Jointly Learning Spatial, Angular, and Temporal Information for Enhanced Lane Detection

TL;DR

This paper presents a new deep learning approach that combines spatial, angular, and temporal data from light field imaging to significantly improve lane detection accuracy in challenging driving conditions.

Contribution

It introduces a novel integration of light field representations with LSTM and CNN architectures for enhanced lane detection performance.

Findings

Superior lane detection accuracy over traditional methods

Effective use of light field data in deep learning models

Potential to advance autonomous vehicle perception systems

Abstract

This paper introduces a novel approach for enhanced lane detection by integrating spatial, angular, and temporal information through light field imaging and novel deep learning models. Utilizing lenslet-inspired 2D light field representations and LSTM networks, our method significantly improves lane detection in challenging conditions. We demonstrate the efficacy of this approach with modified CNN architectures, showing superior per- formance over traditional methods. Our findings suggest this integrated data approach could advance lane detection technologies and inspire new models that leverage these multidimensional insights for autonomous vehicle percep- tion.