Top suggestions for Hyperspectral Anomaly DetectionExplore more searches like Hyperspectral Anomaly DetectionPeople interested in Hyperspectral Anomaly Detection also searched for |
Related Products
Explore more searches like
HyperspectralAnomaly Detection
+methods+use+the+low-rank+representation+(LRR)+model+to+separate+the+background+and+anomaly+components%252C+where+the+anomaly+component+is+optimized+by+handcrafted+sparse+priors+(e.g.%252C+%2524ell_%7b2%252C1%7d%2524-norm).+However%252C+this+may+not+be+ideal+since+they+overlook+the+spatial+structure+present+in+anomalies+and+make+the+detection+result+largely+dependent+on+manually+set+sparsity.+To+tackle+these+problems%252C+we+redefine+the+optimization+criterion+for+the+anomaly+component+in+the+LRR+model+with+a+self-supervised+network+called+self-supervised+anomaly+prior+(SAP).+This+prior+is+obtained+by+the+pretext+task+of+self-supervised+learning%252C+which+is+customized+to+learn+the+characteristics+of+hyperspectral+anomalies.+Specifically%252C+this+pretext+task+is+a+classification+task+to+distinguish+the+original+hyperspectral+image+(HSI)+and+the+pseudo-anomaly+HSI%252C+where+the+pseudo-anomaly+is+generated+from+the+original+HSI+and+designed+as+a+prism+with+arbitrary+polygon+bases+and+arbitrary+spectral+bands.+In+addition%252C+a+dual-purified+strategy+is+proposed+to+provide+a+more+refined+background+representation+with+an+enriched+background+dictionary%252C+facilitating+the+separation+of+anomalies+from+complex+backgrounds.+Extensive+experiments+on+various+hyperspectral+datasets+demonstrate+that+the+proposed+SAP+offers+a+more+accurate+and+interpretable+solution+than+other+advanced+HAD+methods.&cdnurl=https%3a%2f%2fth.bing.com%2fth%2fid%2fR.0f925c76a372770478f45538502a12a6%3frik%3d7%252b6n2e06CddxqA%26pid%3dImgRaw%26r%3d0&exph=630&expw=1200&q=Hyperspectral+Anomaly+Detection&simid=608035660648945869&FORM=IRPRST&ck=68D37E20184D140EC4A5ECC393AD0435&selectedIndex=13&itb=0)
Some results have been hidden because they may be inaccessible to you.Show inaccessible results
Feedback
