Research of Lane Detection Method Based on Attention Mechanism

Abstract

Facing the problems of low accuracy and poor real-time performance in lane detection, a lane detection method based on deep learning was proposed.ENet, a lightweight semantic segmentation network, is used as the backbone of the detection method.In view of the slender characteristics of lane lines, an improved spatial attention module is introduced to enhance the ability to extract lane line features.Then the final detection result is obtained by post-processing operation.Compared with SCNN and ENet, the improved algorithm has better accuracy and meets the requirements of real-time detection.