Camera-view supervision for bird's-eye-view semantic segmentation.

Front Big Data

AI Safety Laboratory, Department of Computer Science, The University of Texas at Dallas, Richardson, TX, United States.

Published: November 2024

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, leading to indirectly supervised and inaccurate camera-to-BEV projections. 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. Our model, evaluated on the nuScenes dataset, shows a 3.8% improvement in Intersection-over-Union (IoU) for vehicle segmentation and a 30-fold reduction in depth error compared to baselines, while maintaining competitive inference times of 32 FPS. This method offers more accurate and reliable BEVSS for real-time autonomous driving systems. The codes and implementation details and code can be found at https://github.com/bluffish/sucam.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11604745PMC
http://dx.doi.org/10.3389/fdata.2024.1431346DOI Listing

Publication Analysis

Top Keywords

bird's-eye-view semantic
8
semantic segmentation
8
feature extraction
8
camera-view supervision
4
supervision bird's-eye-view
4
segmentation
4
segmentation bird's-eye-view
4
segmentation bevss
4
bevss powerful
4
powerful crucial
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!