Enhancing Lane-Tracking Performance in Challenging Driving Environments through Parameter Optimization and a Restriction System

Abstract

The autonomous driving market has experienced rapid growth in recent times. From systems that assist drivers in keeping within their lanes to systems that recognize obstacles using sensors and then handle those obstacles, there are various types of systems in autonomous driving. The sensors used in autonomous driving systems include infrared detection devices, lidar, ultrasonic sensors, and cameras. Among these sensors, cameras are widely used. This paper proposes a method for stable lane detection from images captured by camera sensors in diverse environments. First, the system utilizes a bilateral filter and multiscale retinex (MSR) with experimentally optimized set parameters to suppress image noise while increasing contrast. Subsequently, the Canny edge detector is employed to detect the edges of the lane candidates, followed by utilizing the Hough transform to make straight lines from the land candidate images. Then, using a proposed restriction system, only the two lines that the current vehicle is actively driving within are detected from the candidate lines. Furthermore, the lane position information from the previous frame is combined with the lane information from the current frame to correct the current lane position. The Kalman filter is then used to predict the lane position in the next frame. The proposed lane-detection method was evaluated in various scenarios, including rainy conditions, low-light nighttime environments with minimal street lighting, scenarios with interfering guidelines within the lane area, and scenarios with significant noise caused by water droplets on the camera. Both qualitative and quantitative experimental results demonstrate that the lane-detection method presented in this paper effectively suppresses noise and accurately detects the two active lanes during driving.

U-Net-Based Learning Using Enhanced Lane Detection with Directional Lane Attention Maps for Various Driving Environments

“…By converting from RGB to a different color space and performing image processing, such distortion can be prevented. Lee et al [23] proposed a method of preventing distortion by converting RGB to the CIELab space and then separating only the luminance channel for image processing. Lane markings are typically displayed in clear white or yellow colors on dark road backgrounds to ensure visibility in the driver's line of sight.…”

“…The luminance information in the image allows for measuring the overall brightness of the scene. Lee et al [23] proposed a method for determining the day and night in an image based on the measured average value, and then configuring parameters suitable for daytime and nighttime accordingly.…”

“…To some extent, it is possible to predict the angle of the lane lines in the road area where the vehicle is currently driving from the camera installed on the vehicle [23]. Accordingly, we set up filters to extract only the edge information of the lane lines in a specific direction (the directional edge filter) to emphasize both the left and right lane lines.…”