in the present invention.

FIG. 6 is a diagram for explaining the difference in color extraction method between the first embodiment of the present invention and the conventional technique.

FIG. 7 is a diagram showing a configuration example of a color extraction circuit in the first embodiment of the present invention.

FIG. 8 is a diagram for explaining an operation example of the color extraction circuit of FIG.

FIG. 9 is a diagram for explaining the second embodiment of the present invention.

FIG. 10 is a diagram showing a configuration example of a color extraction circuit according to a second embodiment of the present invention.

FIG. 11 is a diagram showing a configuration example of a color extraction circuit according to a third embodiment of the present invention.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 subject 10 recognition target part 100 sensor camera 200 photographing camera 210 driving mechanism part (head) 220 imaging part 300 three-dimensional position measuring device 310 subject recognition part 311 color space conversion circuit 312 color extraction circuit 312a extraction color logical sum circuit 312b Neighborhood color extraction circuit 312c Extracted color / mixed color extraction circuit 313 Color setting circuit 320 Three-dimensional coordinate measurement unit 321 Coordinate calculation circuit 322 Three-dimensional coordinate calculation circuit 400 Drive control unit 500 Data analysis device

[Procedure amendment]

[Submission date] June 14, 1996

[Procedure amendment 1]

[Document name to be amended] Drawing

[Correction target item name] All figures

[Correction method] Change

[Correction contents]

FIG.

[Fig. 2]

[Figure 3]

[Figure 5]

FIG. 6

FIG. 4

FIG. 7

[Figure 8]

[Figure 9]

FIG. 10

FIG. 11

Front page continuation (72) Inventor Kazuo Abe 1-10-11 Kinuta, Setagaya-ku, Tokyo Inside the Japan Broadcasting Corporation Broadcasting Technology Laboratory (72) Inventor Akio Ishikawa 1-1-10 Kinuta, Setagaya-ku, Tokyo Within the Institute of Broadcasting Technology of the Japan Broadcasting Corporation (72) Inventor Shigezumi Kuwashima 3-26-12 Kita-Sentsu, Ota-ku, Tokyo Inside the Applied Measurement Laboratory, Inc. (72) In-house Takato Suzuki 3-26 Kita-Senka, Ota-ku, Tokyo No. 12 Inside Applied Measurement Laboratories, Inc. (72) Inventor Toru Nakamura 3-26-3 Kita-Senka, Ota-ku, Tokyo No. 12 In-house Applied Measurement Laboratories, Inc. (72) Hiroyuki Kuwahara 3-26 Kita-Senka, Ota-ku, Tokyo No. 12 Applied Research Institute, Inc.

Claims (5)

[Claims] 1. A camera operation including a photographing direction can be controlled by recognizing a subject to be photographed from a stationary body or a moving body in a photographed image of a sensor camera for photographing a wide-angle image, and a control signal from the outside. In a method of recognizing a subject in an automatic photographing camera system for driving and controlling a photographing camera to perform photographing by automatic tracking of the subject, a plurality of colors forming a surface portion of the subject are preset as extraction colors, and Automatic shooting characterized by extracting an image portion of each color corresponding to the extracted color or its designated color from a wide-angle image of a sensor camera, and recognizing the subject to be shot based on image information of the extracting portion A method for recognizing a subject in a camera system. 2. A camera operation including a shooting direction can be controlled by recognizing an object to be shot from a stationary body or a moving body in a captured image of a sensor camera which captures a wide-angle image, and controlling a camera from an external control signal. In a method of recognizing a subject in an automatic photographing camera system for driving and controlling a photographing camera to perform photographing by automatic tracking of the subject, a plurality of colors forming a surface portion of the subject are preset as extraction colors, and From the wide-angle image of the sensor camera, the image portion of each color that corresponds to the extracted color or its designated color and satisfies the positional relationship with each other is extracted, and the subject to be photographed is recognized based on the image information of the extraction portion. A method of recognizing a subject in an automatic photographing camera system, characterized by the above. 3. The condition of the positional relationship is a condition of enlarging the image portion of the corresponding color of interest by a predetermined magnification and determining whether or not an image portion of another corresponding color is included in the range of the enlargement portion. The object recognition method in the automatic photographing camera system according to claim 2. 4. A camera operation including a photographing direction can be controlled by recognizing a subject to be photographed from a stationary body or a moving body in a captured image of a sensor camera which captures a wide-angle image, and a control signal from the outside. In a method of recognizing a subject in an automatic photographing camera system for driving and controlling a photographing camera to perform photographing by automatic tracking of the subject, a plurality of colors forming a surface portion of the subject are preset as extraction colors, and An image part of each color corresponding to the extracted color and its mixed color or the designated color of the extracted color and its mixed color is extracted from the wide-angle image of the sensor camera, and the subject to be photographed is recognized based on the image information of the extraction part. A method of recognizing a subject in an automatic photographing camera system characterized by the above. 5. The method for recognizing an object in an automatic photographing camera system according to claim 1, wherein the set color includes a color that changes depending on photographing conditions.