Elastic Interaction Energy-Informed Real-Time Traffic Scene Perception

TL;DR

This paper introduces EIEGSeg, a novel training strategy using elastic interaction energy loss for real-time traffic scene segmentation, significantly improving accuracy on small and complex objects for autonomous driving.

Contribution

The paper presents a simple, efficient topology-aware energy loss function that enhances segmentation accuracy, especially for fine-scale structures in traffic scenes.

Findings

Improved segmentation accuracy on Cityscapes, TuSimple, and CULane datasets.

Enhanced detection of small and irregular objects.

Better performance on lightweight, real-time networks.

Abstract

Urban segmentation and lane detection are two important tasks for traffic scene perception. Accuracy and fast inference speed of visual perception are crucial for autonomous driving safety. Fine and complex geometric objects are the most challenging but important recognition targets in traffic scene, such as pedestrians, traffic signs and lanes. In this paper, a simple and efficient topology-aware energy loss function-based network training strategy named EIEGSeg is proposed. EIEGSeg is designed for multi-class segmentation on real-time traffic scene perception. To be specific, the convolutional neural network (CNN) extracts image features and produces multiple outputs, and the elastic interaction energy loss function (EIEL) drives the predictions moving toward the ground truth until they are completely overlapped. Our strategy performs well especially on fine-scale structure, \textit{i.e.} small or irregularly shaped objects can be identified more accurately, and discontinuity issues on slender objects can be improved. We quantitatively and qualitatively analyze our method on three traffic datasets, including urban scene segmentation data Cityscapes and lane detection data TuSimple and CULane. Our results demonstrate that EIEGSeg consistently improves the performance, especially on real-time, lightweight networks that are better suited for autonomous driving.