基于SIFT与Contourlet变换的高分辨遥感图像配准

doi:10.11873/j.issn.1004-0323.2013.1.58

閬ユ劅鎶�鏈笌搴旂敤鈥衡�� 2013, Vol. 28 鈥衡�� Issue (1): 58-64.DOI: 10.11873/j.issn.1004-0323.2013.1.58

鈥� 鍥惧儚涓庢暟鎹鐞� 鈥� 涓婁竴绡� 涓嬩竴绡�

鍩轰簬SIFT涓嶤ontourlet鍙樻崲鐨勯珮鍒嗚鲸閬ユ劅鍥惧儚閰嶅噯顎�

娆ч槼鑳介挧¹,鏉庝紵褰�¹,闊﹁敋²,娼樻櫞¹

(1.骞夸笢宸ヤ笟澶у淇℃伅宸ョ▼瀛﹂櫌,骞夸笢骞垮窞 510006;顎�
2.涓浗鍦拌川澶у(鍖椾含)鍦扮悆绉戝涓庤祫婧愬闄�,鍖椾含 100083)

鏀剁鏃ユ湡:2011-11-09 淇洖鏃ユ湡:2012-11-05 鍑虹増鏃ユ湡:2013-02-20 鍙戝竷鏃ユ湡:2013-06-21
浣滆�呯畝浠�:娆ч槼鑳介挧(1987-),鐢�,姹熻タ鍗楁槍浜�,纭曞＋鐮旂┒鐢�,涓昏浠庝簨鍥惧儚閰嶅噯鏂归潰鐨勭爺绌躲�侲mail:ouyang_37@163.com銆�
鍩洪噾璧勫姪:
鍥藉鑷劧绉戝鍩洪噾椤圭洰(61001179),骞夸笢鐪佽嚜鐒剁瀛﹀熀閲戦」鐩�(07301038,9451009001002667)銆�

Registration Technique for High-resolution Remote Sensing Images based on SIFT and Contourlet Transform

Ouyang Nengjun¹,Li Weitong¹,Wei Wei²,Pan Qing¹

(1.School of Information Engeering,Guangdong University of Technology,Guangzhou 510006,China;顎�
2.School of Earth Science and Resource,China University of Geosciences,Beijing 100083,China)

Received:2011-11-09 Revised:2012-11-05 Online:2013-02-20 Published:2013-06-21

鎽樿/Abstract

鎽樿锛�

閽堝楂樺垎杈ㄩ仴鎰熷浘鍍忕壒寰侀噺杈冨鐨勬儏鍐�,鎻愬嚭涓�绉嶅熀浜嶴IFT涓嶤ontourlet鍙樻崲鐩哥粨鍚堢殑鍥惧儚閰嶅噯绠楁硶銆傞鍏堝皢鍥惧儚杩涜Contourlet鍙樻崲鍒嗚В鎴愪綆棰戝拰楂橀瀛愬甫,瀵归珮棰戝瓙甯﹂�氳繃璁惧畾鍚堥�傜殑闃堝�兼潵鎻愬彇鍥惧儚杈圭紭鐗瑰緛鐐�,瀵逛綆棰戝瓙甯﹁繘琛孲IFT鐗瑰緛鐐规彁鍙栥�傚皢涓よ�呮彁鍙栧埌鐨勭壒寰佺偣鍒嗗埆鍖归厤鍚庡緱鍒扮矖鍖归厤鐐瑰,鍒╃敤闅忔満鎶芥牱涓�鑷存��(RANSAC)閫夋嫨鍑虹簿鍖归厤鐐瑰,瀹炵幇鍥惧儚閰嶅噯銆傚疄楠岃〃鏄�:鍦ㄥ婧愰仴鎰熷浘鍍忛厤鍑嗚繃绋嬩腑,涓庡熀浜庨潪閲囨牱Contourlet鍙樻崲(NSCT)鍜屽熀浜嶴IFT鐗瑰緛鎻愬彇鐩告瘮,璇ョ畻娉曡兘澶熸洿鍑嗙‘鍦版彁鍙栧埌鐗瑰緛鐐�,鍏锋湁鏇撮珮鐨勮繍绠楁晥鐜囦互鍙婂尮閰嶇巼銆�

鍏抽敭璇�: SIFT, Contourlet鍙樻崲, 閬ユ劅鍥惧儚閰嶅噯, RANSAC, 楂樺垎杈ㄧ巼

Abstract:

For high-resolution remote images with tremendous feature,a new method of image registration is proposed by combining contourlet transformation with SIFT.Firstly,the discrete contourlet transformation decomposes the original image into a low-frequency sub-band and several high-frequency sub-band.For high-frequency sub-bands,image edge feature points are extracted by an appropriate threshold.For the low-frequency sub-band,image SIFT feature are extracted by SIFT.Then,coarse control point pairs are searched out with normalized corss-correlation matching and SIFT matching before accurate control point pairs are hunted by RANSAC.The experimental results show that,as for high-resolution remote sensing image registration,this method can extract more acculately control point pairs,get higher computing efficiency and matching ratio than these methods based on NSCT or SIFT.

Key words: Scale invariant features transform, Contourlet Transformation, Remote image registration, Random Sample Concensus, High-resolution

涓浘鍒嗙被鍙�:

TP 75

娆ч槼鑳介挧,鏉庝紵褰�,闊﹁敋,娼樻櫞顎�. 鍩轰簬SIFT涓嶤ontourlet鍙樻崲鐨勯珮鍒嗚鲸閬ユ劅鍥惧儚閰嶅噯顎僛J]. 閬ユ劅鎶�鏈笌搴旂敤, 2013, 28(1): 58-64.

Ouyang Nengjun,Li Weitong,Wei Wei,Pan Qing顎�. Registration Technique for High-resolution Remote Sensing Images based on SIFT and Contourlet Transform[J]. Remote Sensing Technology and Application, 2013, 28(1): 58-64.

鍙傝�冩枃鐚�

锛�1锛絉oche A,Malandain G,Ayache N.Unifying Maximum Likelihood Approaches in Medical Image Registration锛籎锛�.International Journal of Imaging Systems and Technology,Special Issue on 3D Imaging,2000,11:71-80.顎�

锛�2锛絑hou Haifang,Du Yunfei,Yang Xuejun,顎奺t al顎�.Study and Implement of Parallel Region-based Registration Algorithm based on Mutual Information for Remote-sensing Images锛籎锛�.Journal of Image and Graphics,2010,15(1):174-180.锛诲懆娴疯姵,鏉滀簯椋�,鏉ㄥ鍐�,绛�.鍩轰簬浜掍俊鎭殑閬ユ劅鍥惧儚鍖哄煙閰嶅噯骞惰绠楁硶鐨勭爺绌朵笌瀹炵幇锛籎锛�.涓浗鍥捐薄鍥惧舰瀛︽姤,2010,15(1):174-180.锛筋��

锛�3锛絀brahim A,Rube E,Maha A,顎奺t al顎�.Image Registration based on Multi-scale SIFT for Remote Sensing Images锛籆锛�//IEEE Signal Processing and Communication Systems,Omaha,NE:2009,09:978-1-4244-4474-8. 顎�

锛�4锛紿ong G,Zhang Y.Wavelet-based Image Registration Technique for High-resolution Remote Sensing Images锛籎锛�.Computers & Geosciences,2008,34:1708-1720.顎�

锛�5锛紺hen Zhigang,Yin Fuchang,Sun Fu.Registration Technique for High-resolution Remote Sensing Images based on Nonsubsampled Contourlet Transform锛籎锛�.Acta Optica Sinica,2009,29(10):2744-2750.锛婚檲蹇楀垰,灏圭鏄�,瀛欏瓪.鍩轰簬闈為噰鏍稢ontourlet鍙樻崲楂樺垎杈ㄧ巼閬ユ劅鍥惧儚閰嶅噯锛籎锛�.鍏夊瀛︽姤,2009,29(10):2744-2750.锛筋��

锛�6锛絑heng Y,Cao Z G,Xiao Y.Mutli-spectral Remote Image Registration based on SIFT锛籎锛�.Electronics Letters,2008,44(2):107-108.顎�

锛�7锛絃iu Jiajia,He Xiaohai,Chen Weilong.Image Matching Algorithm by Wavelet Transform Combined with SIFT Characteristics锛籎锛�.Computer Simulation,2011,28(1):257-260.锛诲垬浣冲槈,浣曞皬娴�,闄堜负榫�.涓�绉嶇粨鍚堝皬娉㈠彉鎹㈢殑SIFT鐗瑰緛鍥惧儚鍖归厤绠楁硶锛籎锛�.璁＄畻鏈轰豢鐪�,2011,28(1):257-260.锛筋��

锛�8锛紻o M N,Vetterli M.The Contourlet Transform:An Efficient Directional Multiresolution Image Representation锛籎锛�.IEEE Transaction on Image Processing,2006,15(6):1610-1620.顎�

锛�9锛紻avid G L.Distinctive Image Features from Scale-invariant Key-points锛籎锛�.International Journal of Computer Vision,2004,60(2):90-110.顎�

锛�10锛紿artley R,Zisserman A.Multiple View Geometry in Computer Vision锛籑锛�.Cambridge:Cambridge University Press,2000.顎�

锛�11锛絃i Xiaojuan,Gong Zhaoning,Liu Xiaomeng.ENVI Remote Image Processing锛籑锛�.Beijing:Environment Science Press of China,2007.锛绘潕灏忓,瀹厗瀹�,鍒樻檽钀�.ENVI閬ユ劅褰卞儚澶勭悊鏁欑▼锛籑锛�.鍖椾含:涓浗鐜绉戝鍑虹増绀�,2007.锛筋��

锛�12锛組a Zhengde,Du Yunfei,Zhou Haifang,顎奺t al顎�.Performance Com-parison of Similarity Measures for Remote Sensing Image Registration锛籎锛�.Computer Engineering & Science,2008,30(2):45-48.锛婚┈鏀垮痉,鏉滀簯椋�,鍛ㄦ捣鑺�,绛�.閬ユ劅鍥惧儚閰嶅噯涓浉浼兼�ф祴搴︾殑姣旇緝鍜屽垎鏋愶蓟J锛�.璁＄畻鏈哄伐绋嬩笌绉戝,2008,30(2):45-48.锛筋��

锛�13锛紼zzeldeen R M,Ramadan H H,Nazmy T M,顎奺t al顎�.Comparative Study for Image Registration Techniques of Remote Sensing Images锛籎锛�.The Egyptian Journal of Remote Sensing and Space Sciences,2010,13:31-36.顎�

[1]	璋㈡稕, 闄堟柦鏂�, 鐬垮缓鍗�, 鐜嬭秴. 缁撳悎鑷�傚簲褰㈡�佸睘鎬у墫闈笌鍐崇瓥铻嶅悎鐨勯珮鍒嗛仴鎰熷彉鍖栨娴�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(3): 536-546.
[2]	鐜嬩紵, 绋嬪媷, 鍛ㄧ帀绉�, 寮犳枃鏉�, 鐜嬪啗, 浣曚匠淇�, 椤鹃泤搴�. 鍩轰簬YOLO鐨勯仴鎰熷奖鍍忕洰鏍囧揩閫熸娴嬭交閲忓寲缃戠粶鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(3): 547-556.
[3]	鏋楁鎬�, 姹皬閽�, 姹ょ传闇�, 鏉庤挋钂�, 鍚寸憺濮�, 榛勫痉鍗�. 鍩轰簬闈㈠悜瀵硅薄CNN鍜孯F鐨勪笉鍚岀┖闂村垎杈ㄧ巼閬ユ劅褰卞儚鍐滀笟澶ф鎻愬彇鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(2): 315-327.
[4]	鍗㈠織鍒�,闄堣姵娣�,琚佽秴,鐢颁害闄�,闄堝己,鏂囩編骞�,灏归敶,鏉ㄥ厜. 閲囩敤I-PSPNet璇箟鍒嗗壊妯″瀷鐨勯珮鍒嗚鲸鐜囬仴鎰熷奖鍍忔煇鐗圭妞嶇墿绉嶆鍦板潡鎻愬彇鐮旂┒[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2024, 39(1): 222-233.
[5]	琚佸惎杩�,璧垫灄,骞歌禐鍝�,閭瑰痉瀵�,璧靛缓濠�,鍒樹笘鍗�,妯婄. 闈掕棌宸ョ▼璧板粖娌跨嚎澶氬勾鍐诲湡鍖鸿瀺鍖栧楂樺垎杈ㄧ巼鍦拌〃鍦熷￥姘村垎鍙嶆紨[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(6): 1350-1363.
[6]	寮犳烦,钁涙瘏,浠昏秺,楂橀,闊╁媷,钁ｆ�濇簮,绉︽澃鑻�,璁歌讲,鍚曞┃,楂樿壋鑺�. 鍩轰簬浼樺寲鐨凞eeplabV3+缃戠粶鍜岄珮鍒嗗奖鍍忓垎鍓叉诞钀嶅瀷鍐滄潙榛戣嚟姘翠綋[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(6): 1433-1444.
[7]	鑳¤吘浜�,瑙ｉ箯椋�,娓╀簹妤�,鎱曞彿浼�. 鍩轰簬涓嶅悓娣卞害瀛︿範妯″瀷鎻愬彇寤虹瓚杞粨鐨勬柟娉曠爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(4): 892-902.
[8]	鑼冩矝钖�,閮濊挋钂�,姹熶笢,涓佹柟瀹�. 鍩轰簬楂樺垎閬ユ劅褰卞儚鐨勯湶澶╃熆鍖哄湡鍦板埄鐢ㄥ姩鎬佺洃娴嬧�斺�斾互骞虫湐鐭垮尯涓轰緥[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(2): 274-284.
[9]	寮犻潤瀹�,瀛欑澘,鏌忓欢鑷�,鍛ㄧ孩鏁�,寮犺但鏋�,鏉庣惇. 澶у叴瀹夊箔鍖楁妫灄鎵板姩瀵筃PP鐨勫奖鍝嶅垎鏋�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(2): 413-421.
[10]	璧典細鑺�,浜庡崥,闄堟柟,鐜嬮浄. 鍩轰簬楂樺垎杈ㄧ巼鍗槦閬ユ劅褰卞儚婊戝潯鎻愬彇鏂规硶鐮旂┒鐜扮姸[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(1): 108-115.
[11]	鏉庣拹,寮犻涓�,閭佃姼,榄忕鏂�,榛勭划鐞�,鐒﹂泤妤�. 鍩轰簬婊戝姩绐楀彛鐨勯珮鍒嗚鲸鐜嘢AR鍥惧儚鐐圭洰鏍囩Н鍒嗗搷搴旇兘閲忚绠楁柟娉曠爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2023, 38(1): 182-189.
[12]	钖涘簡,鏉ㄦ爲鏂�,闂亽,寮犺悓鐢�,寮犲崜. 鍩轰簬SIFT涓庝簰淇℃伅绛涢�変紭鍖栫殑閬ユ劅褰卞儚閰嶅噯[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(5): 1209-1216.
[13]	闂亽,鏉ㄦ爲鏂�,钖涘簡,寮犱箖蹇�,浠樻槺鍑�. 鍩轰簬杈圭紭鐗瑰緛鐨勫婧愰珮鍒嗚鲸鐜囧奖鍍忛厤鍑�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(5): 1259-1266.
[14]	鐜嬫櫠,楂樺竻,閮寒,姹簯. 鍩轰簬澶氬昂搴︾壒寰佽瀺鍚堢殑U-Net缃戠粶楂樺垎褰卞儚涓嶉�忔按闈㈡彁鍙栫爺绌�[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(4): 811-819.
[15]	钁ｇ鏄�,鍒樺繝鍙�,钂嬫��,閮稕,鏉庡畻鍗�. 鍩轰簬WorldView-2褰卞儚鍜岃涔夊垎鍓叉ā鍨嬬殑灏忛害鍒嗙被鎻愬彇[J]. 閬ユ劅鎶�鏈笌搴旂敤, 2022, 37(3): 564-570.

鍩轰簬SIFT涓嶤ontourlet鍙樻崲鐨勯珮鍒嗚鲸閬ユ劅鍥惧儚閰嶅噯顎�

Registration Technique for High-resolution Remote Sensing Images based on SIFT and Contourlet Transform

PDF (PC)

鍙鍖�

鎽樿/Abstract

寮曠敤鏈枃

浣跨敤鏈枃

鍙傝�冩枃鐚�

鐩稿叧鏂囩珷 15

缂栬緫鎺ㄨ崘

Metrics

鏈枃璇勪环