Lane Detection Image Processing Algorithm based on FPGA for Intelligent Vehicle

Abstract

Self-driving cars are of great significance in reducing traffic accidents, traffic congestion, energy conservation and environmental protection, etc. Real-time lane detection is the basic function of autonomous driving perception system. Lane detection based on image processing is one of the main methods in lane detection at present, and there are many kinds of detection algorithms. However, the problem is that the algorithm model is complex and the computation amount is large, most of which can only be realized on the CPU+GPU platform, resulting in low cost performance, high power consumption and large volume, which is not suitable for vehicle-mounted requirements. In order to meet the needs of real-time lane detection performance, power consumption and flexibility requirements. In this paper, based on FPGA development platform, lane line detection algorithm based on image processing and deep learning is designed to achieve the fast lane line detection effect of structured roads, speed up to 104 FPS above. And in view of the road scene shadow, the method proposed in this paper can provide better detection result.