基于bp神经网络的遥感影像棉花识别方法研究.pdfVIP

M ay COM PU T ER ENGINEERING A ND DESIGN Vol No BP back propagation BP GF Ladsat NDVI DVI RVI B B GPS BP BP GF T P A doi issn j Co tton recog nition method f or remo te sensing image based on BP neural netw o rk FA N Ying ing QIA N Y urong Y A N G Liu H U A N G Zhen y School of Sof tw are Xinjiang U niversity U rumqi China Abstract T o improve the accuracy of recognizing cotton using remote sensing data a method w as put forw ard for recognizing cotton based on BP back propagation neural netw ork algorithm Singletemporal GF and Landsat remote sensing data w ere used and normalized difference vegetation index NDVI difference vegetation index DVI ratio vegetation index RVI red band brightness value and nearinf rared band brightness value w ere combined according to the field of GPS measurement data the training sample w as chosen and the BP neural netw ork w as trained by different combination of features It is verified that the recognition accuracy of cotton based on BP neural netw ork reaches w hich is and higher than that based on maximum likelihood and minimum distance respectively Ex perimental results show that the proposed method can effec tively improve the identification accuracy and simplify the identification process Key words remote sensing image cotton recognition BP neural netw ork vegetation index GF 0