A Novel Ship Wake Detection Algorithm Based on WTHT and Radon Transform

ZHAO Moxin; ZHANG Yunhua; DONG Xiao; LI Dong; YANG Jiefang

doi:10.11728/cjss2021.05.836

A Novel Ship Wake Detection Algorithm Based on WTHT and Radon Transform

doi: 10.11728/cjss2021.05.836

1. Key Laboratory of Microwave Remote Sensing, National Space Science Center, Chinese Academy of Sciences, Beijing 100190;
2. University of Chinese Academy of Sciences, Beijing 100049

基金项目:

Supported by National Key R&D Program of China (2016YFC1401004) along with China Manned Space Program

详细信息

作者简介:
ZHANG Yunhua,E-mail:zhangyunhua@mirslab.cn

中图分类号: TN 959.74
计量
- 文章访问数: 393
- HTML全文浏览量: 48
- PDF下载量: 37
- 被引次数: 0
出版历程
- 收稿日期: 2020-03-16
- 修回日期: 2021-01-10
- 刊出日期: 2021-09-15

A Novel Ship Wake Detection Algorithm Based on WTHT and Radon Transform

1. Key Laboratory of Microwave Remote Sensing, National Space Science Center, Chinese Academy of Sciences, Beijing 100190;
2. University of Chinese Academy of Sciences, Beijing 100049

Funds:

Supported by National Key R&D Program of China (2016YFC1401004) along with China Manned Space Program

More Information

Author Bio:
ZHANG Yunhua,E-mail:zhangyunhua@mirslab.cn

摘要

摘要: This paper proposes a novel ship wake detection algorithm based on the White Top-hat Transform (WTHT) and the Radon transform, which aims to improve the contrast between the ship wake and the background so as to improve the detection performance on Synthetic Aperture Radar (SAR) images. The proposed algorithm includes two major processes, and one is to improve the contrast and another one is to locate the ship wake. In high sea state conditions, the contrast of ship wake and background can be very low, which makes it difficult to detect. In the first step, the proposed contrast improvement algorithm is applied to improving the contrast which helps for improving the detection performance. An attribute filter based on edge detection result is adopted here. In the second step the contrast improved image is transformed into the Radon domain followed by peak extraction process to find the wake, the WTHT is used once more in this step. Finally, in the last step, the wake is overlapped on the original image. Experimental results on Tiangong-2 Interferometric Imaging Radar Altimeter (InIRA) images are presented and compared with that obtained by using the classical algorithm, and in this way, the better performance of our algorithm is demonstrated.
- White Top-hat Transform (WTHT) /
- Radon transform /
- SAR image /
- Ship wake /
- Contrast improvement /
- InIRA
Abstract: This paper proposes a novel ship wake detection algorithm based on the White Top-hat Transform (WTHT) and the Radon transform, which aims to improve the contrast between the ship wake and the background so as to improve the detection performance on Synthetic Aperture Radar (SAR) images. The proposed algorithm includes two major processes, and one is to improve the contrast and another one is to locate the ship wake. In high sea state conditions, the contrast of ship wake and background can be very low, which makes it difficult to detect. In the first step, the proposed contrast improvement algorithm is applied to improving the contrast which helps for improving the detection performance. An attribute filter based on edge detection result is adopted here. In the second step the contrast improved image is transformed into the Radon domain followed by peak extraction process to find the wake, the WTHT is used once more in this step. Finally, in the last step, the wake is overlapped on the original image. Experimental results on Tiangong-2 Interferometric Imaging Radar Altimeter (InIRA) images are presented and compared with that obtained by using the classical algorithm, and in this way, the better performance of our algorithm is demonstrated.
- White Top-hat Transform (WTHT) /
- Radon transform /
- SAR image /
- Ship wake /
- Contrast improvement /
- InIRA

HTML全文

参考文献(20)

[1]	KARAKUS O, RIZAEV I, ACHIM A. Ship wake detection in SAR images via sparse regularization[J]. IEEE Trans. Geosci. Remote Sens., 2020, 58(3):1665-1677
[2]	ELDHUSET K. An automatic ship and ship wake detection system for spaceborne SAR images in coastal regions[J]. IEEE Trans. Geosci. Remote Sens., 1996, 34(4):1010-1019
[3]	GRAZIANO M D, D'ERRICO M, RUFINO G. Wake component detection in X-band SAR images for ship heading and velocity estimation[J]. Remote Sens., 2016, 8(498):1-15
[4]	GRAZIANO M D, D'ERRICO M, RUFINO G. Ship heading and velocity analysis by wake detection in SAR images[J]. Acta Astronaut., 2016, 128:72-82
[5]	JIN Yaqiu, WANG Shiqing. An algorithm for ship wake detection from the SAR images using the Radon transform and morphological image processing[J]. J. Syst. Eng. Elect., 2001, 12(4):7-12
[6]	REY M T, TUNALEY J K, FOLINSBEE J T. Application of radon transform techniques to wake detection in Seasat-A SAR images[J]. IEEE Trans. Geosci. Remote Sens., 1990, 28(4):553-560
[7]	COURMONTAGNE P. An improvement of ship wake detection based on the radon transform[J]. Signal Proc., 2005, 85(8):1634-1654
[8]	RADON J. On the determination of functions from their integral values along certain manifolds[J]. IEEE Trans. Med. Imag., 1986, 5(4):170-176
[9]	BIONDI Filippo. Low-rank plus sparse decomposition and localized radon transform for ship-wake detection in synthetic aperture radar images[J]. IEEE Geosci. Remote Sens. Lett., 2018, 15(1):117-121
[10]	AI Jiaqiu, QI Xiangyang, YU Weidiong, et al. A novel ship wake CFAR detection algorithm based on SCR enhancement and normalized Hough transform[J]. IEEE Geosci. Remote Sens. Lett., 2011, 8(4):681-685
[11]	COPELAND A C, RAVICHANDRAN G, TRIVEDI M M. Localized Radon transform-based detection of ship wakes in SAR images[J]. IEEE Trans. Geosci. Remote Sens., 1995, 33(1):35-45
[12]	KUO Jinmin, CHEN K. The application of wavelets correlator for ship wake detection in SAR images[J]. IEEE Trans. Geosci. Remote Sens., 2003, 41(6):1506-1511
[13]	YANG Guozheng, YU Jing, XIAO Chuangbai, et al. Ship wake detection for SAR images with complex backgrounds based on morphological dictionary learning[C]//2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Shanghai:IEEE, 2016:1896-1900
[14]	GONZALEZ R C, WOODS R E. Morphological Image Processing[M]. Digital Image Processing, 3rd ed. USA:Prentice-Hall, 2008:649-709
[15]	LI Yong, YONG Bin, WU Huayi, et al. Filtering airborne lidar data by modified white top-hat transform with directional edge constraints[J]. Photogramm. Eng. Remote Sens., 2014, 80(2):133-141
[16]	WANG Guoqing, WANG Jun, LI Ming, et al. Hand vein image enhancement based on multi-scale top-hat transform[J]. Cybernet. Inform. Technol., 2016, 16(2):125-134
[17]	BAI Xiangzhi, ZHOU Fugen, XUE Bindang. Multiple linear feature detection through top-hat transform by using multi linear structuring elements[J]. Optik, 2012, 123(22):2043-2049
[18]	ZHANG Yunhua, DONG Xiao, SHI Xiaojin, et al. Demonstration of ocean target detection by Tiangong-2 interferometric imaging radar altimeter[C]//201822nd International Microwave and Radar Conference (MIKON). Poznan:IEEE, 2018:261-264
[19]	LEE J S. Refined filtering of image noise using local statistics[J]. Comput. Vision, Graph. Image Proc., 1981, 15:380-389
[20]	On-Line Source. Available online[OL].[2020-03-01]. https://stackoverflow.com/questions/43852754/find-peak-regions-in-2d-data