AUTHOR=Yang Bowen , Yu LinLin , Chen Feng TITLE=Camera-view supervision for bird's-eye-view semantic segmentation JOURNAL=Frontiers in Big Data VOLUME=7 YEAR=2024 URL=https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2024.1431346 DOI=10.3389/fdata.2024.1431346 ISSN=2624-909X ABSTRACT=
Bird's-eye-view Semantic Segmentation (BEVSS) is a powerful and crucial component of planning and control systems in many autonomous vehicles. Current methods rely on end-to-end learning to train models. We propose a novel method of supervising feature extraction with camera-view depth and segmentation information, which improves the quality of feature extraction and projection in the BEVSS pipeline. Through extensive empirical evaluation, we demonstrate that our approach achieves superior performance compared to existing methods, improving the robustness and reliability of BEVSS for autonomous driving systems. Our method achieves very competitive inference and training computational cost when compared to other real-time BEVSS methods, while maintaining superior accuracy. The codes and implementation details and code can be found at https://github.com/bluffish/sucam.