Abstract
Since technologies in image fusion, image splicing, and target recognition have developed rapidly, as the basis of many image applications, the performance of image registration directly affects subsequent work. In this work, for rich features of satellite-borne optical imagery such as panchromatic and multispectral images, the Harris corner algorithm is combined with the scale invariant feature transform (SIFT) operator for feature point extraction. Our rough matching strategy uses the K-D (K-Dimensional) tree combined with the BBF (Best Bin First) method, and the similarity measure is the nearest neighbor/the second-nearest neighbor ratio. Finally, a triangle-area representation (TAR) algorithm is utilized to eliminate false matches in order to ensure registration accuracy. The performance of the proposed algorithm is compared with existing popular algorithms. The experimental results indicate that for visible light and multi-spectral satellite remote sensing images of different sizes and different sources, the proposed algorithm in this work is excellent in accuracy and efficiency.
Highlights
The specific objective of image registration is to find the geometric correspondence between different images that contain the same contents
Since satellite-borne optical remote sensing images are acquired at high altitude, the view differences among images of the same target are slight
Because of small view differences of satellite remote sensing images, a registration method based on point features is designed in this study
Summary
The specific objective of image registration is to find the geometric correspondence between different images that contain the same contents. In the field of remote sensing, there are many types of satellite-borne optical image sensors, and their acquired remote sensing images are of different resolutions and bands. With the continuous development of sensor technology, researchers in the satellite remote sensing field have paid more attention to the study of high-speed and stable information transmission [3,4,5,6,7]. As sensor types become more and more diverse, remote sensing images with different spatial and spectral resolutions can be obtained using different satellite-borne platforms. This work is mainly focused on the registration of satellite-borne optical remote sensing imagery, i.e., panchromatic and multispectral images. Sensors 2021, 21, 2695 registration of satellite-borne optical remote sensing imagery, i.e., panchromatic and multispectral images. Sensors 2021, 21, 2695 registration of satellite-borne optical remote sensing imagery, i.e., panchromatic and multispectral images. tintannhhneeveeaitgarpfrhepeTTrisbaraihhtinotn/neeunrctcrirerripeeeapafmlmerttleireaoaaatonuiinmofnenrsfitddefgehoeethtehrrrhtbmroaoeooadlffgrn(.attSoshhTlrfIrgioaiFhissottrTehirmaaon)imrrt,athtiti,mlc(mchgiSllneeoeeI,ctFrbihiliiTssautnoh)soodcdimrlrci.uaggn,pldaagTgBrnniohinteiinhrezzsgicneetetihd,dpBHtmhliataenaehs,sroeFrfffHBiooisrtblelashllcsaotroeotsrww(iirtBcsnrBssBi.e.iacpnFrnTTo)rpghrhiaFnnloeeeliceigr-snsirasopeettrcrlcepaeiooat(lonhnBgirodmdoBnefrptFssiaer)tteaehnhcclstemdatgieilooongn,tnnrtorseiaicritaiatnhainritnoltmehtergrnsmool,tied/n(dT-sunvuacAaaecrcaneeRareldaiesrs)raelgporersitehnmtatiisonde(sTcAriRb)edalginorditehtmaili,swdhesicchribisedadinopdteetdailt,owehliimchinisataedfoaplsteedmtoateclhimesininaterofuaglshe mmaattcchhiensginanrdouregahlizmeafitcnheirneggiasntrdatrioenal.izMeefainnwe hreilgei,stthraetoiopnti.mMael aanffiwnheitlrea, nthsfeoromptpimaraalmaefftienres tarraenosfbotraminepdafroarmtheteerms aatcreheodbptaoiinnetds. fIonrththeethmirdatscehcetdionp,otihnetsp. rIonpothseedthaligrdorsitehcmtioinn, tthhies pwroorpkoisseedvaallguoartietdhmbyinustihnigs twhoerikmiasgeevsaflruoamtedGFb-y1,uGsiFn-g2 tahnedimASaTgeEsRf.rFoimnaGllyF,-c1o, nGcFlu-2siaonnds AanSdTEdRis.cFuisnsaiollnys, caorencgliuvseinonins athnedfdouisrctuhssseiocntisonar. e given in the fourth section
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
