A New Ship Detection Method for Massive Data High-Resolution Remote Sensing Images

Abstract:

This paper proposes a new method for automatic ship targets detection in remote sensing images. The method uses adaptive segmentation algorithm for getting possible ship targets first, and then calculates Histograms of Oriented Gradient (HOG) feature to extract the structural information of ships, followed by supervised learning algorithm to identify the possible ship targets. Multi-scale sliding-window is used to handle targets with different scales. The experimental results prove that this new method has a good precision and robustness for most of the ship targets and give attention to the efficiency.

• Periodical: Advanced Materials Research (Volumes 532-533)
• Pages: 1105-1109
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.532-533.1105
• Online since: June 2012
• Authors: Hao Sun, Yu Li, Ge Liu, Hui Long, Hong Qi Wang
• Keywords: Histograms of Oriented Gradient (HOG), Image Process, Ship Detection, Support Vector Machine (SVM)

References

[1] N. Otsu. A threshold selection method from gray-level histograms [J] IEEE Transactions on Systems, Man and Cybernetics, Vol. 9, No. 1. (January 1979), pp.62-66.

DOI: 10.1109/tsmc.1979.4310076

[2] J.N. Kapura, P.K. Sahoob and A.K.C. Wong A new method for gray-level picture thresholding using the entropy of the histogram [J] Computer Vision, Graphics, and Image Processing, Volume 29, Issue 3, March 1985, Pages 273-285.

DOI: 10.1016/0734-189x(85)90125-2

[3] CHU Zhaoliang, WANG Qinghua, CHEN Hailin, XU Shoushi. Ship Auto Detection Method Based on Minimum Error Threshold Segmentation[J] Computer Engineering Vol. 33 No. 11 (2007).

[4] TANG Ya-bo; LIU Xiao-jun; XU Shou-shi Multilevel adaptive cluttering segmentation method for marine ship in remote sensing image[J] Computer Applications Vol. 25 pp.2126-2127 (2005).

[5] You Xiaojian Xu Shoushi Hou Lei A New Method for Ship Detection Based on Feature Fusion in Optical Image[J] Computer Engineering and Applications Vol. 41 pp.199-202 (2005).

[6] XIAO Li-ping; CAO Ju; GAO Xiao-ying Detection for ship targets in complicated background of sea and land Opto-Electronic Engineering Vol. 34 pp.6-10 (2007).

[7] TIAN Ming-hui; WAN Shou-hong; YUE Li-hua Ship Detection in Remote Sensing Images with Complex Sea Surface Background[J] Journal of Chinese Computer Systems Vol. 29 pp.2162-2166 (2008).

[8] FU Xiao-shan Removing Cloud from Remote Sensing Image Based on Gray Gradient[J] Bulletin of Surveying and Mapping Vol. 10 (2008).

[9] YE Qiu-guo; ZONG Jing-chun; LI Chuan; TENG Hui-zhong1 Removing Cloud and Mist From Remote Sensing Digital Images Based on Homographic Filtering[J]  Hydrographic Surveying and Charting Vol. 29, No. 3 (2009).

[10] Rohling, H.;  AEG-Telefunken  Radar CFAR Thresholding in Clutter and Multiple Target Situations[J] Aerospace and Electronic Systems, IEEE Transactions on Vol. AES-19 No. 4 pp.608-621 July (1983).

DOI: 10.1109/taes.1983.309350

[11] Navneet Dalal and Bill Triggs Histograms of Oriented Gradients for Human Detection. Computer Vision and Pattern Recognition July (2005).

DOI: 10.1109/cvpr.2005.177

[12] W. T. Freeman and M. Roth. Orientation histograms for hand gesture recognition. Intl. Workshop on Automatic Faceand Faceand Gesture- Recognition, IEEE Computer Society, Zurich, Switzerland, pages 296–301, June (1995).