中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
MSFANet: A Light Weight Object Detector Based on Context Aggregation and Attention Mechanism for Autonomous Mining Truck

文献类型：期刊论文

作者Song, Ruiqi2,4; Ai, Yunfeng2,3; Tian, Bin2,4; Chen, Long2,4; Zhu, Fenghua2,4; Yao, Fei1
刊名IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
出版日期2023-03-01
卷号8期号:3页码:2285-2295
ISSN号2379-8858
关键词Feature extraction Object detection Autonomous vehicles Task analysis Detectors Semantics Real-time systems feature fusion object detection surface mine
DOI10.1109/TIV.2022.3221767
通讯作者Ai, Yunfeng(aiyunfeng@ucas.ac.cn)
英文摘要Accurate and reliable object detection is a fundamental component of perception system for autonomous driving. Specially, in some circumstances like autonomous driving in surface mine, there is a fact that the particularity of scene brings tremendous challenges for object detection with a series of problems caused by the multi-scale and camouflaged objects. In this paper, a multi-scale feature fusion and attention based multi-branches framework was proposed to improve the performance of object detection for above problems called MSFANet. In the proposed MSFANet, a multi-scale feature fusion module, which was used to capture the rich context features for multi-scale high level feature maps, and a multi-scale attention module, which was used to enhance the feature saliency of objects with different scales, were designed. What's more, to improve the performance of multi-scale object detection, we build 4 different prediction branches for large, medium small and smaller scale objects respectively. At last, we built our own dataset for automatic driving in surface mine called SurMine and test the model at our own datasets and KITTI benchmark. It achieved 82.7 mAP(%) and 92.57 mAP(%) in 32 36 ms on a TITAN RTX, compared to 80.2 mAP(%) and 87.83 mAP(%) in 28 similar to 34 ms by YOLOv7 on SurMine and KITTI benchmarks.
WOS关键词NEURAL-NETWORK ; VEHICLES
资助项目Key-Area Research and Development Program of Guangdong Province[2020B090921003] ; Key-Area Research and Development Program of Guangdong Province[2020B0909050001] ; Natural Science Foundation of Hebei Province[2021402011]
WOS研究方向Computer Science ; Engineering ; Transportation
语种英语
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号WOS:000981348100025
资助机构Key-Area Research and Development Program of Guangdong Province ; Natural Science Foundation of Hebei Province
源URL[http://ir.ia.ac.cn/handle/173211/53353]  
专题多模态人工智能系统全国重点实验室
通讯作者Ai, Yunfeng
作者单位1.North Automatic Control Technol Inst, Taiyuan 030006, Peoples R China
2.Waytous Inc, Qingdao 266109, Peoples R China
3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China
4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Song, Ruiqi,Ai, Yunfeng,Tian, Bin,et al. MSFANet: A Light Weight Object Detector Based on Context Aggregation and Attention Mechanism for Autonomous Mining Truck[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,2023,8(3):2285-2295.
APA Song, Ruiqi,Ai, Yunfeng,Tian, Bin,Chen, Long,Zhu, Fenghua,&Yao, Fei.(2023).MSFANet: A Light Weight Object Detector Based on Context Aggregation and Attention Mechanism for Autonomous Mining Truck.IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,8(3),2285-2295.
MLA Song, Ruiqi,et al."MSFANet: A Light Weight Object Detector Based on Context Aggregation and Attention Mechanism for Autonomous Mining Truck".IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 8.3(2023):2285-2295.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。