Elastic Interaction Energy-Informed Real-Time Traffic Scene Perception

arXiv:2310.01449v2 Announce Type: replace
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 …

abstract accuracy arxiv autonomous autonomous driving cs.cv detection driving elastic energy inference lane detection objects pedestrians perception real-time recognition safety segmentation speed targets tasks traffic type urban visual