一種基于封閉均勻區(qū)域的SAR圖像配準(zhǔn)方法

蘇娟; 李彬; 王延釗

doi:10.11999/JEIT160141

一種基于封閉均勻區(qū)域的SAR圖像配準(zhǔn)方法

doi: 10.11999/JEIT160141

蘇娟^1, ,,
李彬¹,
王延釗¹

基金項(xiàng)目:

國(guó)家自然科學(xué)基金(61302195)

計(jì)量
- 文章訪問(wèn)數(shù): 1106
- HTML全文瀏覽量: 187
- PDF下載量: 328
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-01-29
- 修回日期: 2016-10-28
- 刊出日期: 2016-12-19

SAR Image Registration Algorithm Based on Closed Uniform Regions

SU Juan^{1
, ,},
LI Bin¹,
WANG Yanzhao¹

Funds:

The National Natural Science Foundation of China (61302195)

摘要

摘要: 為克服圖像間灰度差異、旋轉(zhuǎn)差異和尺度差異對(duì)SAR圖像配準(zhǔn)精度的影響，該文利用均勻區(qū)域在SAR圖像中的灰度統(tǒng)計(jì)特性，提出一種基于穩(wěn)定封閉均勻區(qū)域的SAR圖像配準(zhǔn)算法。首先基于多尺度非線性擴(kuò)散理論，提取得到輪廓保持性較好的封閉均勻區(qū)域；然后構(gòu)建具有仿射不變性的區(qū)域特征，采取基于多邊形擬合的區(qū)域粗匹配方法和基于重合度的區(qū)域精匹配方法，實(shí)現(xiàn)由粗至精的區(qū)域匹配；最后用匹配區(qū)域的質(zhì)心點(diǎn)構(gòu)建圖像變換模型。實(shí)驗(yàn)結(jié)果表明，該算法配準(zhǔn)精度高，能有效克服待配準(zhǔn)圖像之間的灰度差異、旋轉(zhuǎn)差異和尺度差異，對(duì)噪聲具有較好的適應(yīng)性。
- SAR圖像配準(zhǔn) /
- 封閉均勻區(qū)域 /
- 多尺度非線性擴(kuò)散 /
- 仿射不變性
Abstract: In order to overcome the influence of gray difference, rotation difference and scale difference on image registration accuracy, the gray statistic property of uniform regions in SAR images is utilized and a SAR image registration algorithm based on stable closed uniform regions is proposed. Firstly, based on the multi-scale nonlinear diffusion theory, closed uniform regions with good contour pervserving ability are respectively extracted from two images. Secondly, two affine-invariant region features based on polygon fitting and coincidence degree are constructed to realized the coarse-to-fine region matching. Finally, the centroids of matched regions are used to construct the transform model between two images. Experimental results demonstrate that, the proposed algorithm has high registration accuracy, and is effective for gray difference, rotation difference and scale difference, moreover, it has high adaptability to noise.
- SAR image registration /
- Closed uniform regions /
- Multi-scale nonlinear diffusion /
- Affine-invariant

HTML全文

參考文獻(xiàn)(18)

ZITOVA B and FLUSSER J. Image registration methods: a survey[J]. Image and Vision Computing, 2003, (21): 977-1000.

LOWE D G. Distinctive image features from scale-invariant key points[J]. International Journal of Computer Vision, 2004, (60): 91-110.

LONG Tengfei, JIAO Weili, HE Guojin, et al. A generic framework for image rectification using multiple types of feature[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2015, (102): 161-171. doi: 10.1016/j.isprsjprs.2015. 01.015.

[s2]DELLINGER F, DELON J, GOUSSEAU Y, et al. SAR-SIFT: a SIFT-like algorithm for SAR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 53(1): 453-466. doi: 10.1109/TGRS.2014.2323552.

LI Dapeng. A novel method for multi-angle SAR image matching[J]. Chinese Journal of Aeronautics, 2015, 28(1): 240-249. doi: 10.1016/j.cja.2014.12.019.

CHEN Tianze, CHEN Limin, and SU Yi. A SAR image registration method based on pixel migration of edge-point feature[J]. IEEE Transactions on Geoscience and Remote Sensing Letters, 2014, 11(5): 906-910. doi: 10.1109/LGRS. 2013.2281729.

XU Chuan, SUI Haigang, LI Hongli, et al. An automatic optical and SAR image registration method with iterative level set segmentation and SIFT[J]. International Journal of Remote Sensing, 2015, 36(15): 3997-4017. doi: 10.1080/ 01431161.2015.1070321.

蘇娟, 林行剛, 劉代志. 一種基于結(jié)構(gòu)特征邊緣的多傳感器圖像配準(zhǔn)方法[J]. 自動(dòng)化學(xué)報(bào), 2009, 35(3): 251-257. doi: 10. 3724/SP.J.1004.2009.00251.

SU Juan, LIN Xingang and LIU Daizhi. A multi-sensor image registration algorithm based on structure feature edges[J]. Acta Automatica Sinica, 2009, 35(3): 251-257. doi: 10.3724/ SP.J.1004.2009.00251.

WANG Jinfeng, PI Yiming, and CAO Zongjie. Level set method for SAR image coregistration[J]. IEEE Geoscience and Remote Sensing Letters, 2008, 5(4): 615-619. doi: 10.1109 /LGRS.2008.2000995.

XIONG Boli, HE Zhiguo, HU Canbin, et al. A method of acquiring tie points based on closed regions in SAR images[C]. IEEE International Conference on Geoscience and Remote Sensing, Munich, Germany, 2012: 2121-2124.

DAI Xiaolong and KHORRAM S. A feature-based image registration algorithm using improved chain-code representation combined with invariant moments[J]. IEEE Transactions on Geoscience and Remote Sensing, 1999, 37(5): 2351-2362.

李振華, 江耿紅, 徐勝男, 等. 基于輪廓多邊形擬合的紅外與可見(jiàn)光圖像配準(zhǔn)算法[J]. 系統(tǒng)工程與電子技術(shù), 2015, 37(12): 2872-2878. doi: 10.3969/j.issn.1001-506X.2015.12.32.

LI Zhenhua, JIANG Genghong, XU Shengnan, et al. Image registration algorithm for infrared and visible images based on contour polygon fitting[J]. Systems Engineering and Electronics, 2015, 37(12): 2872-2878. doi: 10.3969/j.issn. 1001-506X.2015.12.32.

劉哲, 楊健, 張麗. 基于橢圓傅里葉描述子的遙感圖像配準(zhǔn)算法[J]. 光電子激光, 2015, 26(2): 352-359. doi: 10.16136/j.joel. 2015.02.0566.

LIU Zhe, YANG Jiang, and ZHANG Li. Remote sensing image registration algorithm based on elliptic Fourier descriptor[J]. Journal of Optoelectronics and Laser, 2015, 26(2): 352-359. doi: 10.16136/j.joel.2015.02.0566.

PERONA P and MALIK J. Scale space and edge detection using anisotropic diffusion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7): 629-639.

HE X C and YUNG NHC. Curvature scale space corner detector with adaptive threshold and dynamic region of support[C]. IEEE International Conference on Pattern Recognition, Cambridge, UK, 2004: 791-794.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問(wèn)統(tǒng)計(jì)