Work

EdgeCaseDNet: An enhanced detection architecture for edge case perception in autonomous driving

Year: 2025

Type: article

Abstract: Autonomous driving perception systems still encounter significant challenges in edge scenarios involving multi-scale target changes and adverse weather, which seriously compromise detection reliability. To address this issue, we introduce a novel edge case dataset that extends existing benchmarks by capturing extreme road conditions (fog, rain, snow, nighttime et al.) with precise annotations, and develop EdgeCaseDNet as an optimized object-detection framework. EdgeCaseDNet's architecture extends YOLOv8 through four synergistic innovations: (1) a Haar_HGNetv2 backbone that enables hierarchical feature extraction with enhanced long-range dependencies, (2) an asymptotic feature pyramid network for context-aware multi-scale fusion, (3) a hybrid partial depth-wise separable convolution module, and (4) Wise-IoU loss optimization for accelerated convergence. Comprehensive evaluations demonstrated the superiority of EdgeCaseDNet over YOLOv8, achieving improvements of +10.6% in mAP@50, and +8.4% in mAP@[.5:.95]. All the relevant codes are available at https://github.com/yutianku/EdgeCaseDNet.

Source: PLoS ONE

DOI: 10.1371/journal.pone.0338638

Authors: Yin Lei, Chen Shan, Wancheng Ge

Institution: Tongji University

Language: English

Topic: Advanced Neural Network Applications

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

SDG: Sustainable cities and communities

Open Access status: gold

Estimated APC paid: $2,382