Offshore Platform Extraction Using RadarSat-2 SAR Imagery: A Two-Parameter CFAR Method Based on Maximum Entropy

doi:10.3390/e21060556

	Offshore Platform Extraction Using RadarSat-2 SAR Imagery: A Two-Parameter CFAR Method Based on Maximum Entropy
	Wang, Qi 1; Zhang, Jing 1,2,3; Su, Fenzhen 1
刊名	ENTROPY
	2019-06-01
卷号	21 期号:6 页码:22
关键词	offshore platform extraction two-parameter CFAR maximum entropy Pearl River Estuary Basin
ISSN号	1099-4300
DOI	10.3390/e21060556
通讯作者	Su, Fenzhen(sufz@lreis.ac.cn)
英文摘要	The ability to determine the number and location of offshore platforms is of great significance for offshore oil spill monitoring and offshore oil and gas development. Considering the problem that the detection threshold parameters of the two-parameter constant false alarm rate (CFAR) algorithm require manual and repeated adjustment of the during the extraction of offshore platform targets, this paper proposes a two-parameter CFAR target detection method based on maximum entropy based on information entropy theory. First, a series of threshold parameters are obtained using the two-parameter CFAR algorithm for target detection. Then, according to the maximum entropy principle, the optimal threshold is estimated to obtain the target detection results of the possible offshore platform. Finally, the neighborhood analysis method is used to eliminate false alarm targets such as ships, and the final target of the offshore platform is obtained. In this study, we conducted offshore platform extraction experiments and an accuracy evaluation using data from the Pearl River Estuary Basin of the South China Sea. The results show that the proposed method for platform extraction achieves an accuracy rate of 97.5% and obtains the ideal offshore platform distribution information. Thus, the proposed method can objectively obtain the optimal target detection threshold parameters, greatly reduce the influence of subjective parameter setting on the extraction results during the target detection process and effectively extract offshore platform targets.
资助项目	National Natural Science Foundation of China[41890854]
WOS关键词	SHIP DETECTION ; SEGMENTATION ; FILTER
WOS研究方向	Physics
语种	英语
出版者	MDPI
WOS记录号	WOS:000475304200017
资助机构	National Natural Science Foundation of China
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/58172]
专题	中国科学院地理科学与资源研究所
通讯作者	Su, Fenzhen
作者单位	1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China 2.Lanzhou Jiaotong Univ, Fac Geomat, Lanzhou 730070, Peoples R China 3.Gansu Prov Engn Lab Natl Geog State Monitoring, 88 Anning Rd, Lanzhou 730070, Peoples R China
推荐引用方式 GB/T 7714	Wang, Qi,Zhang, Jing,Su, Fenzhen. Offshore Platform Extraction Using RadarSat-2 SAR Imagery: A Two-Parameter CFAR Method Based on Maximum Entropy[J]. ENTROPY,2019,21(6):22.
APA	Wang, Qi,Zhang, Jing,&Su, Fenzhen.(2019).Offshore Platform Extraction Using RadarSat-2 SAR Imagery: A Two-Parameter CFAR Method Based on Maximum Entropy.ENTROPY,21(6),22.
MLA	Wang, Qi,et al."Offshore Platform Extraction Using RadarSat-2 SAR Imagery: A Two-Parameter CFAR Method Based on Maximum Entropy".ENTROPY 21.6(2019):22.