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
  5. 互联网大数据与安全信息学研究中心
Cross-Modality 3D Multiobject Tracking Under Adverse Weather via Adaptive Hard Sample Mining

文献类型：期刊论文

作者Qiao, Lifeng1; Zhang, Peng1; Liang, Yunji1; Yan, Xiaokai1; Huangfu, Luwen2,3; Zheng, Xiaolong1,4,5; Yu, Zhiwen1
刊名IEEE INTERNET OF THINGS JOURNAL
出版日期2024-07-15
卷号11期号:14页码:25268-25282
关键词Three-dimensional displays Point cloud compression Meteorology Laser radar Feature extraction Robustness Trajectory Adverse weather hard sample mining multimodality object tracking
ISSN号2327-4662
DOI10.1109/JIOT.2024.3392844
通讯作者Liang, Yunji(liangyunji@nwpu.edu.cn)
英文摘要3-D multiobject tracking (MOT) is an important task in numerous applications, including robotics and autonomous driving. Nevertheless, existing 3-D MOT solutions suffer from significant performance degradation under adverse weather conditions. Inspired by the fact that hard objects (e.g., missed detections or wrongly-associated objects) are more constructive to performance improvement, in this article, we leverage hard samples for robust 3-D MOT in adverse weather conditions. Specifically, we implement a cross-modality 3-D MOT framework to learn the 3-D region proposals from point clouds and RGB images, respectively. To minimize the risk of missed detection and wrong association, we introduce an adaptive hard sample mining scheme to align the 3-D region proposals provided by two modalities. We quantify the hard level by comparing the confidence values of the same object in the two branches and their distance in the embedding space. Meanwhile, we dynamically adjust the weights of hard samples during training to enhance the representation learning for robust 3-D MOT. Extensive experimental results showcase that our proposed solution effectively mitigates the missed detection and reduces wrong association with good generalization.
WOS关键词OBJECT DETECTION ; LIDAR ; PERFORMANCE ; CNN
资助项目Natural Science Foundation of China[72225011] ; Natural Science Foundation of China[62372378]
WOS研究方向Computer Science ; Engineering ; Telecommunications
语种英语
WOS记录号WOS:001271416600059
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/59333]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_互联网大数据与安全信息学研究中心
通讯作者Liang, Yunji
作者单位1.Northwestern Polytech Univ, Sch Comp Sci, Xian 710129, Peoples R China
2.San Diego State Univ, Fowler Coll Business, San Diego, CA 92182 USA
3.San Diego State Univ, Ctr Human Dynam Mobile Age, San Diego, CA 92182 USA
4.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China
5.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Qiao, Lifeng,Zhang, Peng,Liang, Yunji,et al. Cross-Modality 3D Multiobject Tracking Under Adverse Weather via Adaptive Hard Sample Mining[J]. IEEE INTERNET OF THINGS JOURNAL,2024,11(14):25268-25282.
APA Qiao, Lifeng.,Zhang, Peng.,Liang, Yunji.,Yan, Xiaokai.,Huangfu, Luwen.,...&Yu, Zhiwen.(2024).Cross-Modality 3D Multiobject Tracking Under Adverse Weather via Adaptive Hard Sample Mining.IEEE INTERNET OF THINGS JOURNAL,11(14),25268-25282.
MLA Qiao, Lifeng,et al."Cross-Modality 3D Multiobject Tracking Under Adverse Weather via Adaptive Hard Sample Mining".IEEE INTERNET OF THINGS JOURNAL 11.14(2024):25268-25282.

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。