JP2001285850A - Device and method for automatic following, and recording medium for recording automatic following program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an automatic following device which is capable of zooming up even to a moving object and following it efficiently. SOLUTION: The device is provided with a picture input means, a turning means for turning the picture input means in a bi-axial direction, a following object extracting means for extracting an object to be the object of following from a picture, a position storing means for transforming the positions of the following points of the object at different times to positions on absolute coordinates by using the pan tilt angle of the turning means and the zooming power of the picture input means to store them time serially and retransforming the stored position of the following points to camera coordinates, a position estimating means for estimating the moving position of the object, a velocity calculating means for calculating the moving velocity of the object, a turning control means for controlling the pan tilt angle from the estimated moving position and the moving velocity, an object moving area calculating means for calculating the area of a space to be swept on the camera coordinates by moving of the following object, and a zooming control means for controlling the zoom power of the picture from the moving space area of the following object.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an automatic tracking technique for tracking an object in an image input from a surveillance camera or the like by an imaging device having a turning function, and more particularly to an automatic tracking device that is robust to the movement of an object. , An automatic tracking method, and a recording medium on which an automatic tracking program is recorded.

[0002]

2. Description of the Related Art Conventionally, an automatic tracking system of this kind extracts a target object from an image taken by a monitoring camera or the like installed in a turning device, and turns the extracted object so as to always fit in the image. Tracking is performed by controlling the pan / tilt angle of the device. An example of a conventional automatic tracking system is described in Japanese Patent Application Laid-Open No. H10-210343. The automatic tracking system described in this publication extracts an object to be tracked from an output image of an imaging device, converts the displacement of the object from the image center into an angular velocity command of a pan / tilt rotation device, and extracts the object. Means for converting a size difference between the size of the object on the image and the set target size into a zoom operation command.

[0003]

However, the tracking device according to the prior art performs control using only the position information on the screen of the object in the tracking in the pan / tilt rotation, so that the tracking of the moving object is performed. There is a problem that it cannot be performed with high accuracy. For example, as shown in FIG. 11, consider a case where an object is located at the edge of the screen and is facing the center of the screen. In the state where the control parameters are set so that the camera pan is operated so that the object at the edge of the screen is captured in the center of the screen, the object is located at the edge of the screen as shown in FIG. When moving, when performing the same control as in the case of FIG. 11, the object cannot be captured in the center of the screen, and when the movement of the object is large, the object may deviate from the angle of view. That is, in the method of tracking an object only at the position on the screen, there is a problem that stable tracking cannot be performed depending on the size and direction of movement of the object.

In a zoom control method in which the size of an object on an image is kept constant, the zoom control amounts of a stopped object and a moving object are the same, as shown in FIG. Since the apparent amount of movement on the image increases as the object zooms in, the object that moves at a high speed tends to deviate from the angle of view, and the tracking of the moving object is difficult even when using zoom control. There is a problem that it cannot be performed stably.

The present invention has been made in view of such circumstances, and enables an automatic tracking apparatus that can perform zoom-up even for a moving object without deteriorating the stability of tracking, and that can track with high accuracy. It is an object of the present invention to provide a recording medium recording an automatic tracking method and an automatic tracking program.

[0006]

According to the present invention, there is provided an automatic tracking apparatus for tracking an object using a captured image, wherein the automatic tracking apparatus needs to track the object. Image input means having a camera for obtaining an image of an area, turning means for turning the image input means in two axial directions based on the input pan / tilt angle control amount, and image obtained by the image input means A tracking object extracting means for extracting an object to be tracked from, and converting a position of a tracking point of the tracking target object at a different time into a position on absolute coordinates using the pan / tilt angle of the turning means. Position storage means for storing a plurality of tracking points stored in chronological order, converting the stored positions of the tracking points again into camera coordinates and outputting the coordinates, and estimating the position of the object based on the positions of the tracking points of the past object. Means and things of the past Speed calculating means for calculating the moving speed of the object from the position of the tracking point, and turning control means for controlling a pan / tilt angle of the turning means based on the estimated moving position and the moving speed. And

According to a second aspect of the present invention, there is provided an automatic tracking apparatus for tracking an object using a captured image, wherein the automatic tracking apparatus obtains an image of a region where the object needs to be tracked. An image input unit provided with a camera; and an image input unit based on the input pan / tilt angle control amount.
Turning means for turning in the axial direction, tracking object extracting means for extracting an object to be tracked from an image obtained by the image input means, and a position of a tracking point of the object to be tracked at a different time, Using the pan / tilt angle of the means and the zoom magnification of the image input means, convert to absolute coordinates and store them in chronological order, and convert the stored multiple tracking points to camera coordinates again for output. Position estimating means for estimating the moving position of the object from the position of the tracking point of the past object; speed calculating means for calculating the moving speed of the object from the position of the past object tracking point; Panning of the turning means based on the moving position and the moving speed
Turning control means for controlling a tilt angle, object moving area calculating means for calculating an area of an area swept on camera coordinates by movement of a tracking object, and controlling a zoom magnification of the image input means from the moving area area of the tracking object. And a zoom control unit that performs the control.

According to a third aspect of the present invention, there is provided an automatic tracking method for tracking an object using a captured image, wherein the automatic tracking method determines a position of a tracking point of an object to be tracked at different times. By using the pan / tilt angle of the image input means, the position is converted to a position on absolute coordinates and stored in chronological order, and the stored positions of the plurality of tracking points are converted again to camera coordinates and output. The position of the object is estimated from the position of the tracking point of the object, and the moving speed of the object is calculated, and the pan / tilt angle of the image input means is controlled from the estimated position and the moving speed.

According to a fourth aspect of the present invention, there is provided an automatic tracking method for tracking an object using a captured image, wherein the automatic tracking method determines a position of a tracking point of an object to be tracked at different times. Using the pan / tilt angle and the zoom magnification of the image input means, the position is converted to a position on absolute coordinates and stored in chronological order, and the stored positions of the plurality of tracking points are again converted to camera coordinates and output. Estimating the moving position of the object and calculating the moving speed of the object from the position of the tracking point of the past tracked object, controlling the pan / tilt angle of the image input means from the estimated position and the moving speed, It is characterized in that the area of a region to be swept on the camera coordinates by movement is calculated, and the zoom magnification is controlled from the area of the moving region of the tracking object.

According to a fifth aspect of the present invention, there is provided a computer-readable recording medium having recorded thereon an automatic tracking program for performing tracking by using a captured image, wherein the automatic tracking program is configured to perform tracking of tracking objects at different times. The position of the tracking point of the object is converted into a position on absolute coordinates using the pan / tilt angle of the image input means and stored in time series, and the stored positions of the plurality of tracking points are converted into camera coordinates again. Converting and outputting, estimating the moving position of the object and calculating the moving speed of the object from the position of the tracking point of the past object, and controlling the pan / tilt angle of the image input means from the estimated position and the moving speed. Is performed by a computer.

According to a sixth aspect of the present invention, there is provided a computer-readable recording medium having recorded thereon an automatic tracking program for performing tracking by using a captured image, wherein the automatic tracking program is configured to perform tracking of an object to be tracked at different times. The position of the tracking point of the object is converted into a position on absolute coordinates using the pan / tilt angle and the zoom magnification of the image input means and stored in chronological order, and the stored positions of the plurality of tracking points are stored in the camera. The coordinates are again converted and output, and the moving position of the object is estimated and the moving speed of the object is calculated from the position of the tracking point of the past tracked object, and the pan / tilt angle of the image input means is calculated from the estimated position and the moving speed. Calculating the area of the area swept on the camera coordinates by the movement of the tracking object, and controlling the zoom magnification from the area of the movement area of the tracking object. .

[0012]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an automatic tracking device according to an embodiment of the present invention will be described with reference to the drawings. FIG. 1 is a block diagram showing the configuration of the first embodiment. In this figure, reference numeral 1 denotes an image input device constituted by a CCD camera or the like, and the captured image is a moving image.
Reference numeral 3 denotes a turning device for turning the image input device 1 in two axes, up and down and left and right. Reference numeral 4 denotes an image output device that displays an image acquired by the image input device 1. Code 5
Is a tracking object extracting unit that extracts a region of a tracking target object from an image acquired by the image input device 1. Code 7
Calculates the position of the tracking point from the object area of the tracking target extracted by the tracking object extracting means 5, further obtains the pan / tilt angle from the turning device 3, and converts the position of the tracking point into a position on absolute coordinates. This is a position storage unit that stores the tracking points at a plurality of absolute coordinates stored in the memory and converts the stored positions to the camera coordinates again using the pan / tilt angles obtained from the turning device 3 and outputs the converted positions. Reference numeral 8 denotes a speed calculating unit that calculates the moving speed of the tracking point from the positions of the plurality of tracking points output from the position storage unit 7. Reference numeral 9 denotes position estimating means for estimating the tracking point position of the tracked object at the next time from the positions of the plurality of tracking points output from the position storage means 7. Reference numeral 10 denotes a turning device control unit 10 that determines a pan / tilt control amount of the turning device 3 from the tracking point position and the moving speed output from the speed calculating unit 8 and the position estimating unit 9.

Next, the overall operation of this embodiment will be described in detail with reference to FIG. First, the tracking object extracting unit 5 extracts a region of a target object to be tracked from an image captured by the image input device 1. An existing method using background difference and template matching will be described as a method for determining and extracting a tracking object. First, in a state where the pan / tilt turning device 3 is stopped, an intruding object is detected using the existing background subtraction method. In the background subtraction method, an image containing no object to be detected is stored in advance as a background image f (x, y), and a difference image h (x) between the input image g (x, y) and the luminance value of the background image is stored. , Y) = | g (x, y) −f (x, y) |. Further, by binarizing the gradation value of h (x, y) with a certain threshold value, it is possible to detect an intruding object region when an object that is not in the background image enters.

Here, tracking is performed with the detected intruding object as an object to be tracked. The area of this intruding object is circumscribed by a circumscribed rectangle, and its upper left coordinate is represented by (x1, y1) and its lower right coordinate is represented by (x2, y2). This (x1, y
1) The image of the object region represented by (x2, y2) is stored as an initial template t (x, y). Based on this template, an object to be tracked is extracted from an input image that changes due to pan / tilt turning using template matching.

The template matching means that the input image g
In this method, a position having the highest similarity to the template image t (x, y) is searched from (x, y). "Introduction to Computer Image Processing" for how to calculate template matching
Supervised by Hideyuki Tamura, Soken Publishing (ISBN4-7952-6)
304-3) Details on p149. Since the size or the shape of the object on the image changes as the tracking object moves or changes its direction, the tracking object in the input image may not match the template image, which may make it difficult to extract the object.
Therefore, in order to cope with a change in size, a plurality of templates having a size obtained by enlarging and reducing the template are prepared in advance, and template matching is performed using the plurality of templates, and the template size and position at which the similarity becomes the largest are obtained. To determine. In order to cope with a change in the shape of the object, an image of the template size is cut out from a position determined to have the highest similarity in the input image and stored as a new template. This makes it possible to extract a tracking object whose size and shape gradually changes in the input image.

An existing motion vector may be used for object extraction. In this method, motion in an image is represented by a vector, clustering is performed on blocks containing vectors in similar directions, and the largest block excluding a large background area caused by camera movement is regarded as a moving object area. Extract as a moving object. A circumscribed rectangle of the extracted area is obtained, and its upper left coordinates (x1, y1) and lower right coordinates (x
2, y2). The motion vector calculation method is described in "Processing and Recognition of Images" by Takeshi Akuin and Tomoharu Nagao, Shokodo P.
164 (ISBN4-7856-9043-7).

The position storage means 7 first extracts points representative of the area of the object extracted by the tracking object extraction means 5 as tracking points. As a tracking point extraction method, when a tracking object is extracted using template matching, an average of upper left coordinates (x1, y1) and lower right coordinates (x2, y2) of the template rectangle at the extracted position is taken. The center pixel ((x1
+ X2) / 2, (y1 + y2) / 2) are calculated as tracking points. In applications where only people are tracked,
In some cases, tracking the head is more convenient than tracking the center of the person area. In this case, the tracking point is not at the center pixel of the template but at the upper part of the template, for example, at a position at 80% height ((x1 + x2) / 2, (4 × y1 + y2)).
/ 5) may be selected as the tracking point. When the area of the tracking object is extracted by the motion vector, the center of gravity of the tracking object area may be selected as the tracking point, or the center of the circumscribed rectangle of the object may be selected.

Next, the position storage means 7 obtains a pan angle corresponding to the horizontal turning angle and a tilt angle corresponding to the vertical turning angle from the turning device 3 and obtains the image input device 1 obtained in advance. From the angle of view (viewing angle), the position of the extracted tracking point is temporarily converted to a position on absolute coordinates. As a method for converting a tracking point into a position on absolute coordinates, polar coordinates represented by pan / tilt angles are used as absolute coordinates as shown in FIG.

Here, the point Oc at the center of the camera image (the origin of the camera coordinates) can be expressed by equation (1) when expressed by a pan / tilt angle. Similarly, the point P on the image can be expressed as the equation (2) by the pan / tilt angle.

(Equation 1)

(Equation 2)

Where f is the focal length of the lens system [mm]
Where x and y are positions [mm] on the camera image plane (CCD element plane), and the position on the image plane is calculated from the size and the number of pixels of the camera image sensor CCD. If x, y << f, it can be represented by linear approximation as in equation (3).

(Equation 3)

By using this transformation, as shown in FIG. 4, the position of an arbitrary point on the camera coordinates can be represented by polar coordinates using the pan / tilt angle, and the position of the tracking point of the object in absolute coordinates Can be grasped.

Next, the positions of the tracking points converted on the absolute coordinates are stored in time series. Since there is a limit on the memory to be stored, only the positions of N (N ≧ 2) tracking points are stored. When storing the position of the new tracking point, the position of the oldest tracking point is deleted, and the position of the new tracking point is added.

Finally, as shown in FIG. 5, the positions of the N tracking points stored in this memory are again determined by using the equation (4) according to the pan / tilt angle from the turning device 3. Convert to a position on camera coordinates and output. That is, the stored positions of the N tracking points are virtually reproduced on an arbitrary camera line of sight, and the positions of the tracking points converted into camera coordinates need to be within the camera view angle. There is no.

(Equation 4)

The speed calculating means 8 calculates the moving speed V from the N tracking point positions output from the position storage means 7. As shown in FIG. 6, assuming that the movement of the object is linear on the camera coordinates, the moving speed V is calculated using the current tracking point position G0 and the tracking point position G1 one unit time ago (5).
It is obtained by the formula.

(Equation 5)

The position estimating means 9 estimates the tracking point position Obj at the next time from the N tracking point positions output from the position storage means 7. The tracking point estimation position can be determined from the past N positions using extrapolation using a polynomial or extrapolation using a rational function. These are described in "Numerical Recipes in Sea" Technical Review, William H.S. Press, S
aul A. Teukolsky, William
T. Vetterling, Brian P .;
By Frankery, Dankatsu Katsuichi, Haruhiko Okumura, Toshiro Sato,
Translated by Makoto Kobayashi 96 (ISBN4-87408-56
0-1). When N = 2, assuming that the current tracking point position is G0 and the tracking point position one unit time ago is G1 (6)
It is obtained by the formula.

(Equation 6)

The turning device control means 10 includes a speed calculation means 8
An appropriate pan / tilt control value is calculated from the moving speed calculated in step (1) and the position of the tracking point at the next time estimated by the position estimating means 9 so that the tracking object (tracking point) can be captured at the center of the image. The shift (Δx, Δy) between the estimated position of the tracking point at the next time and the center of the image is calculated, and feedback control is performed so that the shift becomes zero. For the pan / tilt control amount, as shown in FIG. 7, the pan movement angular velocity is calculated from the x coordinate deviation Δx, and the tilt movement angular velocity is calculated from the y coordinate deviation Δy. At this time, if the deviation (Δx, Δy) is smaller than the minimum movement amount of the pan / tilt on the image, the object cannot be captured at the center of the image, causing an overshoot (overshoot) and unstable control ( Vibrates).

For this reason, the minimum movement amount (Pmin, Tmin) on the image is calculated in advance from the angle of view of the image input device 1 and the minimum control amount of pan and tilt, and the deviation (Δx, Δy) is calculated by -If the tilt is smaller than the minimum movement amount, do not perform the pan or tilt operation. Further, based on the moving speed (vector) of the object obtained from the speed calculating means 8, the control amount of pan / tilt is changed depending on whether the object is moving toward the center of the image or away from the center of the image. be able to. Since an object moving away from the center of the image may deviate from the angle of view, it is necessary to perform quick pan / tilt control before deviating from the angle of view.

However, since there is little danger of the object coming toward the center of the screen deviating from the angle of view, the control is made as gentle as possible. That is, it is not necessary to move the tracking point to the center of the image by one pan / tilt control, and it is sufficient to perform gentle control so that the tracking point gradually approaches the center of the image by several controls. As a result, it is possible to provide a tracking image that does not cause a sudden movement of the object in the image and does not cause discomfort to the observer.

As described above, the positions of a plurality of tracking points of an object to be tracked at different times are converted into positions on absolute coordinates using pan / tilt angles and stored, and the positions of these tracking points are determined. Again, by converting the current pan / tilt angle to camera coordinates, the position of the tracking point at the next time is estimated,
The moving speed can be calculated, and the pan / tilt control is performed using these values. Therefore, tracking can be performed smoothly without losing the object according to the position and speed of the object.

Next, a second embodiment of the present invention will be described in detail with reference to the drawings. FIG. 2 is a block diagram showing the configuration of the second embodiment. In this figure, the same parts as those of the apparatus shown in FIG. 1 are denoted by the same reference numerals, and description thereof will be omitted. Reference numeral 2 denotes a zoom driving device including an electric zoom lens mounted on the image input device 1,
By operating the zoom lens, the angle of view of the image input device 1 can be controlled. The swivel device 3 enables the user to swing with the image input device 1 in two axes, up and down and left and right. Reference numeral 6 denotes an angle-of-view referencing unit that refers to the angle-of-view information of the image input device 1 that is set in advance by a zoom value. Reference numeral 11 denotes an object moving area calculating unit that calculates an area on a screen that is swept by moving an object in a unit time based on the area of the object region extracted by the tracking object extracting unit 5 and the moving speed output from the speed calculating unit 8. It is. Symbol 12 is
This is a zoom control unit that determines the amount of zoom operation from the object movement area calculation unit 11. The device shown in this figure is different from the device shown in FIG. 1 in that a zoom driving device 2, an angle-of-view referencing device 6, an object moving area calculating device 11, and a zoom controlling device 12 mounted on the image input device 1 are further provided. It is a point that is.

Next, the overall operation of the present embodiment will be described in detail with reference to FIG. First, the angle of view reference means 6
Acquires a zoom value from the zoom drive device 2 and outputs angle-of-view information corresponding to the obtained zoom value. The zoom value is a value corresponding to the focus value f of the zoom lens of the zoom driving device 2, and a combination of the zoom value and the corresponding angle of view of the image input device 1 is stored in a memory or the like in advance. Since the number of combinations of the zoom value and the angle of view to be stored in advance is limited due to the limitation of the memory or the like, only the main combinations may be stored, and the rest may be approximated by interpolation.

Next, the position storage means 7 extracts a point representing the area of the object extracted by the tracking object extracting means 5 as a tracking point, acquires a pan / tilt angle from the turning device 3, and obtains a view angle reference means. 6, the angle of view of the image input device 1 is acquired, the extracted tracking point position is temporarily converted into a position in absolute coordinates, and stored in chronological order. Is converted again into a tracking position in camera coordinates using the pan / tilt angle from.

The object moving area calculating means 11 calculates an area S swept on the screen by the movement of the object in a unit time as shown in FIG. In the case of approximating the rectangle by simplifying the object area, the object is set to the width W and the height H, and the moving speed vector is set to V
Assuming that (Vx, Vy), the object moving area S is obtained as the equation (7).

(Equation 7)

The zoom control means 12 controls a zoom operation based on the moving area area calculated by the object moving area calculating means 11. As a zoom control method, it is determined in advance how much the object is to be zoomed in on the image, and the object area at this time is registered as a set area S0 so that the moving area area S of the tracking object becomes S0. Performs zoom feedback control. That is, when S-S0> 0, the control signal is sent to the zoom operation device 2 to perform zoom-out, and when S-S0 <0, to perform zoom-in. Where S ≒ S
In order to prevent the zoom control from becoming unstable due to a small change in the object area S at 0, as shown in FIG. 9, when the deviation from the set area is equal to or less than a threshold value TH, the zoom control is performed. If not performed, the obtained image is also stable, and the electric zoom device need not be driven unnecessarily.

Further, when an object to be tracked is extracted by template matching in the tracking object extracting means 5, it is better to limit the zoom speed in accordance with the template update speed. This is because it is difficult to extract an object if the amount of change in zoom is larger than the allowable range of change with respect to size in template matching (Zoom_Max shown in FIG. 9).

As for zoom-in, as shown in FIG. 10, a zoom-in area is set in advance on the screen, and when the tracking point (Gx, Gy) of the object is located in the area (( Only when the expression 8) is satisfied), zoom-in control is performed. This is because, when the object is away from the center of the screen, the zoom-in may cause the tracked object to deviate from the angle of view.

(Equation 8)

As described above, the positions of the tracking points of the tracking object at different times are converted into the positions on the absolute coordinates by using the pan / tilt / zoom values and stored, and the positions of the plurality of tracking points are panned again. By converting the tilt angle to the current camera coordinates, the position of the tracking point at the next time can be estimated, the moving speed can be calculated, and the area of the moving area of the object can be calculated from this and the object area. Since these values are used to perform pan / tilt and zoom control, the pan / tilt control according to the position / speed of the tracking target object and the zoom ratio according to the position / speed / size of the tracking target object By adjusting, it is possible to perform tracking with zoom up without losing sight of the object.

A program for realizing the configuration shown in FIGS. 1 and 2 is recorded on a computer-readable recording medium, and the program recorded on this recording medium is read by a computer system and executed to automatically execute the program. Tracking processing may be performed. Here, the “computer system” includes an OS and hardware such as peripheral devices. "Computer system"
If a WWW system is used, this also includes a homepage providing environment (or display environment). The “computer-readable recording medium” means a portable medium such as a floppy (registered trademark) disk, a magneto-optical disk, a ROM, a CD-ROM, and a storage device such as a hard disk built in a computer system. . Further, the “computer-readable recording medium” refers to a volatile memory (RAM) inside a computer system that becomes a server or a client when a program is transmitted through a network such as the Internet or a communication line such as a telephone line. And those holding programs for a certain period of time.

The above program may be transmitted from a computer system storing the program in a storage device or the like to another computer system via a transmission medium or by a transmission wave in the transmission medium. Here, the "transmission medium" for transmitting a program refers to a medium having a function of transmitting information, such as a network (communication network) such as the Internet or a communication line (communication line) such as a telephone line. Further, the program may be for realizing a part of the functions described above. further,
What can implement | achieve the function mentioned above in combination with the program already recorded on the computer system, and what is called a difference file (difference program) may be sufficient.

[0040]

As described above, according to the present invention, the moving speed of an object to be tracked in any camera line of sight can be obtained by converting the object position at different times into a position on absolute coordinates and storing it. And the predicted position of the object is calculated, and the pan / tilt is controlled according to the direction of the position / movement speed, so that pan / tilt tracking can be performed according to the position and movement speed of the object. Even if the reversal of the direction occurs, an effect is obtained that tracking can be performed smoothly and accurately without losing sight.

Further, according to the present invention, the object positions at different times are converted into absolute coordinate positions and stored, whereby
Since the zoom is controlled according to the area of the moving area swept by the object to be tracked even in an arbitrary camera line of sight, tracking can be performed by zooming up according to the moving speed of the object. In tracking, tracking is performed with zoom-up suppressed so as not to be overlooked, and the effect of automatically zooming-up tracking of an object with little motion can be obtained.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a first exemplary embodiment of the present invention.

FIG. 2 is a block diagram showing a configuration of a second exemplary embodiment of the present invention.

FIG. 3 is an explanatory diagram showing an operation of the first exemplary embodiment of the present invention.

FIG. 4 is an explanatory diagram showing an operation of the first exemplary embodiment of the present invention.

FIG. 5 is an explanatory diagram showing an operation of the first exemplary embodiment of the present invention.

FIG. 6 is an explanatory diagram showing an operation of the first exemplary embodiment of the present invention.

FIG. 7 is an explanatory diagram showing an operation of the first exemplary embodiment of the present invention.

FIG. 8 is an explanatory diagram showing an operation of the second exemplary embodiment of the present invention.

FIG. 9 is an explanatory diagram showing the operation of the second exemplary embodiment of the present invention.

FIG. 10 is an explanatory diagram showing an operation of the second exemplary embodiment of the present invention.

FIG. 11 is an explanatory diagram showing a tracking operation according to a conventional method.

FIG. 12 is an explanatory diagram showing a tracking operation according to a conventional method.

FIG. 13 is an explanatory diagram showing a tracking operation according to a conventional method.

[Explanation of symbols]

 DESCRIPTION OF SYMBOLS 1 ... Image input device, 2 ... Zoom drive device, 3 ... Turning device, 4 ... Image output device, 5 ... Tracking object extraction means, 6 ... View angle reference means, 7 ··· Position storage means ·············································································································································································································

Claims (6)

[Claims] 1. An automatic tracking device that performs tracking of an object using a captured image, wherein the automatic tracking device includes a camera that acquires an image of an area where the object needs to be tracked. Turning means for turning the image input means in two axial directions based on the input pan / tilt angle control amount; and tracking object extraction for extracting an object to be tracked from an image obtained by the image input means. Means, the position of the tracking point of the object to be tracked at different times is converted to a position on absolute coordinates using the pan / tilt angle of the turning means, and stored in chronological order; Position storage means for converting the position of the tracking point into camera coordinates again for output, position estimating means for estimating the moving position of the object from the position of the past object tracking point, and object from the position of the past object tracking point Travel speed A speed calculation means for calculating, automatic tracking apparatus being characterized in that and a turning control means for controlling the pan and tilt angles of the turning unit based on the moving speed and the estimated travel position. 2. An automatic tracking device for tracking an object using a captured image, wherein the automatic tracking device includes a camera for acquiring an image of a region where the object needs to be tracked. Turning means for turning the image input means in two axial directions based on the input pan / tilt angle control amount; and tracking object extraction for extracting an object to be tracked from an image obtained by the image input means. Means, the position of the tracking point of the object to be tracked at different times is converted into a position on absolute coordinates using the pan / tilt angle of the turning means and the zoom magnification of the image input means, and stored in chronological order. A position storage means for converting the stored positions of the plurality of tracking points into camera coordinates again and outputting the coordinates, a position estimating means for estimating the moving position of the object from the positions of the tracking points of the past object, and a past object. Follow-up Speed calculating means for calculating a moving speed of an object from a position of a point; turning control means for controlling a pan / tilt angle of the turning means based on the estimated moving position and the moving speed; and camera coordinates by moving the tracked object. An automatic tracking device, comprising: an object moving region calculating unit that calculates an area of a region to be swept up above; and a zoom control unit that controls a zoom magnification of the image input unit based on a moving region area of the tracking object. . 3. An automatic tracking method for tracking an object using a captured image, the automatic tracking method comprising: determining a position of a tracking point of an object to be tracked at different times by using a pan Using the tilt angle, the position is converted to a position on absolute coordinates and stored in chronological order.The stored positions of the plurality of tracking points are converted back to camera coordinates and output, and the positions of the tracking points of the past object are output. An automatic tracking method comprising: estimating a moving position of an object and calculating a moving speed of the object from the image data; and controlling a pan / tilt angle of the image input means based on the estimated position and the moving speed. 4. An automatic tracking method for tracking an object using a captured image, the automatic tracking method comprising: determining a position of a tracking point of an object to be tracked at a different time by using a pan Using the tilt angle and zoom magnification, the position is converted to a position on absolute coordinates and stored in chronological order.The stored positions of the plurality of tracking points are again converted to camera coordinates and output, and the past tracking object Estimate the moving position of the object and calculate the moving speed of the object from the position of the tracking point, control the pan / tilt angle of the image input means from the estimated position and the moving speed, and sweep on the camera coordinates by moving the tracking object. An automatic tracking method comprising calculating an area of a region, and controlling a zoom magnification based on a moving region area of a tracking object. 5. A computer-readable recording medium recording an automatic tracking program for performing tracking using a captured image, wherein the automatic tracking program determines a position of a tracking point of an object to be tracked at different times. By using the pan / tilt angle of the image input means, the position is converted to a position on absolute coordinates and stored in chronological order, and the stored positions of the plurality of tracking points are converted again to camera coordinates and output. Estimating the moving position of the object from the position of the tracking point of the object and calculating the moving speed of the object, and causing the computer to control the pan / tilt angle of the image input means from the estimated position and the moving speed. A recording medium on which a featured automatic tracking program is recorded. 6. A computer-readable recording medium recording an automatic tracking program for performing tracking using a captured image, wherein the automatic tracking program determines a position of a tracking point of an object to be tracked at different times. Using the pan / tilt angle and the zoom magnification of the image input means, the position is converted to a position on absolute coordinates and stored in chronological order, and the stored positions of the plurality of tracking points are again converted to camera coordinates and output. Estimating the moving position of the object and calculating the moving speed of the object from the position of the tracking point of the past tracked object, controlling the pan / tilt angle of the image input means from the estimated position and the moving speed, An automatic tracking program characterized by calculating the area of the area swept on the camera coordinates by movement and causing the computer to control the zoom magnification from the area of the movement area of the tracking object. Recording the recording medium.