IRDCLNet: Instance Segmentation of Ship Images Based on Interference Reduction and Dynamic Contour Learning in Foggy Scenes

doi:10.1109/TCSVT.2022.3155182

	IRDCLNet: Instance Segmentation of Ship Images Based on Interference Reduction and Dynamic Contour Learning in Foggy Scenes
	Sun, Yuxin 1,2; Su, Li 1,2; Luo, Yongkang 3; Meng, Hao 1,2; Zhang, Zhi 1,2; Zhang, Wen 1,2; Yuan, Shouzheng 1,2
刊名	IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
	2022-09-01
卷号	32 期号:9 页码:6029-6043
关键词	Marine vehicles Image segmentation Meteorology Feature extraction Interference Object detection Visualization Foggy scene ship instance segmentation interference reduction module dynamic contour learning
ISSN号	1051-8215
DOI	10.1109/TCSVT.2022.3155182
通讯作者	Su, Li(suli406@hrbeu.edu.cn)
英文摘要	Frequent bad weather at sea severely damages the quality of visual images captured by imaging equipment. Ship instance segmentation in adverse weather conditions remains a major challenge because of poor visibility at sea. Existing approaches for instance segmentation are primarily designed for clear days and rarely consider the aforementioned severe weather. Blurred ship objects can easily cause missed ship detection and decrease the instance segmentation performance on ship images, especially in the case of frequent fog at sea. To this end, we propose a ship instance segmentation framework (IRDCLNet) based on Interference Reduction and Dynamic Contour Learning in foggy scenes. The Interference Reduction Module is proposed to reduce the interference caused by fog and solves the problem of missed ship detection. Meanwhile, we present Dynamic Contour Learning to predict the overall contour of the blurred ships to assist in mask prediction. To handle the scarcity of ocean data in foggy weather, we build the Foggy ShipInsseg dataset, which contains 5,739 real and simulated foggy ship images with 10,900 fine instance mask annotations. Experiments on the Foggy ShipInsseg dataset show that our IRDCLNet outperforms the Mask R-CNN and CondInst baselines and achieves the state-of-the-art performance.
资助项目	National Key Research and Development Program of China[2019YFE0105400] ; Project of Intelligent Situation Awareness System for Smart Ship[MC-201920-X01]
WOS研究方向	Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000849300000027
资助机构	National Key Research and Development Program of China ; Project of Intelligent Situation Awareness System for Smart Ship
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50014]
专题	智能机器人系统研究
通讯作者	Su, Li
作者单位	1.Harbin Engn Univ, Coll Intelligent Syst Sci & Engn, Minist Educ, Harbin 150001, Peoples R China 2.Harbin Engn Univ, Key Lab Intelligent Technol & Applicat Marine Equ, Minist Educ, 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	Sun, Yuxin,Su, Li,Luo, Yongkang,et al. IRDCLNet: Instance Segmentation of Ship Images Based on Interference Reduction and Dynamic Contour Learning in Foggy Scenes[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,2022,32(9):6029-6043.
APA	Sun, Yuxin.,Su, Li.,Luo, Yongkang.,Meng, Hao.,Zhang, Zhi.,...&Yuan, Shouzheng.(2022).IRDCLNet: Instance Segmentation of Ship Images Based on Interference Reduction and Dynamic Contour Learning in Foggy Scenes.IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY,32(9),6029-6043.
MLA	Sun, Yuxin,et al."IRDCLNet: Instance Segmentation of Ship Images Based on Interference Reduction and Dynamic Contour Learning in Foggy Scenes".IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 32.9(2022):6029-6043.