Scopus记录号: 2-s2.0-84904470835
论文题名: Jeffries Matusita based mixed-measure for improved spectralmatching in hyperspectral image analysis
作者: Padma S ; , Sanjeevi S
刊名: International Journal of Applied Earth Observation and Geoinformation
ISSN: 15698432
出版年: 2014
卷: 32, 期: 1 起始页码: 138
结束页码: 151
语种: 英语
英文关键词: Classification
; Hyperspectral image
; Jeffries-matusita
; Spectral angle mapper
; Spectral matching
Scopus关键词: algorithm
; image analysis
; image classification
; land cover
; sensor
; spectral analysis
; spectral resolution
英文摘要: This paper proposes a novel hyperspectral matching technique by integrating the Jeffries-Matusita mea-sure (JM) and the Spectral Angle Mapper (SAM) algorithm. The deterministic Spectral Angle Mapper andstochastic Jeffries-Matusita measure are orthogonally projected using the sine and tangent functions toincrease their spectral ability. The developed JM-SAM algorithm is implemented in effectively discrim-inating the landcover classes and cover types in the hyperspectral images acquired by PROBA/CHRISand EO-1 Hyperion sensors. The reference spectra for different land-cover classes were derived fromeach of these images. The performance of the proposed measure is compared with the performance ofthe individual SAM and JM approaches. From the values of the relative spectral discriminatory proba-bility (RSDPB) and relative discriminatory entropy value (RSDE), it is inferred that the hybrid JM-SAMapproach results in a high spectral discriminability than the SAM and JM measures. Besides, the use ofthe improved JM-SAM algorithm for supervised classification of the images results in 92.9% and 91.47%accuracy compared to 73.13%, 79.41%, and 85.69% of minimum-distance, SAM and JM measures.It is also inferred that the increased spectral discriminability of JM-SAM measure is contributed by theJM distance. Further, it is seen that the proposed JM-SAM measure is compatible with varying spectralresolutions of PROBA/CHRIS (62 bands) and Hyperion (242 bands). © 2014 Elsevier B.V. 资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/79724
Appears in Collections: 气候变化事实与影响
There are no files associated with this item.
作者单位: Department of Geology, Anna University, Chennai 600025, India
Recommended Citation:
Padma S,, Sanjeevi S. Jeffries Matusita based mixed-measure for improved spectralmatching in hyperspectral image analysis[J]. International Journal of Applied Earth Observation and Geoinformation,2014-01-01,32(1)