KR20150146374A - System for lane recognition using environmental information and method thereof - Google Patents

Abstract

A system for recognizing a lane in real time and a method therefor are disclosed. The system for recognizing a lane in real time comprises: a pretreatment module pretreating an image and a picture obtained from a camera or a black box installed in a vehicle; a region of interest setting module setting a region of interest (Rol) from the pretreated image obtained from the pretreatment module; a lane recognition module obtaining vehicle position information through a GPS to recognize a lane in the set Rol using the obtained vehicle position information; and a display module displaying the recognized lane information.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention [0001] The present invention relates to a lane recognition system using surroundings information,

The present invention relates to a lane recognition system and a method thereof, and more particularly, to a system and method for real-time lane recognition using surrounding environment information.

Recently, researches on intelligent automobiles are being actively carried out. Among them, interest in information processing technology through video is increasing day by day. Particularly, efforts are being made to provide driving optimum lane information to the driver in real time by using lane recognition using an image acquired through a camera mounted on the front or rear of the vehicle, thereby improving the convenience of travel and prevention of safety accidents.

Lane recognition technology has been studied actively from the past. However, since the conventional lane recognition technology extracts image information of all frames of motion picture data taken while driving and uses it for lane recognition, much time is required for image processing.

In addition, since the lane image is mainly used for the lane recognition, the image recognition error rate is high and it is difficult to improve the driving convenience of the driver.

An object of the present invention is to perform lane recognition more accurately using a black box image and position information acquired through navigation.

In addition, image preprocessing and region of interest (ROI) extraction are performed more efficiently, thereby reducing the amount of computation required for lane recognition and providing the driver with fast and accurate lane recognition information in real time.

According to an aspect of the present invention, there is provided a lane recognition system including a preprocessing module for preprocessing images and images obtained from a vehicle-mounted camera or a black box, (ROI, Region of Interest), a position information of the vehicle is acquired by GPS, and the curve amount of the vehicle is calculated from the number of lanes in the running and the direction information of the vehicle included in the obtained vehicle position information A lane recognition module for mapping the lane information acquired in the image through the extracted information and the position information and recognizing the lane in the set area of interest by discriminating the lane position and the type of lane according to the mapping result, And a display module for displaying information.

In a preferred embodiment, the lane recognition system further includes an error detection module for detecting an error in the lane recognition process through the GPS and the location information of the vehicle under running and the lane (TOP VIEW).

In a preferred embodiment, the preprocessing module includes a lane candidate selector for extracting color space from the image and the image obtained through the color space representation data including YCbCr and RGB and for emphasizing the lane area, An edge extracting unit for extracting an edge of the extracted lane area, and a thinning unit for extracting a lane skeleton from edge information of the extracted lane area, thereby recognizing the lane included in the obtained image and the image.

In a preferred embodiment, the ROI module sets a region of interest of a dynamic image acquired through a camera mounted on the vehicle or an image sensor, or sets an ROI of a fixed image acquired using the location information of the vehicle.

In a preferred embodiment, the lane recognition module may include a lane search unit for searching lanes included in the ROI through the Hough transform and the vanishing point extraction process, the vehicle GPS information, And a candidate lane searching unit for searching for candidate lanes adjacent to the optimal lane using the optimum lane determining unit and the optimal lane information for determining the driving optimum lane among the lanes and for determining the driving situation of the searched candidate lanes.

In a preferred embodiment, the display module displays at least one of the optimum lane and the candidate lane determined in the lane recognition module, displays a display for emphasizing the safety distance and the driving lane from the preceding vehicle in the lane in which the vehicle is running , And displays a danger signal warning the lane departure when the vehicle leaves the lane by more than a predetermined value.

According to another aspect of the present invention, there is provided a lane recognition method comprising the steps of: preprocessing images and images obtained from a vehicle-mounted camera or a black box; setting a region of interest (RoI) from a preprocessed image; A process of recognizing a lane in an area of interest set by using the acquired vehicle location information, a process of detecting an error in the lane recognition process through the location information of the vehicle under driving and a lane (TOP VIEW) And displaying the detected lane information.

In a preferred embodiment, the preprocessing process includes a process of extracting a region of interest from an acquired image and an image, a process of performing histogram stretching of the extracted region of interest, and a process of performing a sobell operation and a binarization process after a histogram stretching process. and performing a binary operation.

In a preferred embodiment, a process of setting a region of interest (RoI) includes a process of extracting a color space from an image and an image obtained through color space representation data including YCbCr and RGB to emphasize a lane area, Extracting an edge of an emphasized lane area, and extracting a lane skeleton from edge information of the extracted lane area.

In a preferred embodiment, the process of detecting an error includes a step of performing a top view transform on the lane recognized by the GPS and the location information of the vehicle and the image information input to the vehicle, And performing a transform (Hough transform).

In a preferred embodiment, the process of recognizing a lane in a set ROI includes searching for a lane included in the ROI through a Hough transform and vanishing point extraction process, detecting vehicle GPS information, Determining a driving optimal lane among the searched lanes, and searching candidate lanes adjacent to the optimal lane using the optimal lane information, and determining a driving situation of the searched candidate lanes.

In a preferred embodiment, the displaying process displays at least one of the optimum lane and the candidate lane determined by the lane recognition module, displays a display for emphasizing the safety distance and the driving lane from the lane in which the vehicle is running And acquiring the lane departure signal of the vehicle and displaying the danger signal according to the lane departure value after the lane departure signal is acquired.

According to the present invention, by using the positional information of the vehicle obtained from the navigation, the lane recognition of the image acquired through the black box and various cameras mounted on the vehicle can be performed more accurately, thereby preventing a safety accident, .

It also reduces image recognition errors through top view conversion of lane recognition images.

In addition, by filtering the area of interest for lane recognition by linking the position information of the vehicle obtained from the navigation with the image information acquired by the vehicle, the amount of calculation required for lane recognition is reduced. This improves the response performance of the entire system.

1 is a block diagram showing a schematic configuration of a lane recognition system according to an embodiment of the present invention.
2 is a block diagram showing a detailed configuration of a lane recognition system according to an embodiment of the present invention.
3 is a flowchart illustrating a lane recognition method according to an embodiment of the present invention.
4A is a flowchart of a preprocessing process according to an embodiment of the present invention.
4B to 4C are diagrams showing examples of image processing according to an embodiment of the present invention.
5 is a flowchart illustrating a candidate lane recognition process according to an embodiment of the present invention.
6 is a flowchart illustrating a process of performing a candidate lane recognition according to an embodiment of the present invention using a top view,
7A to 7I are views showing an embodiment of a candidate lane recognition process.
8A to 8C are views showing a lane-searching embodiment in the candidate lane searching unit 350 according to the embodiment.
9A to 9D show an example of lane information display in the display module according to the embodiment.
10A to 10D are views showing an embodiment of a lane recognition process using a top view.

The present invention is a result of research carried out with the support of the "RE-EV practical research base construction project" which was funded by the Ministry of Industry and Trade (MOTIE) and supported by the Korea Industrial Technology Development Organization (KIAT).

The present invention is also applicable to a top view within 10 cm of resolution 0043358 with the support of the Ministry of Trade Industry and Energy (MOTIE) and the Korea Institute of Advancement of Technology (KIAT) And a peripheral image information configuration and recognition system capable of panorama view ".

In the present invention, the lane recognition is performed more accurately using the black box image and the position information acquired through navigation.

In addition, by performing image preprocessing and region of interest (ROI) extraction more efficiently, the amount of computation required for lane recognition is reduced, thereby providing the driver with quick and accurate lane identification information in real time.

By filtering the area of interest for lane recognition by linking the position information of the vehicle obtained from the navigation and the image information acquired from the vehicle, the image recognition error is reduced through top view conversion of the lane recognition image, Thereby reducing the amount of computation required to perform recognition. This improves the response performance of the entire system.

BRIEF DESCRIPTION OF THE DRAWINGS The advantages and features of the present invention, and the manner of achieving them, will be apparent from and elucidated with reference to the embodiments described hereinafter in conjunction with the accompanying drawings. The present invention may, however, be embodied in many different forms and should not be construed as being limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. Is provided to fully convey the scope of the invention to those skilled in the art, and the invention is only defined by the scope of the claims. It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. In the present specification, the singular form includes plural forms unless otherwise specified in the specification.

The term " module ", as used herein, should be interpreted to include software, hardware, or a combination thereof, depending on the context in which the term is used. For example, the software may be machine language, firmware, embedded code, and application software. In another example, the hardware may be a circuit, a processor, a computer, an integrated circuit, a circuit core, a sensor, a micro-electro-mechanical system (MEMS), a passive device, or a combination thereof.

1 is a block diagram showing a schematic configuration of a lane recognition system according to an embodiment of the present invention.

Referring to FIG. 1, a lane recognition system using image processing includes a preprocessing module 100, a region of interest setting module 200, and a lane recognition module 300, and a display module 400 ). ≪ / RTI >

The preprocessing module 100 preprocesses images and images obtained from a vehicle-mounted camera or a black box. The preprocessed images and images are transferred to the ROI module.

The region of interest setting module 200 sets a region of interest (RoI) from the preprocessed image acquired from the preprocessing module. In the embodiment, the area of interest is the area for lane recognition, and the remaining area excluding the parts unnecessary for lane recognition in the black box and the image acquired through the camera may be the area of interest.

The lane recognition module 300 acquires the position information of the vehicle through the GPS, extracts the curve amount of the vehicle from the running lane number included in the obtained vehicle position information and the traveling direction information of the vehicle, The lane information acquired from the image is mapped through the position information, and the lane position and the type of the lane are determined according to the mapping result to recognize the lane in the set interest area.

Specifically, the lane recognition module 300 determines how many lanes the road on which the vehicle is traveling is based on the vehicle position information, and when recognizing the traveling direction of the vehicle, the maximum lane of the road on which the vehicle is currently traveling can be known. Thereby, it is possible to map the lane information acquired from the image and determine the position of the lane more accurately and the type of the lane.

In addition, since the image state acquired in the vehicle is often dependent on the weather (sunny, cloudy, etc.) of the driving area, it is difficult to always guarantee the quality of the image obtained in the vehicle. In the embodiment according to the present invention, when it is difficult to distinguish an object included in the image from an image acquired in the cloudy weather through the location information of the vehicle and the lane information mapping, in order to compensate the object, Various information included in the information can be used.

The error detection module 400 detects an error in the recognized lane information. In general, when a vehicle travels at night or on a curved road, a lane recognition error occurs more highly. In the embodiment, the top view of the road, which is obtained by linking the black box image and the vehicle location information, Adaptive lane recognition is performed to minimize lane recognition errors.

      Then, the lane identification information on which the error detection is completed is displayed on the display module 400. [ In the embodiment, the display module 400 displays at least one of the optimal lane and the candidate lane determined by the lane recognition module 300. In accordance with the driver's selection, the safety distance from the lane in which the vehicle is running, A display emphasizing the driving lane can be displayed. In addition, when the vehicle being driven leaves the lane by more than a predetermined value, a danger signal warning the lane departure can be displayed.

2 is a block diagram showing a detailed configuration of a lane recognition system according to an embodiment of the present invention.

2, the preprocessing module 100 of the lane recognition system according to the embodiment includes a lane candidate selecting unit 110, an edge extracting unit 130, and a thinning unit 150, (V-ROI) setting unit 200 includes a dynamic image interest region setting unit 210, a fixed image RO region setting unit 230, and a camera RO region setting unit 250. The V- And the like. The error detection module 400 may include a top view conversion unit 410 and a Huff conversion unit 430.

Hereinafter, the operation of each component and the operation of the lane recognition system will be described in detail with reference to the drawings showing the embodiments.

The lane candidate selecting unit 110 included in the preprocessing module 100 extracts a color space from the obtained image and image through color space representation data including YCbCr and RGB to emphasize the lane area. YCbCr is a type of color space used in an image system, and is a color representation method in which brightness components and chrominance components are separated from color information. Y denotes a luminance signal, and Cb and Cr denotes color difference signals. YCbCr is not an absolute color space, but is a color representation method that converts RGB information having visually uniform information of red, green, and blue primary colors to different information by using a brightness signal and a color difference signal. When the lane candidate selecting unit 110 emphasizes the lane area by the color space data difference, it is transmitted to the edge extracting unit 130.

The edge extracting unit 130 extracts the edge of the lane area emphasized by the lane candidate selecting unit 110. [ An edge is a feature that represents the boundary of a region in an image. In an embodiment, the edge extracting unit 130 extracts an edge using a method of obtaining a pixel corresponding to a contour line as a discontinuous point of image brightness, or extracts an edge included in an image using a color space difference. The extracted edge data is transmitted to the thinning unit 150.

The thinning unit 150 extracts the lane skeleton from the edge information of the extracted lane area.

The interest area setting module 200 is configured to set the interest area of the camera through the camera and the image sensor mounted on the vehicle through the dynamic image interest area setting section 210, the fixed image interest area setting section 230, Sets the region of interest of the dynamic image to be acquired or sets the region of interest of the fixed image to be acquired using the vehicle location information.

7A and 7B, when the black box image image shown in FIG. 7A is obtained in the ROI module 200, the lower part of the image unnecessary for lane recognition is filtered, Set the same area of interest. This reduces the amount of computation required to perform lane recognition and improves the response performance of the entire system.

The lane search unit 310 included in the lane recognition module 300 searches for lanes included in the area of interest through the Hough transformation and the vanishing point extraction process. Figs. 7C and 7D show a Hough transform embodiment, and Fig. 7G shows an embodiment in which a vanishing point is extracted and a lane is searched. FIG. 7C is an original image before Huff transform, and FIG. 7D is an image in which line segments are extracted after Huff transform. The Hough transform is a transformation for extracting a line segment for lane recognition in image processing. Specifically, if a straight line is represented by xcosθ + ysinθ =?, The same straight line falls to one point in the θ-? Find a straight line by clustering in the plane. At this time, the straight line is? -? Falling to the plane is called Hough transform.

The optimal lane determining unit 330 determines the best driving lane among the searched lanes by using the vehicle GPS information, the information of the front and rear vehicles sensed, and the lane searching information input from the lane searching unit 310, and the like. For example, as shown in FIG. 7H, when at least one lane is recognized, the best lane determining unit 330 determines the best lane by applying the best lane filter. For example, as shown in FIG. 7I, the optimum lane determining unit 330 filters the candidate lanes based on the number of vehicles in operation and the distance data to the preceding vehicle, which are sensed in the lane, .

Thereafter, the candidate lane searching unit 350 searches the candidate lanes adjacent to the optimal lane by using the optimal lane information, and determines the driving situation of the searched candidate lanes, thereby continuously providing lane information most suitable for driving to the driver have.

8A to 8C are views showing a lane-searching embodiment in the candidate lane searching unit 350 according to the embodiment. For example, when the lane recognition rate is too weak to recognize the lane completely as shown in Fig. 8A, the candidate lane searching unit 350 displays the candidate lane with the symbols such as the points shown in Fig. 8B, As shown in 8c, the driving lane can be recognized by connecting the point representing the candidate lane and the vanishing point of the front vehicle.

The top view conversion unit 410 included in the error detection module 400 performs top view conversion on an image acquired using GPS and vehicle location information to minimize lane recognition errors due to environmental factors such as night driving and curved roads . 10A to 10C show the top view converted image according to the embodiment. In the embodiment, the Hough transform unit 430 performs Hough transform on the top view converted image, thereby minimizing occurrence of the lane recognition error.

The display module 500 displays the lane information in a form that the driver can easily recognize. 9A to 9D show an example of lane information display in the display module according to the embodiment. 9A, the display module 500 emphasizes lane information in the form of a UI (User Interface), or the display module 500 displays safety distance information with respect to the preceding vehicle as color As shown in FIG. Specifically, if the distance to the front vehicle is greater than the safety distance, the vehicle is shown in green, and if the distance is less than the safety distance, a lane is displayed in red so that the driver can easily see whether the driver maintains the safety distance with the front vehicle. Further, as shown in FIG. 9C, the display module 500 emphasizes the vanishing point of the lane or, as shown in FIG. 9D, the display module 500 displays a danger signal when the vehicle deviates from the lane by more than a predetermined value Can be shown.

3 is a flowchart illustrating a lane recognition method according to an embodiment of the present invention.

In step S310, a process of preprocessing images and images obtained from a vehicle-mounted camera or a black box is performed. Generally, the preprocessing process of S310 is most important to improve the recognition rate of lane recognition.

In step S320, a process of setting a region of interest (RoI) from the preprocessed image is performed.

In step S330, a process of acquiring the vehicle position information through the GPS and recognizing the lane in the set area of interest using the acquired vehicle position information is performed. In step S340, the position information of the vehicle and the lane of the lane (TOP VIEW) A process of detecting an error in the lane recognition process is performed. Thereafter, in step S350, a process of displaying the error-detected lane information is performed.

Hereinafter, each process will be described in detail with reference to the drawings.

4A is a flowchart of a preprocessing process according to an embodiment of the present invention.

If the black box image is acquired in step S410, a process of minimizing the recognition range of the acquired image is performed through the set interest area in step S420. In step S430, a histogram stretching process is performed to fix the binarization threshold value to the minimized recognition range, thereby uniformly distributing brightness values of the gray image as shown in FIG. 4B. In step S440, a Sobel operation and a binarization operation are performed. As shown in FIG. 4C, the Sobel operation and the binarization operation are processes for extracting an edge in the horizontal direction. After the threshold value is set, the area lower than the threshold value is processed as black, and the area higher than the threshold value is processed as white Emphasize the lane.

FIG. 5 is a flowchart illustrating a candidate lane recognition process according to an exemplary embodiment of the present invention, and FIGS. 7C to 7I illustrate a candidate lane recognition process.

In step S510, the preprocessed image is Huff transformed to detect straight lines. In step S520, a process of filtering the lines having low similarity with the lane using the Huff filter is performed. Thereafter, a process of grouping the minimized lines is performed in step S530. After grouping them into one line, the recognition rate is increased by performing a filtering process once again using the vanishing point in step S540. Thereafter, the lane is detected in step S550.

FIG. 6 is a flowchart illustrating a process of performing a candidate lane recognition using a top view according to an embodiment of the present invention. FIGS. 10A to 10D illustrate a lane recognition process using a top view.

Since the lane recognition rate is considerably lowered when the color of the lane is obscured, is running at night, or is traveling on a curved road, the embodiment of the present invention increases the recognition rate of the candidate lane and minimizes the lane recognition error by using the top view.

When the candidate lane recognition image is inputted, the top view conversion process is performed in step S610, and the top view interest area of the lane is acquired as shown in FIG. 8A. The binarized lane detection image as shown in FIG. 10B is obtained by performing the Sobel operation and the binarization operation on the top view interest area, and in step S620, the Hough transform process is performed on the obtained top view ROI image, And obtains the lane identification image as shown in 10c. FIG. 10D shows an embodiment in which a lane recognition image is displayed. The present invention minimizes a lane recognition error and allows a driver to recognize a candidate lane.

As described above, in the embodiment of the present invention, the lane recognition is performed more accurately by using the black box image and the position information acquired through the navigation.

In addition, by performing image preprocessing and region of interest (ROI) extraction more efficiently, the amount of computation required for lane recognition is reduced, thereby providing the driver with quick and accurate lane identification information in real time.

By filtering the area of interest for lane recognition by linking the position information of the vehicle obtained from the navigation and the image information acquired from the vehicle, the image recognition error is reduced through top view conversion of the lane recognition image, Thereby reducing the amount of computation required to perform recognition, thereby improving the response performance of the entire system.

Meanwhile, the lane recognition method according to the embodiment of the present invention can be implemented in a computer system or recorded on a recording medium. The computer system may include at least one or more processors, a memory, a user input device, a data communication bus, a user output device, and a storage. Each of the above-described components performs data communication via a data communication bus.

The computer system may further include a network interface 129 coupled to the network. The processor may be a central processing unit (CPU), or a semiconductor device that processes instructions stored in memory and / or storage.

The memory and the storage may include various forms of volatile or non-volatile storage media. For example, the memory may include ROM and RAM.

Meanwhile, the lane recognition method according to the embodiment of the present invention described above can be implemented as a computer-readable code on a computer-readable recording medium. The computer-readable recording medium includes all kinds of recording media storing data that can be decoded by a computer system. For example, there may be a ROM (Read Only Memory), a RAM (Random Access Memory), a magnetic tape, a magnetic disk, a flash memory, an optical data storage device and the like. The computer-readable recording medium may also be distributed and executed in a computer system connected to a computer network and stored and executed as a code that can be read in a distributed manner.

It will be understood by those skilled in the art that the present invention may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. The scope of the present invention is defined by the appended claims rather than the detailed description, and all changes or modifications derived from the scope of the claims and their equivalents should be construed as being included within the scope of the present invention.

Claims (13)

A preprocessing module for preprocessing images and images obtained from a vehicle-mounted camera or a black box;
A ROI (Region of Interest) setting region of interest (ROI) from the preprocessed image acquired from the preprocessing module;
The vehicle position information is acquired through GPS, and the curve amount of the vehicle is extracted from the number of running lanes included in the obtained vehicle position information and the traveling direction information of the vehicle, A lane recognition module for mapping lane information acquired from an image and recognizing a lane in the set area of interest by discriminating a lane position and a lane type according to a mapping result; And
A display module for displaying the recognized lane information; Of the lane recognition system.
The system according to claim 1, wherein the lane recognition system
And an error detection module for detecting an error in the lane recognition process through the GPS and the position information of the vehicle during the running and a lane (TOP VIEW).
2. The apparatus of claim 1, wherein the preprocessing module
A lane candidate selecting unit for extracting a color space from the obtained image and the image through color space expression data including YCbCr and RGB to emphasize a lane area;
An edge extracting unit for extracting an edge of a lane area emphasized by the lane candidate selecting unit; And
A thinning unit for extracting a lane skeleton from edge information of the extracted lane area; And the lane recognition unit recognizes the lane included in the obtained image and the image.
2. The apparatus of claim 1, wherein the ROI module
Wherein a region of interest of the dynamic image acquired through the camera and the image sensor mounted on the vehicle is set or an area of interest of the fixed image acquired using the position information of the vehicle is set.
The system of claim 1, wherein the lane recognition module
A lane searching unit searching a lane included in the ROI through a Hough transform and a vanishing point extraction process;
An optimum lane determining unit for determining a driving optimum lane among the searched lanes using the vehicle GPS information and information on the front and rear vehicles sensed; And
A candidate lane searching unit searching candidate lanes adjacent to the optimal lane using the optimal lane information and determining a running state of the searched candidate lanes; The lane recognition system comprising:
The display device of claim 1, wherein the display module
Wherein the display unit displays at least one of the optimum lane and the candidate lane determined by the lane recognition module, displays a display for emphasizing the safety distance and the driving lane from the lane in which the vehicle is running, And displays a danger signal warning of lane departure when the vehicle departs from a predetermined value or more.
A process of pre-processing images and images obtained from a vehicle-mounted camera or a black box;
Setting a region of interest (RoI) from the preprocessed image;
Obtaining location information of the vehicle through GPS, and recognizing a lane in the set area of interest using the obtained vehicle location information; And
Detecting an error of the lane recognition process through the position information of the driving vehicle and the lane (TOP VIEW); And
Displaying the error-detected lane information; The lane recognition method comprising:
8. The method of claim 7, wherein the pre-
Extracting a region of interest from the acquired image and image;
Performing histogram stretching of the extracted region of interest; And
Performing a Sobel operation and a binary operation after the histogram stretching process; Wherein the lane recognition method comprises the steps of:
8. The method according to claim 7, wherein the step of setting the region of interest (RoI)
Extracting a color space from the obtained image and image through color space representation data including YCbCr and RGB to emphasize a lane area;
Extracting an edge of the highlighted lane area;
And extracting a lane skeleton from edge information of the extracted lane area.
8. The method of claim 7, wherein the detecting the error comprises:
Performing a top view transform on the lane recognized by the GPS and the location information of the vehicle and the image information input to the vehicle;
Performing a Hough transform on the image subjected to the top view conversion; Wherein the lane recognition method comprises the steps of:
8. The method of claim 7, wherein the step of recognizing a lane in the set region of interest comprises:
Searching a lane included in the ROI through a Hough transform and a vanishing point extraction process;
Determining a driving optimal lane among the searched lanes by using the vehicle GPS information and information on the front and rear vehicles; And
Searching for candidate lanes adjacent to the optimal lane using the optimal lane information and determining a running state of the searched candidate lanes; The lane recognition system comprising:
8. The method of claim 7,
A display unit for displaying at least one of the optimum lane and the candidate lane determined by the lane recognition module and displaying a display for emphasizing the safety distance and the driving lane from the lane in which the vehicle is running,
Obtaining a lane departure signal of the vehicle; And
And displays a danger signal according to the lane departure value after the lane departure signal is acquired.
A computer-readable recording medium storing a program for causing a computer to execute the method according to any one of claims 7 to 12.

Images