VISION BASED LANE DETECTION TECHNIQUES AND DRIVER STATE MONITORING FOR ADAS

Abstract

The present research work aims to develop Advanced Driver Assistance System (ADAS) features, those are namely vision-based lane detection and tracking techniques, and driver state monitoring system. Lane feature extraction is a primary step for lane detection in ADAS. In connection with the lane feature extraction, an edge map feature generation technique based on a two-dimensional discrete Fourier transform (DFT) with a sliding window is proposed for road images to detect the lanes and road markings. The 2 × 2 sliding window DFT based kernels with bin indices (k1, k2 = 0, 1) for horizontal edge detection and (k1, k2 = 1, 0) for vertical edge detection have been proposed. The 2-D sliding discrete Fourier transform (SDFT)-based edge detector has been proven to be more efficient for lane and road marking images in comparison with conventional edge detectors and cellular neural network-based edge detectors. In the presence of noise and various signal-to-noise ratio conditions, the horizontal and vertical edges have been efficiently recovered with good Pratt figure of merit (PFOM) without applying any pre-processing, noise removal process, and post-processing techniques. The PFOM was found to be quite stable, with a wide threshold range for various noise levels. The consistent performance of the proposed edge detector is proved with MSE and PSNR determination of detected edge images. Moreover, the proposed 2-D SDFT-based edge detector performs well in developing edge maps for real-time road videos. The systemon- chip implementation of the 2-D SDFT edge detector on Cyclone IV FPGA chip is also carried out for detecting the lane and road markings.