Cross Dataset Analysis and Network Architecture Repair for Autonomous Car Lane Detection

TL;DR

This paper introduces ERFCondLaneNet, an improved lane detection network for autonomous vehicles that enhances detection of complex lane topologies while reducing model size and features, validated on multiple benchmarks.

Contribution

The paper proposes ERFCondLaneNet, a novel architecture that improves lane detection accuracy for complex topologies and reduces model complexity compared to existing methods.

Findings

ERFCondLaneNet performs comparably to ResNet-based models.

The new architecture reduces model size by 46%.

It uses 33% fewer features while maintaining accuracy.

Abstract

Transfer Learning has become one of the standard methods to solve problems to overcome the isolated learning paradigm by utilizing knowledge acquired for one task to solve another related one. However, research needs to be done, to identify the initial steps before inducing transfer learning to applications for further verification and explainablity. In this research, we have performed cross dataset analysis and network architecture repair for the lane detection application in autonomous vehicles. Lane detection is an important aspect of autonomous vehicles driving assistance system. In most circumstances, modern deep-learning-based lane recognition systems are successful, but they struggle with lanes with complex topologies. The proposed architecture, ERFCondLaneNet is an enhancement to the CondlaneNet used for lane identification framework to solve the difficulty of detecting lane lines with complex topologies like dense, curved and fork lines. The newly proposed technique was tested on two common lane detecting benchmarks, CULane and CurveLanes respectively, and two different backbones, ResNet and ERFNet. The researched technique with ERFCondLaneNet, exhibited similar performance in comparison to ResnetCondLaneNet, while using 33% less features, resulting in a reduction of model size by 46%.