^{1}

^{*}

^{2}

^{*}

At present, most lane line detection methods are aimed at simple road surface. There is still no good solution for the situation that the lane line contains arrow, text and other signs. The edge left by markers such as arrow and text will interfere with the detection of lane lines. In view of the situation of arrow mark and text mark interference between lane lines, the paper proposes a new processing algorithm. The algorithm consists of four parts, Gaussian blur, image graying processing, DLD-threshold (Dark-Light-Dark-threshold) algorithm, correlation filter edge extraction and Hough transform. Among them, the DLD-threshold algorithm and related filters are mainly used to remove the identification interference between lane lines. The test results on the Caltech Lanes dataset are given at the end of the article. The result of verification of this algorithm showed a max recognition rate of 97.2%.

In recent years, traffic accidents caused by improper driving of drivers or fatigue driving have made the field of safe driving [

Computer vision is the key technology for safe driving, automatic driving and lane detection. The main task is to complete the detection and tracking of the lane line. It can provide safety for the vehicle and a more comfortable ride for passengers.

At this stage, many researchers and research centers have done a lot of research on lane line detection. For the case of lane mark detection, many approaches have been made until now. As proposed in [

In the case of no other sign interference in the middle of the lane line, the conventional preprocessing method combined with the Hough transform can detect and identify the lane line very well. However, if there is an arrow mark or a text mark in the middle of the lane line, the common preprocessing method will leave some noise information to interfere with the Hough transform [

In this paper, we propose a simple algorithm to eliminate inter-line marker interference. The method is divided into four parts. First, it uses Gaussian blur to remove the noise points, and then convert it to grayscale. After, DLD-threshold algorithm and correlation filter are used to remove the interference area in the middle of the lane line and extract the edge of the lane line. After, by the use of Hough transform, a linear cluster is obtained to determine the lane line distribution. The test results on the Caltech-lane dataset are provided at the end of the article and can be found to perform well in complicated conditions.

Gaussian blur [

G ( x , y , σ ) = 1 2 π σ 2 e − ( x 2 + y 2 ) 2 σ 2 (1)

where G is the two-dimensional Gaussian function. In the image, Gaussian functions can be represented in the form of convolution.

L ( x , y , σ ) = G ( x , y , σ ) ∗ I ( x , y ) (2)

( x , y ) represents the pixel coordinates in the image, σ is the standard deviation of the normal distribution, I ( x , y ) represents the input image, G ( x , y , σ ) is the Gaussian convolution kernel, L ( x , y , σ ) is the image filtered by Gaussian convolution.

The simulation results are as follow: Including the original image, the blurred image after the Gaussian blurring, where sigma is 5.

When the camera captures a color image, it contains three components of R, G, and B, which takes up a large space and is easily interfered by external brightness. The grayscale image has only one component and takes up little space, at the same time, considering that the human eye responds differently to different color bands. We assign different weight values to the original three channels to obtain the gray image in

G r a y = R ( x , y ) × 0.299 + G ( x , y ) × 0.587 + B ( x , y ) × 0.114 (3)

In order to eliminate the interference of road signs and other signs on lane line detection, we use the DLD-threshold algorithm here.

Here, we define m as the number of rows of the image, n is the number of columns of the image, s p a n is the average Manhattan distance between the pixels at the two edges of the lane line, t h r e s h o l d is the difference between the lane line and the local background gray value near it, I ( i , j ) is the gray value of input

image at ( i , j ) , O U T ( i , j ) is the gray value of the input image at ( i , j ) .

The set of pixels on both sides of the lane line are as follows:

P = { p 0 , p 1 , p 2 , ⋯ , p N } (4)

Q = { q 0 , q 1 , q 2 , ⋯ , q M } (5)

( X p i , Y p j ) , ( X q j , Y q j ) respectively represent the pixel coordinates of p i , q j . d ( p i , q j ) represents the Manhattan distance between pixel p i and pixel q j ,S represents the number of elements in s p a n i j .

d ( p i , q j ) = | X p i − X q j | + | Y p i − Y q j | (6)

s p a n i j = { d ( p i , q j ) } , i = 0 , 1 , 2 , ⋯ , N ; j = 0 , 1 , 2 , ⋯ , M ; | i − j | ≤ 1 (7)

s p a n = ∑ S s p a n i j S (8)

As shown in

In order to reduce the computational complexity, the conventional Canny edge extraction operator [

The correlation filtering algorithm [

g = f ⊗ h (9)

where f is the input image, h is the filter template and g is the corresponding output image.

f ⊗ h ( τ ) = ∫ ∞ − ∞ f * ( τ ) h ( t + τ ) d t (10)

Intuitive expression in the image is as follows

g ( i , j ) = ∑ k , l f ( i + k , j + l ) ⋅ h ( k , l ) (11)

Here, we use the 3 * 3 correlation filter to process image.

h = [ − 3 0 3 − 3 0 3 − 3 0 3 ] (12)

We use a correlation filter to extract the image at a single edge, where the amplitudes are taken as −3 and 3 respectively to enhance the edge strength. The result is shown in

Generally speaking, the lane line and the identification information are located in the middle part of the image, and a template is set to match the image with the template, leaving only valid information such as lane lines and identifiers. The result is shown in

In 1962, Paul Hough proposed the concept of Hough transform [

In the Cartesian coordinate system, the linear equation is generally expressed as the following form

y = k x + b (13)

In this equation, k is the slope and b is the intercept. Tacking into consideration this aspect, other parameters are proposed, denoted as ρ and θ ,which are polar coordinates.

ρ = x cos θ + y sin θ , θ ∈ [ − π , π ) (14)

As shown in

As shown in

ρ 0 = x cos θ 0 + y sin θ 0 (15)

We do the same operation described above for points of interest in the ROI area from the image. If there are multiple curves corresponding to different points intersecting in the coordinate system ρ θ ,it means that there is a straight line that can connect the multiple points. We can get the main lane line in the image by selecting the line with the intersection number in the Hough space. Also, the number of intersections must be greater than zero and greater than a predetermined threshold.

In addition, we may encounter some frame pictures without any mark but noise interference. We can also use the information of the previous frame in the Hough space to predict the lane line information of the next frame. The mark line detected from the current frame picture will not generate a large offset and the accuracy of the lane line detection of the consecutive frame picture can be improved.

This paper uses the Canny edge extraction operator and combine the Hough transform for comparison experiments. The experimental results are shown in

We use the Caltech Lanes dataset [

The following pictures in

Dataset | total | error | Correct_rate |
---|---|---|---|

Caltech-lanes-result-washington 2 | 232 | 25 | 89.22% |

Caltech-lanes-result-washington 1 | 232 | 53 | 77.16% |

Caltech-lanes-result-cordova 2 | 406 | 31 | 92.36% |

Caltech-lanes-result-cordova 1 | 250 | 7 | 97.2% |

This paper presents a lane line detection algorithm under the complicated conditions. The algorithm uses Gaussian blur, image graying, DLD-threshold algorithm, correlation filter and Hough transform to determine the distribution of lane lines. The experimental results show that the method can work effectively and accurately, and obtain good results, both in the case of complicated road information and simple road information. Of course, this paper doesn’t consider the impact of strong light and unclear road markings on the road environment. In the future, we can combine various conditions to continue to improve lane detection.

The authors declare no conflicts of interest regarding the publication of this paper.

Our research is supported by the Shandong Provincial Key R&D Program 2017GGX10113, Shenzhen Science and Technology Research and Development Funds (No. JCYJ20170818104011781).

Zhang, Z.C. and Ma, X. (2019) Lane Recognition Algorithm Using the Hough Transform Based on Complicated Conditions. Journal of Computer and Communications, 7, 65-75. https://doi.org/10.4236/jcc.2019.711005