基于增強指數(shù)加權(quán)均值比的SAR圖像邊緣檢測算法

胡炎; 單子力; 高峰

doi:10.11999/JEIT170806

基于增強指數(shù)加權(quán)均值比的SAR圖像邊緣檢測算法

doi: 10.11999/JEIT170806

基金項目:

中國電子科技集團公司航天信息應(yīng)用技術(shù)重點實驗室開放基金(EX166290025)

計量
- 文章訪問數(shù): 1561
- HTML全文瀏覽量: 268
- PDF下載量: 154
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2017-08-14
- 修回日期: 2018-02-01
- 刊出日期: 2018-05-19

Edge Detection Algorithm for SAR Image Based on Enhanced ROEWA

Funds:

The Open Fundation of CETC Key Laboratory of Aerospace Information Applications (EX166290025)

摘要

摘要: 研究學(xué)者們認為指數(shù)加權(quán)均值比(ROEWA)算子存在無法計算SAR圖像邊緣方向的缺陷。為此，進行了一些通過方向濾波器為ROEWA算法施加方向的工作。該文對ROEWA算法進行了深入的探討和分析，通過對ROEWA算法卷積過程的進一步推導(dǎo)，獲得了ROEWA算法像素級的觀測公式。根據(jù)推導(dǎo)結(jié)果，提出了一種增強的ROEWA(EROEWA)邊緣檢測算法。首先，利用新的卷積策略將ROEWA的公式項解耦，獲得了4個方向的指數(shù)加權(quán)均值；然后把SAR圖像旋轉(zhuǎn)45，再利用新的卷積策略獲取額外的4個方向的指數(shù)加權(quán)均值；最后，將8個方向的指數(shù)加權(quán)均值表示成8個矢量，通過矢量合成求出邊緣強度和邊緣方向。實驗結(jié)果表明，提出的EROEWA算法不僅具有優(yōu)秀的邊緣方向計算能力，與ROEWA算法相比，邊緣強度的提取也有顯著的增強效果。
- 指數(shù)加權(quán)均值比 /
- 觀測公式 /
- 矢量 /
- 增強指數(shù)加權(quán)均值比
Abstract: Researchers generally consider that Ratio Of Exponentially Weighted Averages (ROEWA) can not calculate the edge directions of SAR images. Therefore, some directional filters are used to add directions to ROEWA. In this paper, an Enhanced ROEWA (EROEWA) algorithm is proposed. Through the further derivation of the ROEWA algorithm convolution process, the pixel-level observation formula of ROEWA algorithm is obtained. First, a new convolution strategy is used to decouple the ROEWA formula to obtain exponentially weighted averages over the four directions. Second, the SAR images are rotated by 45 and exponentially weighted averages of the four additional directions are calculated. Finally, exponentially weighted averages of eight directions are expressed as eight vectors, and edge intensity and direction are solved by vector synthesis. Experimental results show that the EROEWA has a significant enhancement effect on the edge intensity and the direction.
- Ratio Of Exponentially Weighted Averages (ROEWA) /
- Observation formula /
- Vector /
- Enhanced Ratio Of Exponentially Weighted Averages (EROEWA)

HTML全文

參考文獻(26)

劉偉, 陳建宏, 曾陽帆, 等. 基于混合模型的多尺度水平集高分辨率SAR圖像水體分割[J]. 信息工程大學(xué)學(xué)報, 2016, 17(2): 178-183.

LIU Wei, CHEN Jianhong, ZENG Yangfan, et al. Water segmentation in high resolution SAR images using multi-scale level set method based on hybrid model[J]. Journal of Information Engineering University, 2016, 17(2): 178-183.

ZHANG Xiaoqiang, DONG Ganggang, XIONG Boli, et al. Refined segmentation of ship target in SAR images based on GVF snake with elliptical constraint[J]. Remote Sensing Letters, 2017, 8(8): 791-800. doi: 10.1080/2150704X.2017. 1327124.

CHANGLEI Dongye and ZHENG Yongguo. An efficient global minimization model for synthetic aperture radar image segmentation[J]. Journal of Computational and Theoretical Nanoscience, 2016, 13(3): 1846-1851. doi: 10.1166/jctn.2016. 5122.

吳鵬, 于秋則, 閔順新, 等. 魯棒KAZE算法的SAR圖像配準(zhǔn)[J]. 科學(xué)技術(shù)與工程, 2016, 16(28): 101-109. doi: 10.3969/j.issn.1671- 1815.2016.28.018.

WU Peng, YU Qiuze, MIN Shunxin, et al. Robust SAR image registration based on KAZE algorithm[J]. Science Technology and Engineering, 2016, 16(28): 101-109. doi: 10.3969/j.issn.1671- 1815.2016.28.018.

張巖, 李建增, 李德良, 等. 基于特征的遙感圖像匹配技術(shù)研究[J].無線電工程, 2016, 46(2): 61-64. doi: 10.3969/j.issn. 1003-3106.2016.02.15.

ZHANG Yan, LI Jianzeng, LI Deliang, et al. Research of remote sensing image matching based on key points[J]. Radio Engineering, 2016, 46(2): 61-64. doi: 10.3969/j.issn.1003- 3106.2016.02.15.

TOUZI R, LOPES A, and BOUSQUET P. A statistical and geometrical edge detector for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 1988, 26(6): 764-773. doi: 10.1109/36.7708.

FJORTOFT R, LOPES A, MARTHON P, et al. An optimal multidege detector for SAR image segmentation[J]. IEEE Transactions on Geoscience and Remote Sensing, 1998, 36(3): 793-802. doi: 10.1109/36.673672.

劉夯, 何政偉, 趙銀兵, 等. SAR圖像ROEWA邊緣檢測器的改進[J]. 遙感學(xué)報, 2017, 21(2): 273-279.

LIU Hang, HE Zhengwei, ZHAO Yinbing, et al. The improvement of SAR picture edge detector[J]. Journal of Remote Sensing, 2017, 21(2): 273-279.

安成錦, 辛玉林, 陳曾平. 基于改進ROEWA算子的SAR圖像邊緣檢測方法[J].中國圖象圖形學(xué)報, 2011, 16(8): 1484-1488.

AN Chengjin, XIN Yulin, and CHEN Zengping. Edge detection algorithm for SAR image based on improved ROEWA[J]. Journal of Image and Graphics, 2011, 16(8): 1484-1488.

楊道蓮, 魯昌華, 張金良, 等. 基于ROEWA與Hough變換的SAR圖像邊緣檢測[J]. 電子測量與儀器學(xué)報, 2013, 27(6): 543-547. doi: 10.3724/SP.J.1187.2013.00543.

YANG Daolian, LU Changhua, ZHANG Jinliang, et al. Edge detection in SAR images based on ROEWA and Hough transform[J]. Journal of Electronic Measurment and Instrument, 2013, 27(6): 543-547. doi: 10.3724/SP.J.1187. 2013.00543.

劉帥奇, 胡紹海, 肖揚, 等. 基于局部混合濾波的SAR圖像邊緣檢測[J]. 電子與信息學(xué)報, 2015, 35(5): 1120-1127. doi: 10.3724/SP.J.1146.2012.01198.

LIU Shuaiqi, HU Shaohai, XIAO Yang, et al. SAR image edge detection based on local hybrid filter[J]. Journal of Electronics Information Technology, 2015, 35(5): 1120-1127. doi: 10.3724/SP.J.1146.2012.01198.

賈承麗, 匡綱要. 一種改進的SAR圖像邊緣檢測方法[J]. 電子與信息學(xué)報, 2007, 29(2): 379-382. doi: 10.3724/SP.J.1146. 2005.00824.

JIA Chengli and KUANG Gangyao. An improved edge detection algorithm for SAR images[J]. Journal of Electronics Information Technology, 2007, 29(2): 379-382. doi: 10.3724 /SP.J.1146.2005.00824.

孔瑩瑩, 周建江, 張焱. 基于ROEWA和Gabor濾波的SAR圖像邊緣提取[J]. 光電子?激光, 2010, 21(8): 1257-1263. doi: 10.16136/j.joel.2010.08.024.

KONG Yingying, ZHOU Jianjiang, and ZHANG Yan. A new edge detection method for SAR image based on ROEWA and gabor filter[J]. Journal of OptoelectronicsLaser, 2010, 21(8): 1257-1263. doi: 10.16136/j.joel.2010.08.024.

熊博蒞. SAR圖像配準(zhǔn)及變化檢測技術(shù)研究[D]. [博士論文], 國防科學(xué)技術(shù)大學(xué), 2012.

XIONG Boli. Study of registration and change detection in SAR images[D]. [Ph.D. dissertation], National University of Defense Technology, 2012.

朱磊. 合成孔徑雷達圖像相干斑抑制方法研究[D]. [博士論文], 西安電子科技大學(xué), 2013.

ZHU Lei. Study on speckle reduction methods for synthetic aperture radar images[D]. [Ph.D. dissertation], Xidian University, 2013.

相關(guān)文章

施引文獻

資源附件(0)

訪問統(tǒng)計