A Robust Deep Affinity Network for Multiple Ship Tracking | |
Zhang, Wen1,2; He, Xujie1,2; Li, Wanyi3; Zhang, Zhi1,2; Luo, Yongkang3; Su, Li1,2; Wang, Peng3 | |
刊名 | IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT |
2021 | |
卷号 | 70页码:20 |
关键词 | Complex marine scenes joint global region modeling (JGRM) module marine surveillance motion-matching optimization (MMO) module multiple ship tracking (MST) |
ISSN号 | 0018-9456 |
DOI | 10.1109/TIM.2021.3077679 |
通讯作者 | He, Xujie(hexujie@hrbeu.edu.cn) |
英文摘要 | Multiple ship tracking (MST) is an important task in marine surveillance and ship situational awareness systems. Considerable work has been conducted on multiple object tracking in recent years, but it has focused primarily on pedestrians and automobiles, leaving a gap in studies on MST due to the particularities of complex marine scenes, such as ship scale variations, the long-tailed distribution of ships, and long-term occlusions caused by ship movements. In this article, we present a robust deep affinity network (RoDAN) for MST. To overcome the above difficulties in MST, we start with the basic deep affinity network (DAN) and improve it in three aspects: scale, region, and motion. For the scale dimension, we integrate an atrous spatial pyramid pooling (ASPP) module to improve the modeling ability for multiscale ships. For the region dimension, we propose the joint global region modeling (JGRM) module, which further strengthens the modeling ability of DAN and exploit it to overcome the long- tailed distribution property of ships. For the motion dimension, we propose the motion-matching optimization (MMO) module to fine-tune the tracking results and make our tracker more robust, less reliant on the front-end detector, and ameliorate long-term occlusions. The experimental results demonstrate that our MST method outperforms the state-of-the-art methods. In particular, it reduces the number of ID switches (IDSs) and trajectory fragmentations (FMs), achieving holistically preferable performance. Meanwhile, our method achieves a comparable speed. |
资助项目 | Development Project of Ship Situational Intelligent Awareness System[MC-201920-X01] ; National Natural Science Foundation of China[61771471] |
WOS关键词 | OBJECT DETECTION ; LOW-RANK ; MOTION |
WOS研究方向 | Engineering ; Instruments & Instrumentation |
语种 | 英语 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
WOS记录号 | WOS:000677581700015 |
资助机构 | Development Project of Ship Situational Intelligent Awareness System ; National Natural Science Foundation of China |
内容类型 | 期刊论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/45572] |
专题 | 智能机器人系统研究 |
通讯作者 | He, Xujie |
作者单位 | 1.Harbin Engn Univ, Minist Educ, Key Lab Intelligent Technol & Applicat Marine Equ, Harbin 150001, Peoples R China 2.Harbin Engn Univ, Coll Intelligent Syst Sci & Engn, Harbin 150001, Peoples R China 3.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Wen,He, Xujie,Li, Wanyi,et al. A Robust Deep Affinity Network for Multiple Ship Tracking[J]. IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,2021,70:20. |
APA | Zhang, Wen.,He, Xujie.,Li, Wanyi.,Zhang, Zhi.,Luo, Yongkang.,...&Wang, Peng.(2021).A Robust Deep Affinity Network for Multiple Ship Tracking.IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT,70,20. |
MLA | Zhang, Wen,et al."A Robust Deep Affinity Network for Multiple Ship Tracking".IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 70(2021):20. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论