Remote Sensing Object Detection Based on Lightweight YOLO-V4

Keng Li*, Yunfei Cao, He Chen

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

The remote sensing object detection algorithms based on deep learning have high detection performances, but the network structures are too complexity to meet the real-time processing requirements in on-board remote sensing object detection. In order to solve this problem, we proposed a lightweight YOLO-v4 network, which is 76% smaller than the original YOLO-v4. As for the decrease of lightweight network's accuracy, we adopted the general instance distillation algorithm, which used the original YOLO-v4 network as the teacher network and whose detection accuracy achieved 2.1% mAP gain.

源语言英语
主期刊名7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering
编辑Tao Zhang
出版商SPIE
ISBN(电子版)9781510656437
DOI
出版状态已出版 - 2022
活动7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering - Xishuangbanna, 中国
期限: 18 3月 202220 3月 2022

出版系列

姓名Proceedings of SPIE - The International Society for Optical Engineering
12294
ISSN(印刷版)0277-786X
ISSN(电子版)1996-756X

会议

会议7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering
国家/地区中国
Xishuangbanna
时期18/03/2220/03/22

指纹

探究 'Remote Sensing Object Detection Based on Lightweight YOLO-V4' 的科研主题。它们共同构成独一无二的指纹。

引用此