Lane detection with Position Embedding

TL;DR

This paper introduces position embedding to enhance spatial features in lane detection, building on RESA, resulting in improved accuracy on the Tusimple dataset for autonomous driving applications.

Contribution

It proposes integrating position embedding into RESA to better capture spatial features, achieving state-of-the-art accuracy in lane detection.

Findings

Achieved 96.93% accuracy on Tusimple dataset

Enhanced spatial feature representation with position embedding

Improved lane detection performance over existing methods

Abstract

Recently, lane detection has made great progress in autonomous driving. RESA (REcurrent Feature-Shift Aggregator) is based on image segmentation. It presents a novel module to enrich lane feature after preliminary feature extraction with an ordinary CNN. For Tusimple dataset, there is not too complicated scene and lane has more prominent spatial features. On the basis of RESA, we introduce the method of position embedding to enhance the spatial features. The experimental results show that this method has achieved the best accuracy 96.93% on Tusimple dataset.