KR20130015982A - Apparatus and method for tracking car - Google Patents

Abstract

PURPOSE: A vehicle tracing method and an apparatus thereof are provided to accurately trace a vehicle region even in a difficult driving situation for accurately detecting the features of a vehicle. CONSTITUTION: A vehicle region detector receives multiple images from a camera module(S120) which puts a time lag between each received image. The vehicle region detector detects vehicle feature points from a first image(S130). The vehicle region detector extracts the optical flow of the vehicle feature points that exist between the first image and a second image(S140). The vehicle region detector traces the vehicle region based on the extracted optical flow(S150). [Reference numerals] (AA) Start; (BB) End; (S120) Receiving multiple images from a camera; (S130) Detecting a vehicle feature point from a first image; (S140) Extracting an optical flow existing between the first image and a second image; (S150) Tracing a vehicle based on the optical flow

Description

Vehicle tracking method and device thereof {APPARATUS AND METHOD FOR TRACKING CAR}

The present invention relates to a method and apparatus for tracking a vehicle area, and more particularly, to a method and apparatus for tracking a vehicle whose size changes in a plurality of images having a time difference.

With cameras mounted on vehicles, development of devices for detecting objects such as vehicles, signals, lanes or other indicators is actively progressing. Information about the object detected through such a detection device may be used to drive the vehicle. In particular, a method of detecting a vehicle from an image captured by the camera and tracking the movement of a specific vehicle over time based on the detection result may be used.

In the prior art, a method of detecting a feature point of a vehicle in each of images captured with a time difference, and storing and analyzing a movement trajectory of the feature point is used. However, there are cases where a feature point of a vehicle is not detected in an image captured at any time due to various environmental factors. For example, when the camera's field of view is momentarily shaken due to an irregular road surface, part or all of a specific vehicle does not appear on the screen. In this case, there is a possibility that the vehicle detection and tracking performance is degraded. Therefore, there is a need for improvement in terms of vehicle detection and tracking accuracy.

Therefore, an object of the present specification is to propose a more accurate vehicle area detection and tracking method in order to solve the above problem. That is, the present specification proposes a method of tracking an area of a vehicle whose size changes in a plurality of images. According to an embodiment of the present invention, the vehicle region is tracked by using the vehicle feature point tracking and the determination of maintaining similarity based on the light flow.

According to one disclosure herein, a vehicle area tracking method is provided to achieve the above object. The method includes receiving a plurality of images at a parallax from a camera module; Detecting vehicle feature points in a first image of the plurality of images; Tracking the vehicle area based on the optical flow of the vehicle feature points. The light flow of the vehicle feature points may be present between the first image and a second image of the plurality of images.

The vehicle feature points detected in the first image of the plurality of images may be texture or outline information of the vehicle representing detailed features of the vehicle.

The texture or contour information of the vehicle may be one or more of a locally assembled binary (LAB) feature, a histograms of oriented gradients (HOG) feature, and a local binary pattern (LBP) feature.

The tracking of the vehicle area based on the light flow may include: extracting a vehicle based on a first shape formed by the vehicle feature points detected in the first image and a light flow existing between the first image and the second image; This can be accomplished by tracking whether the second shape of the feature points achieves geometric similarity.

The geometric similarity may be a scaling relationship between the first form and the second form.

The vehicle area tracking method may further include outputting the tracked vehicle area.

According to another disclosure herein, a vehicle area tracking device is provided to achieve the above object. The apparatus may be configured to receive a plurality of images with a parallax from a camera module, detect vehicle feature points in a first image of the plurality of images, and track a vehicle area based on an optical flow of the vehicle feature points. Wow; The camera module may transmit an image photographing the outside of the vehicle to the controller under the control of the controller.

The vehicle feature points detected in the first image of the plurality of images may be texture or outline information of the vehicle representing detailed features of the vehicle.

The texture or contour information of the vehicle may be one or more of a locally assembled binary (LAB) feature, a histograms of oriented gradients (HOG) feature, and a local binary pattern (LBP) feature.

The control unit may have geometrical similarity between a first shape formed by the vehicle feature points detected in the first image and a second shape formed by vehicle feature points extracted based on a light flow existing between the first image and the second image. Can track whether or not

The geometric similarity may be a scaling relationship between the first form and the second form.

The vehicle area tracking apparatus further includes a display unit, and the controller may control the display unit to output the detected vehicle area.

The present invention can accurately track the vehicle area even in various driving situations where it is difficult to accurately detect the vehicle feature point.

1 is a block diagram showing the configuration of a vehicle tracking device according to an embodiment of the present invention.
2 is a mounting view of the vehicle tracking device according to an embodiment of the present invention.
3 is an exemplary diagram for a modeling technique for detecting a feature point of a vehicle.
4A and 4B are exemplary views of detecting feature points of a vehicle in an image.
5 is a conceptual diagram of a method for tracking a vehicle area based on a light flow of vehicle feature points.
6 is a flowchart illustrating a vehicle area estimation method according to an exemplary embodiment of the present invention.

It is to be noted that the technical terms used herein are merely used to describe particular embodiments, and are not intended to limit the present invention. It is also to be understood that the technical terms used herein are to be interpreted in a sense generally understood by a person skilled in the art to which the present invention belongs, Should not be construed to mean, or be interpreted in an excessively reduced sense. In addition, when the technical terms used herein are incorrect technical terms that do not accurately express the spirit of the present invention, they should be replaced with technical terms that can be understood correctly by those skilled in the art. In addition, the general terms used in the present invention should be interpreted according to a predefined or prior context, and should not be construed as being excessively reduced.

Also, the singular forms "as used herein include plural referents unless the context clearly dictates otherwise. In the present application, the term "comprising" or "comprising" or the like should not be construed as necessarily including the various elements or steps described in the specification, Or may be further comprised of additional components or steps.

In addition, the suffixes "module" and "unit" for the components used herein are given or mixed in consideration of ease of specification, and do not have distinct meanings or roles from each other.

Furthermore, terms including ordinals such as first, second, etc. used in this specification can be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, wherein like reference numerals refer to like or similar elements throughout the several views, and redundant description thereof will be omitted.

In the following description, well-known functions or constructions are not described in detail since they would obscure the invention in unnecessary detail. It is to be noted that the accompanying drawings are only for the purpose of facilitating understanding of the present invention, and should not be construed as limiting the scope of the present invention with reference to the accompanying drawings.

1 is a block diagram showing the configuration of a vehicle area tracking device according to an embodiment of the present invention.

As shown in the drawing, the vehicle area tracking apparatus 10 may include a camera module 110, a controller 120, a display unit 130, and a storage 140. Not all components of the vehicle area tracking device 10 shown in FIG. 1 are essential components, and the vehicle area tracking device 10 may be implemented by more components than those shown in FIG. 1. Vehicle area tracking device 10 may also be implemented by fewer components.

The camera module 110 may include at least one pair of cameras (eg, a stereo camera or a stereo camera) spaced apart at horizontal intervals on the same central axis of any same plane of the vehicle area tracking apparatus 10. A stereoscopic camera or a single camera. In this case, the fixed horizontal interval may be set in consideration of a distance between two eyes of a general person, and is set when configuring the vehicle area tracking apparatus 10. In addition, the camera module 110 may be any camera module capable of image capturing.

In addition, the camera module 110 may include a first image (eg, a left image captured by a left camera included in the pair of cameras) and a second image captured by the pair of cameras simultaneously. For example, the right image captured by the right camera included in the pair of cameras) is received.

In addition, the camera module 110 may be an image sensor such as a CCD device and a CMOS device.

In addition, when installed in a vehicle, the camera module 110 may be fixed to a predetermined position of the vehicle, and may be configured to photograph the front, the side, the rear of the driving direction, and the like to receive the photographed image.

According to the embodiments disclosed herein, the camera module 110 may acquire a plurality of images with a parallax through the camera. The plurality of images can be used to extract light flow. The plurality of images may be frame images of a video.

The controller 120 controls the overall operation of the vehicle area tracking device 10. In addition, the controller 120 may control a separate classifier and / or detector for the detection and tracking.

The controller 120 may receive a plurality of images with a parallax from the camera module. In addition, the controller 120 may detect vehicle feature points in a first image of the plurality of images. In this case, the vehicle feature points detected in the first image may be texture or outline information of the vehicle representing detailed features of the vehicle, and the texture or outline information of the vehicle may include a locally assembled binary (LAB) feature and histograms of HOG. or one or more of a oriented gradients (LBP) feature or a local binary pattern (LBP) feature.

The controller 120 may extract the light flow of the vehicle feature point existing between the first image and the second image. The second image may be an image photographed after a predetermined time T has elapsed from the photographing time of the first image.

The controller 120 may track the vehicle area based on the optical flow of the vehicle feature points.

The optical flow refers to the velocity distribution of the apparent motion in the image caused by slowly changing the brightness pattern. In other words, the optical flow refers to a vector representing the apparent motion appearing in the image from two different temporally different image data photographed and input by the camera.

Based on the light flow, an object (for example, a lane or a vehicle) may be detected. Each pixel of the current image of the frame in which the previous image and the respective pixels of the previous frame and the current frame of the current frame of the current frame are respectively detected. Compare or divide the previous image data into a plurality of unit blocks having a predetermined pixel, and move the current image data in pixel units and divide the previous image data into unit blocks having the same size as the unit block of the previous image data. Each unit block of the previous image data is compared with a plurality of unit blocks of the current image data to obtain a difference value such as luminance and chromaticity of the pixels in the unit block. Is expressed as a vector, and when a vector of a certain size or more occurs in a specific area, To detect the object.

The light flow of the vehicle feature points may be a light flow existing between the first image and a second image of the plurality of images. At this time, the tracking of the vehicle area is formed by the first feature formed by the vehicle feature points detected in the first image and the vehicle feature points extracted based on the light flow existing between the first image and the second image. This can be done by tracking whether the two forms achieve geometric similarity. The geometric similarity may mean that the first form and the second form have a scaling relationship. That is, it may mean that the second form is a form in which the first form is reduced or enlarged.

In addition, the control unit 120 may control to display the vehicle area tracking result on the display unit 130.

The display unit 130 displays various contents such as various menu screens using a user interface and / or a graphic user interface included in the storage unit 140 under the control of the controller 120. Here, the content displayed on the display unit 130 includes a menu screen including various text or image data (including various information data) and data such as an icon, a list menu, a combo box, and the like.

In addition, the display unit 130 includes a 3D display or a 2D display. In addition, the display unit 130 may include a liquid crystal display (LCD), a thin film transistor liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), and a flexible display. The display device may include at least one of a flexible display and a light emitting diode (LED).

In addition, the display unit 130 displays the 3D image (or 2D image) under the control of the controller 120.

In addition, two or more display units 130 may exist according to the implementation form of the vehicle area tracking apparatus 10. For example, the plurality of display units may be spaced apart or integrally disposed on one surface (same surface) of the vehicle area tracking apparatus 10, or may be disposed on different surfaces.

On the other hand, when the display unit 130 and a sensor for detecting a touch operation (hereinafter, referred to as a touch sensor) form a mutual layer structure (hereinafter referred to as a touch screen), the display unit 130 outputs the touch panel. In addition to the device can also be used as an input device. The touch sensor may have, for example, a form of a touch film, a touch sheet, a touch pad, or a touch panel.

In addition, the touch sensor may be configured to convert a change in pressure applied to a specific portion of the display unit 130 or capacitance generated at a specific portion of the display unit 130 into an electrical input signal. In addition, the touch sensor may be configured to detect not only the position and area of the touch but also the pressure at the time of touch. If there is a touch input to the touch sensor, the corresponding signal (s) is sent to a touch controller (not shown). The touch controller processes the signal (s) and then transmits the corresponding data to the controller 120. As a result, the controller 120 may determine which area of the display unit 130 is touched.

In addition, the display unit 130 may include a proximity sensor. In addition, the proximity sensor may be disposed in the inner region of the vehicle area tracking device 10 surrounded by the touch screen or near the touch screen.

In addition, the proximity sensor refers to a sensor that detects the presence or absence of an object approaching a predetermined detection surface or an object present in the vicinity without using a mechanical contact by using an electromagnetic force or infrared rays. The proximity sensor has a longer life and higher utilization than a contact sensor.

Examples of the proximity sensor include a transmission photoelectric sensor, a direct reflection photoelectric sensor, a mirror reflection photoelectric sensor, a high frequency oscillation proximity sensor, a capacitive proximity sensor, a magnetic proximity sensor, and an infrared proximity sensor. And to detect the proximity of the pointer by the change of the electric field along the proximity of the pointer when the touch screen is electrostatic.

In this case, the touch screen (touch sensor) may be classified as a proximity sensor. Hereinafter, for convenience of explanation, the act of recognizing that the pointer is positioned on the touch screen while the pointer is not in contact with the touch screen is referred to as "proximity touch" The act of actually touching the pointer on the screen is called "Contact Touch ". A position where the pointer is proximally touched on the touch screen means a position where the pointer corresponds to the touch screen vertically when the pointer is touched.

In addition, the proximity sensor detects a proximity touch and a proximity touch pattern (for example, a proximity touch distance, a proximity touch direction, a proximity touch speed, a proximity touch time, a proximity touch position, and a proximity touch movement state). Information corresponding to the sensed proximity touch operation and proximity touch pattern may be output on the touch screen.

As such, when the display unit 130 is used as an input device, a command or control signal may be received by an operation such as receiving a button operation by a user or touching / scrolling the displayed screen.

The storage unit 140 stores various menu screens, various user interfaces (UIs), and / or graphical user interfaces (GUIs).

According to the embodiments disclosed herein, when the light flow representing the difference between the plurality of images is extracted by the control unit 120, the storage unit 140, the extracted light flow value (or motion vector) Can be stored.

In addition, the storage unit 140 stores equations such as transformation matrices (eg, homographic matrices), curve equations, least squares methods, and the like.

In addition, the storage unit 140 stores data, a program, and the like necessary for the vehicle area tracking apparatus 10 to operate.

Here, the vehicle area tracking device of FIG. 1 may not only be configured as stand alone, but also a mobile terminal, a telematics terminal, a smart phone, and a portable terminal. Terminal, Personal Digital Assistant (PDA), Portable Multimedia Player (PMP), Notebook Computer, Tablet PC (Tablet PC), Wibro Terminal, IPTV (Internet Protocol Television) Terminal, Television It can be applied to various terminals such as television, 3D television, video equipment, telematics terminal, navigation terminal, audio video navigation (AVN) terminal, and the like.

2 is a mounting view of the vehicle area tracking device according to an embodiment of the present invention.

The vehicle area tracking device 10 may be mounted at a position capable of looking at the front of the vehicle 50. In FIG. 2, the vehicle area tracking device 10 is mounted at a position similar to the eye height of the vehicle driver. However, the mounting position may be changed by factors caused by the vehicle or the driver. In addition, the vehicle area tracking device 10 may be mounted to all the components in one location, the camera module and other components may be mounted separately. The vehicle detection method disclosed herein may also be used to detect a vehicle adjacent to the side or the rear, and at this time, the position of the vehicle area tracking device 10 may be changed.

3 is an exemplary diagram for a modeling technique for detecting a feature point of a vehicle.

(A) and (b) of FIG. 3 is an exemplary diagram representing haar-wavelet characteristics of the vehicle, and (c) of FIG. 3 is an exemplary diagram representing locally assembled binary (LAB) characteristics of the vehicle. 3 (d) is an exemplary diagram representing the histograms of oriented gradients (HOG) characteristics of the vehicle.

The lower wavelet feature is a model of a feature such as contrast difference in various areas of a rectangular shape. That is, in the case of a vehicle, various characteristic patterns appearing in the rectangular area are modeled. In addition, the LAB, local binary pattern (LBP), and HOG features, which are more complex features capable of expressing texture and contour information of a vehicle region, are used to detect a vehicle in an image. Although not illustrated in FIG. 3, LBP is a method of expressing a texture of a local image. The LBP is divided into regions having an arbitrary size and position for each input image, and then the remaining neighbors based on the median of the divided image regions. This method binarizes the pixel value. It is known that a texture that is robust to changes in illumination can be expressed by the above method.

The detector of the vehicular area tracking device typically learns various feature points of the vehicle using the modeling techniques. After the learning, a specific search area (or vehicle candidate area) is searched to determine whether the object of the image is a vehicle according to how much of the vehicle feature points are found.

4A and 4B are exemplary views of detecting feature points of a vehicle in an image.

4A is an image photographed at an arbitrary time, and FIG. 4B is an image photographed after a predetermined time elapses from the photographing time of FIG. 4A.

As can be seen with reference to Figures 4A and 4B, there are several feature points in the area of the vehicle to be tracked. For example, vehicle feature points may exist at the top edges 200a and 200a ', the side mirrors 200b and 200b', and the rear wheels 200c and 200c '. The vehicle area tracking apparatus may use a vehicle detector (or classifier) trained using the various features described with reference to FIG. 3 to detect the vehicle feature points from the image.

The vehicle area tracking device detects vehicle feature points in the image as shown in FIG. 4A. If the vehicle area to be tracked is an area corresponding to the middle lane, the vehicle detector detects a plurality of vehicle feature points in the set area.

4B is an image photographed after a predetermined time elapses, and is a target for tracking where the vehicle region detected in the image illustrated in FIG. 4A has moved. 4B illustrates that the area of the vehicle being tracked is closer to the camera direction. At this time, the traced vehicle and its area appearing in the image will appear larger than in the previous image, and if the vehicle feature point is detected in the same manner as in Fig. 4A, the vehicle feature points 200a ', 200b' and 200c 'are shown. ) Will be detected.

In a general driving situation, as described above, the vehicle feature point may be detected for each image at each time to continuously track a specific vehicle area.

However, the tracking of the vehicle area may be difficult depending on the driving environment. For example, a pitch motion may occur in a driving situation such as an excessively moving vehicle due to an irregular road surface situation. Pitch motion of a vehicle refers to an up-down movement of the vehicle due to a moving road surface condition. As a result, vehicle feature points may be incorrectly detected in the image at a particular moment, and the detected feature point may not appear in the image after the particular view in the image before the specific view. Therefore, even in such a case, there is a need for a method capable of accurately tracking the vehicle feature point and the vehicle area.

5 is a conceptual diagram of a method for tracking a vehicle area based on optical flow of vehicle feature points.

The optical flow refers to the velocity distribution of the apparent motion in the image caused by slowly changing the brightness pattern. In other words, the optical flow refers to a vector representing the apparent motion appearing in the image from two different temporally different image data photographed and input by the camera.

Based on the light flow, an object (for example, a vehicle or a lane) can be detected. Each pixel of the current image of the frame in which the previous image and the respective pixels of the previous frame and the current frame of the current frame of the current frame are respectively detected. Compare or divide the previous image data into a plurality of unit blocks having a predetermined pixel, and move the current image data in pixel units and divide the previous image data into unit blocks having the same size as the unit block of the previous image data. Each unit block of the previous image data is compared with a plurality of unit blocks of the current image data to obtain a difference value such as luminance and chromaticity of the pixels in the unit block, and the position at which the pixel of the previous image data moves by the obtained difference value Is expressed as a vector, and when a vector of a certain size or more occurs in a specific area, To detect the object.

The vehicle area tracking apparatus 10 detects a feature point of the vehicle from an image (hereinafter, referred to as a first image) captured at a specific time. In this case, the methods described above with reference to FIGS. 3 and 4 may be used.

Thereafter, the vehicle area tracking apparatus 10 analyzes a photographed image (hereinafter, referred to as a second image) after a predetermined time elapses from the photographing time of the first image. That is, an optical flow of vehicle feature points, which exists between the first image and the second image, is extracted. The extracted optical flow may be represented as vector forms 400a and 400b.

The vehicle region tracking apparatus 10 may track the vehicle region based on the form of the end points of the vectors. That is, among the end points of the vectors, end points having a shape that is geometrically similar to the shape in which the feature points of the vehicle detected in the first image are distributed are determined to be determined as the vehicle area. For example, if a feature in which the feature points of the vehicle detected in the first image are distributed is a trapezoidal shape, a distribution area of the end points of the vectors collected in a form in which the trapezoidal shape is reduced or enlarged is determined as the vehicle area.

As can be seen with reference to FIG. 5, when only the end points of some of the vectors 400a of the vectors representing the light flows are seen, the vehicle area 400 of the first image is distributed in an enlarged shape 400 ′. On the other hand, this is not the case if the end points of some other vectors 400b are viewed together. Therefore, in this case, the area in which only the endpoints of the 400a vectors are distributed may be determined as the vehicle area.

In the above, the case where the end points of the light flows gather the vehicle feature point distribution area in an enlarged shape has been described, but the above-described method may be applied to the reverse case. In other words, the same method may be applied to a case where the tracking vehicle area becomes smaller due to a greater distance from the tracked vehicle.

6 is a flowchart illustrating a vehicle area estimation method according to an exemplary embodiment of the present invention.

The vehicle area detector may receive a plurality of images with a parallax from the camera module (S120). At this time, the shooting time of each image can be managed.

The vehicle region detector may detect vehicle feature points in a first image of the plurality of images (S130). Here, the vehicle feature points detected in the first image may be texture or outline information of the vehicle representing detailed features of the vehicle, and the texture or outline information of the vehicle may include a locally assembled binary (LAB) feature and histograms of oriented. One or more of a gradients) feature, a local binary pattern (LBP) feature, or another feature pattern.

The vehicle region detector may extract an optical flow of a vehicle feature point existing between the first image and the second image (S140). Here, the second image is an image photographed after a predetermined time elapses from the photographing time of the first image.

The vehicle region detector may track the vehicle region based on the optical flow of the vehicle feature points (S150). The light flow of the vehicle feature points may be a light flow existing between the first image and a second image of the plurality of images. At this time, the tracking of the vehicle area tracks whether the first shape in which the vehicle feature points detected in the first image are distributed and the second shape in which the vehicle feature points extracted based on the optical flow are distributed are geometrically similar. This can be done by. The geometric similarity may mean that the first form and the second form have a scaling relationship. That is, it may mean that the second form is a form in which the first form is reduced or enlarged.

The vehicle area detector may output the tracked vehicle area through an output unit. In addition, an alarm may be generated according to the tracking result.

The embodiments described so far may be implemented in a recording medium readable by a computer or similar device using, for example, software, hardware or a combination thereof.

While the present invention has been described with reference to exemplary embodiments, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, but, on the contrary, May be modified, modified, or improved.

10: vehicle zone tracking device

Claims (12)

Receiving a plurality of images with parallax from a camera module;
Detecting vehicle feature points in a first image of the plurality of images; And
Tracking a vehicle area based on an optical flow of the vehicle feature points,
And a light flow of the vehicle feature points is present between the first image and a second image of the plurality of images. According to claim 1, Vehicle feature points detected in the first image of the plurality of images,
Vehicle area tracking method characterized in that the texture or contour information of the vehicle representing the detailed characteristics of the vehicle. The method of claim 2, wherein the texture or contour information of the vehicle,
And at least one of a locally assembled binary (LAB) feature, a histograms of oriented gradients (HOG) feature, and a local binary pattern (LBP) feature. The method of claim 1, wherein tracking the vehicle area based on the light flow comprises:
Whether the first shape formed by the vehicle feature points detected in the first image and the second shape formed by vehicle feature points extracted based on the light flow existing between the first image and the second image form a geometric similarity. Vehicle area tracking method, characterized in that made by tracking. The method of claim 4, wherein the geometric similarity is
And the first form and the second form have a scaling relationship. The method of claim 1,
And outputting the tracked vehicle area. Receive a plurality of images at a parallax from the camera module,
Detecting vehicle feature points in a first image of the plurality of images,
A controller for tracking a vehicle area based on an optical flow of the vehicle feature points; And
Under the control of the control unit includes a camera module for transmitting an image photographing the outside of the vehicle,
And an optical flow of the vehicle feature points is present between the first image and a second image of the plurality of images. The method of claim 7, wherein the vehicle feature points detected in the first image of the plurality of images,
Vehicle area tracking device characterized in that the texture or contour information of the vehicle representing the detailed characteristics of the vehicle. The method of claim 8, wherein the texture or contour information of the vehicle,
And at least one of a locally assembled binary (LAB) feature, a histograms of oriented gradients (HOG) feature, and a local binary pattern (LBP) feature. 8. The apparatus of claim 7,
Whether the first shape formed by the vehicle feature points detected in the first image and the second shape formed by vehicle feature points extracted based on the light flow existing between the first image and the second image form a geometric similarity. Vehicle area tracking device, characterized in that for tracking. The method of claim 10, wherein the geometric similarity is
And a scaling relationship between the first form and the second form. 8. The method of claim 7,
The display unit may further include a control unit.
And controlling the display unit to output the detected vehicle area.

Images