利用SAR-FAST角點(diǎn)檢測(cè)的合成孔徑雷達(dá)圖像配準(zhǔn)方法

劉妍; 余淮; 楊文; 李立

doi:10.11999/JEIT160386

利用SAR-FAST角點(diǎn)檢測(cè)的合成孔徑雷達(dá)圖像配準(zhǔn)方法

doi: 10.11999/JEIT160386

劉妍¹,
余淮¹,
楊文^1, ,,
李立¹

基金項(xiàng)目:

國(guó)家自然科學(xué)基金(61271401, 61331016)

計(jì)量
- 文章訪問(wèn)數(shù): 1859
- HTML全文瀏覽量: 169
- PDF下載量: 426
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-04-20
- 修回日期: 2016-08-30
- 刊出日期: 2017-02-19

SAR Image Registration Using SAR-FAST Corner Detection

LIU Yan¹,
YU Huai¹,
YANG Wen^{1
, ,},
LI Li¹

Funds:

The National Natural Science Foundation of China (61271401,61331016)

摘要

摘要: 合成雷達(dá)孔徑圖像配準(zhǔn)作為變化檢測(cè)和圖像信息融合的基礎(chǔ)，對(duì)多時(shí)相SAR圖像的解譯具有重要作用。該文提出一種基于SAR-FAST角點(diǎn)檢測(cè)的圖像配準(zhǔn)方法。首先，選用迭代引導(dǎo)平滑算法抑制斑點(diǎn)噪聲對(duì)角點(diǎn)檢測(cè)的影響；然后，以檢測(cè)點(diǎn)為圓心，選擇合適的檢測(cè)半徑，在圓周上選取檢測(cè)窗口，統(tǒng)計(jì)與檢測(cè)點(diǎn)不相似的窗口數(shù)量，判斷檢測(cè)點(diǎn)是否為角點(diǎn)；最后，對(duì)候選角點(diǎn)進(jìn)行分析，根據(jù)其強(qiáng)度分布特點(diǎn)進(jìn)一步剔除誤檢點(diǎn)。實(shí)驗(yàn)結(jié)果表明，SAR-FAST可以檢測(cè)到足夠數(shù)量且穩(wěn)定性和重復(fù)性好的角點(diǎn)，應(yīng)用于圖像配準(zhǔn)，也能獲得較好的配準(zhǔn)效果。
- 合成孔徑雷達(dá) /
- 角點(diǎn)檢測(cè) /
- 特征描述 /
- 圖像配準(zhǔn)
Abstract: As the basis of change detection and image fusion, SAR image registration plays an important role in the interpretation of multi-temporal SAR images. This paper presents a method of SAR image registration based on corner detection using SAR-FAST, which is a customized version of Features from Accelerated Segment Test (FAST) for processing SAR images. The proposed method firstly employs rolling guidance filter to suppress speckle noise. Secondly, the candidate corner point is determined by quantitative analysis of the dissimilarities of the detection windows on the extended circle and the center window. Finally, the error detections are removed by analyzing the intensity distribution properties of the candidate corners. The experimental results show that SAR-FAST can detect a sufficient number of corners with stability and high repeatability, and when applying to image registration, it also can get better registration results.
- SAR /
- Corner detection /
- Feature description /
- Image registration

HTML全文

參考文獻(xiàn)(21)

王國(guó)力, 周偉, 柴勇, 等. 基于單演信號(hào)理論的SAR圖像配準(zhǔn)[J]. 電子與信息學(xué)報(bào), 2013, 35(8): 1779-1785 doi: 10.3724/ SP.J.1146.2012.01487.

WANG Guoli, ZHOU Wei, CHAI Yong, et al. SAR image registration based on monogenic signal theory[J]. Journal of Electronics Information Technology, 2013, 35(8): 1779-1785. doi: 10.3724/SP.J.1146.2012.01487.

DALIMIYA C and DHARUN V. A survey of registration techniques in remote sensing images[J]. Indian Journal of Science and Technology, 2015, 26(8). Paper No. 24, doi: 10.17485/ijst/ 2015/v8i26/81048.

ZHANG H, NI W, YAN W, et al. Robust SAR image registration based on edge matching and refined coherent point drift[J]. IEEE Geoscience and Remote Sensing Letters, 2015, 12(10): 2115-2119. doi: 10.1109/LGRS.2015.2451396.

李英杰, 張俊舉, 常本康, 等. 一種多波段紅外圖像聯(lián)合配準(zhǔn)和融合方法[J]. 電子與信息學(xué)報(bào), 2016, 38(1): 8-14. doi: 10.11999/JEIT150479.

LI Yingjie, ZHANG Junju, CHANG Benkang, et al. Joint image registration and fusion for multispectral infrared images[J]. Journal of Electronics Information Technology, 2016, 38(1): 8-14. doi: 10.11999/JEIT150479.

鄧梁, 史儀凱, 張均田. 基于時(shí)變醫(yī)學(xué)先驗(yàn)信息的約束成像及圖像配準(zhǔn)方法[J]. 電子與信息學(xué)報(bào), 2013, 35(12): 2942-2947. doi: 10.3724/SP.J.1146.2012.01565.

DENG Liang, SHI Yikai, and ZHANG Juntian. A constrained imaging and registration scheme based on time-varying anatomical priors [J]. Journal of Electronics Information Technology, 2013, 35(12): 2942-2947. doi: 10.3724/SP.J.1146.2012.01565.

WANG S, YOU H, and FU K. BFSIFT: A novel method to find feature matches for SAR image registration[J]. IEEE Geoscience and Remote Sensing Letters, 2012, 9(4): 649-653. doi: 10.1109/LGRS.2011.2177437.

LOWE D. Object recognition from local scale-invariant features[C]. IEEE International Conference on Computer Vision, Corfu, Greece, 1999: 1150-1157.

SCHWIND P, SURI S, and REINARTZ P. Applicability of the SIFT operator to geometric SAR image registration[J]. International Journal of Remote Sensing, 2010, 31(8): 1959-1980. doi: 10.1080/01431160902927622.

WANG B, ZHANG J, LU L, et al. A uniform SIFT-like algorithm for SAR image registration[J]. IEEE Transactions on Geoscience and Remote Sensing, 2015, 12(7): 1426-1430. doi: 10.1109/LGRS.2015.2406336.

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.

HARRIS C and STEPHENS M. A combined corner and edge detector[C]. Proceedings of the Fourth Alvey Vision Conference, Manchester, UK. 1988: 147-151.

ROSTEN E, PORTER R, and DRUMMOND T. Faster and better: a machine learning approach to corner detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(1): 105-119. doi: 10.1109/ TPAMI.2008.275

ZHANG Q, SHEN X, XU L, et al. Rolling guidance filter[C]. European Conference on Computer Vision, Zurich, Switzerland, 2014: 815-830.

MOHANNA F, MOKHTARIAN F. Performance evaluation of corner detection algorithms under affine and similarity transforms[C]. 12th British Machine Vision Conference, Manchester, UK, 2001: 1-10

BAY H, TUYTELAARS T, VAN G, et al. SURF: speeded-up robust features[J]. International Journal on Computer Vision and Image Understanding, 2008, 110(3): 346-359. doi: 10.1007/11744023_32.

LEUTENEGGER S, CHLI M, SIEGWART R, et al. BRISK: Binary robust invariant scalable keypoints[C]. IEEE International Conference on Computer Vision, Barcelona, Spain, 2011: 2548-2555.

CALONDER M, LEPETIT V, STRECHA C, et al. Brief: Binary robust independent elementary features[C]. European Conference on Computer Vision 2010, Heraklion, Greece, 2010: 778-792.

ANDONI A and INDYK P. Near-optimal hashing algorithms for approximate nearest neighbor in high dimensions[J]. Communications of the Association for Computing Machinery, 2008, 51(1): 117-122.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問(wèn)統(tǒng)計(jì)