Currently ship target detection in optical remote sensing image accuracy rate is not high and lack of quantitative analysis. In this paper, the using of high resolution optical remote sensing data, use object-oriented image feature extraction technique, combine single threshold detection and constant false alarm rate (CRAF) detection model, and suggest an improved single threshold ship targeting method, using the target and background area ratio (TBR) maximum guidelines extracts the ship's latitude and longitude, aspect ratio and the main direction. Using the object-oriented image feature extraction technique to detect GF-1 data from different time periods, finally, ship identification rate of over 90%, the ship features information accurate rate of over 80%. Comparing with traditional methods, this method has the advantages on ship identification accuracy and quantitative analysis. The study provides a new ship detection method for marine traffic regulation. At the same time, demonstrating the ability of high-resolution optical remote sensing imaging in ship detection.
[1]
Ali Olfat,et al.
CFAR detection for multistatic radar
,
2008,
2008 International Radar Symposium.
[2]
Hui Lin,et al.
Feature extraction for high-resolution imagery based on human visual perception
,
2013
.
[3]
Laurent Najman,et al.
A complete processing chain for ship detection using optical satellite imagery
,
2010
.
[4]
Peter F. McGuire,et al.
Automatic Target Recognition in Synthetic Aperture Radar Imagery: A State-of-the-Art Review
,
2016,
IEEE Access.
[5]
Tianxu Zhang,et al.
Ship target detection and tracking in cluttered infrared imagery
,
2011
.
[6]
Gilbert Laporte,et al.
A heuristic for the multi-satellite, multi-orbit and multi-user management of Earth observation satellites
,
2007,
Eur. J. Oper. Res..
[7]
Changming Sun,et al.
Iterative infrared ship target segmentation based on multiple features
,
2014,
Pattern Recognit..