ESA Earth Home Missions Data Products Resources Applications
EO Data Access
How to Apply
How to Access
Site Map
Frequently asked questions
Terms of use
Contact us



Comparison and Evaluation for Ship Target Detection Algorithms with ENVISAT ASAR

Xi ZHANG(1), Jie ZHANG(2) and Yonggang JI(2)

(1) Ocean University of China, NO.5 Yushan Road, Qingdao, 266071, China
(2) First Institute of Oceanography,SOA, NO.6 Xianxialing Road,High-Tech Park, Qingdao,266061, China


Many ship target detection algorithms with space-based SAR imagery have been developed. The typical algorithms include CFAR algorithm, wavelet transform algorithm and cross correlation algorithm. Different algorithm has its own characteristic, and can be used in different conditions. In this paper, three detection algorithms are used to detect ship targets on a common set of ENVISAT ASAR images. Then the detection results of those algorithms are compared with in situ data and with each other to analyze the detection rate and the application scope of each algorithm. From the comparison, it can be shown that choice of an appropriate threshold probably constitutes one of the major drawbacks of CFAR algorithm, and CFAR algorithm is not suitable in coarse sea state. On the contrary, the wavelet transform algorithm and cross correlation algorithm have great robustness and can extract weak signatures of ship target which are easy to be disturbed by background noise. But the two algorithms would miss some details information of vessel structure, and the structure details are very important to future vessel classification.


Workshop poster

Keywords: ESA European Space Agency - Agence spatiale europeenne, observation de la terre, earth observation, satellite remote sensing, teledetection, geophysique, altimetrie, radar, chimique atmospherique, geophysics, altimetry, radar, atmospheric chemistry