A level set method for oil slick segmentation in SAR images

2005 ◽  
Vol 26 (6) ◽  
pp. 1145-1156 ◽  
Author(s):  
B. Huang ◽  
H. Li ◽  
X. Huang
Keyword(s):  
Level Set Method ◽  
Level Set ◽  
Sar Images ◽  
Oil Slick

scholarly journals Inshore Ship Detection Based on Level Set Method and Visual Saliency for SAR Images

Sensors ◽  
2018 ◽  
Vol 18 (11) ◽  
pp. 3877 ◽  
Author(s):  
Tao Xie ◽  
Weike Zhang ◽  
Linna Yang ◽  
Qingping Wang ◽  
Jingjian Huang ◽  
...  
Keyword(s):  
Level Set Method ◽  
Level Set ◽  
Signal To Noise Ratio ◽  
Visual Saliency ◽  
Saliency Map ◽  
Local Contrast ◽  
Signal To Noise ◽  
Sar Images ◽  
Ship Detection ◽  
Noise Ratio

Inshore ship detection is an important research direction of synthetic aperture radar (SAR) images. Due to the effects of speckle noise, land clutters and low signal-to-noise ratio, it is still challenging to achieve effective detection of inshore ships. To solve these issues, an inshore ship detection method based on the level set method and visual saliency is proposed in this paper. First, the image is fast initialized through down-sampling. Second, saliency map is calculated by improved local contrast measure (ILCM). Third, an improved level set method based on saliency map is proposed. The saliency map has a higher signal-to-noise ratio and the local level set method can effectively segment images with intensity inhomogeneity. In this way, the improved level set method has a better segmentation result. Then, candidate targets are obtained after the adaptive threshold. Finally, discrimination is employed to get the final result of ship targets. The experiments on a number of SAR images demonstrate that the proposed method can detect ship targets with reasonable accuracy and integrity.

scholarly journals Optimized Level Set Method for Segmentation of SAR Images using Adaptive Fuzzy-K-Means Clustering

2020 ◽  
Vol 9 (3) ◽  
pp. 2039-2049
Keyword(s):  
Level Set Method ◽  
Level Set ◽  
Sar Images ◽  
Adaptive Fuzzy

The icomplications ithat ioccurred iin iremote isensing iimage iinformation iand ianalysis ialgorithms igrowth iof ia ilarge iscale iimage isegmentation ihaven't ikept ia iplace iwith ithe irequirement ifor ithe imethods iwhich ito idevelop ithe ifinal iaccuracy iof iobject idetection ias iwell ias ithe irecognition. iTraditional iLevel iset isegmentation imethods iwhich iare iChan-Vese i(CV), iImage iand iVision iComputing i(IVC) i2010, iACM iwith iSBGFRLS, iand iOnline iRegion-Based iACM i(ORACM) iare isuffered ifrom imore iamounts iof itime icomplexity, ias iwell ias ilow isegmentation iaccuracy idue ito ilarge iintensity ihomogeneities iand ithe inoise iat iwhich ithe iregion ibased isegmentation iis iimpossible. iSo ithis iis ithe ireason, iwe iproposed ia inavel ihybrid imethodology icalled iadaptive iparticle iswarm ioptimization i(PSO) ibased iFuzzy iK-Means iclustering ialgorithm. iThe iproposed iapproach iis idiversified iinto itwo istages; iin istage ione, ipre-processing ithe iinput iimage ito iimprove ithe iclustering iefficiency iand iovercome ithe iobstacles ipresent iin itraditional imethods iby iusing iparticle iswarm ioptimization i(PSO) iand iAdaptive iFuzzy iK-means iclustering ialgorithm. iWith ithe ihelp iof ithe iPSO ialgorithm, iwe iget ithe i"optimum" ipixels ivalues iare iextracted ifrom ithe iinput iSAR iimages, ithese ioptimum ivalues iare iautomatically iacted ias iclusters icenters ifor iAdaptive iFuzzy iK-Means iClustering iinstead iof irandom iinitialization ifrom ithe ioriginal iimage. iThe ipre-processing isegmentation iresult iimproved ithe iclustering iefficiency ibut isuffers ifrom ifew idrawbacks isuch ias iboundary ileakages iand ioutliers ieven iparticle iSwarm ioptimization iis iused. iTo iovercome ithe iabove idrawbacks ipost-processing iis ineeded ito ifacilitate ithe isuperior isegmentation iresults iwith ithe ihelp iof ithe ilevel iset imethod. iIt iutilizes ian iefficient icurve ideformation idriven iby iexternal iand iinternal iforces ito icapture ithe iimportant istructures i(usual iedges) iin ian iimage. iThe icombined iapproach iof iboth ipre-processing iand ipost-processing iwhich iis icalled iParticle iSwarm iOptimization ibased iAdaptive iFuzzy-K-Means i(AFKM) iclustering ivia ithe ilevel iset imethod. iThe iproposed iapproach iis isuccessfully iimplemented ion ilarge iscale iremote isensing iimagery iand ithe idataset iare itaken ifrom ithe iopen-source iNASA iearth iobservatory idatabase ifor isegmenting ithe ioil islicker icreeps, ioil islicker iregions, ityphoon, isoulnik iand ithe iGulf iof iAlaska, ietc. iSo ihere iin ithis, ithe iproposed inew imethod ihad ifeasibility iand iefficiency iwhich icould iattain ithe ihigh iaccurate isegmentation iresults

Sign in / Sign up

Export Citation Format

Share Document