跳到主要导航 跳到搜索 跳到主要内容

A Lightweight YOLOv8-Based Camera Backbone for Efficient BEVFusion

  • Yifan Zhu
  • , Hui Jin*
  • *此作品的通讯作者
  • Beijing Institute of Technology

科研成果: 书/报告/会议事项章节 › 会议稿件 › 同行评审

摘要

To address the high computational cost and limited real-time performance of multimodal 3D perception systems, this paper explores camera backbone lightweight design for efficient multi-view feature extraction. A lightweight YOLOv8-based backbone is first constructed through structural optimization, and then integrated into the BEVFusion framework by replacing the original Swin Transformer-based camera encoder without modifying the overall fusion pipeline. On the nuScenes benchmark, the proposed backbone demonstrates competitive 3D detection accuracy alongside improved inference efficiency, despite requiring considerably fewer parameters and lower computational cost. This confirms that the method achieves a favorable balance between performance and efficiency, making it particularly suitable for real-time autonomous driving scenarios where hardware resources are constrained.

源语言英语
主期刊名Proceedings of 2026 2nd International Conference on Artificial Intelligence and Computational Intelligence, AICI 2026
出版商Association for Computing Machinery, Inc
页228-235
页数8
ISBN(电子版)9798400722790
DOI
出版状态已出版 - 19 8月 2026
活动2026 2nd International Conference on Artificial Intelligence and Computational Intelligence, AICI 2026 - Zhengzhou, 中国
期限: 6 2月 2026 → 8 2月 2026

丛书

姓名Proceedings of 2026 2nd International Conference on Artificial Intelligence and Computational Intelligence, AICI 2026

会议

会议2026 2nd International Conference on Artificial Intelligence and Computational Intelligence, AICI 2026
国家/地区中国
市Zhengzhou
时期6/02/26 → 8/02/26

学术指纹

探究 'A Lightweight YOLOv8-Based Camera Backbone for Efficient BEVFusion' 的科研主题。它们共同构成独一无二的学术指纹。

引用此