6533b870fe1ef96bd12cf9c4
RESEARCH PRODUCT
Optimal band selection for future satellite sensor dedicated to soil science
Sandrine MathieuSivasathivel KandasamyPierre GoutonFrédéric BaretAudrey Minghelli-romanFrancois Tavinsubject
Statistical classificationContextual image classificationComputer scienceBandwidth (signal processing)Hyperspectral imagingSatelliteFeature selectionSpectral bandsData transmissionRemote sensingdescription
Hyperspectral imaging systems could be used for identifying the different soil types from the satellites. However, detecting the reflectance of the soils in all the wavelengths involves the use of a large number of sensors with high accuracy and also creates a problem in transmitting the data to earth stations for processing. The current sensors can reach a bandwidth of 20 nm and hence, the reflectance obtained using the sensors are the integration of reflectance obtained in each of the wavelength present in the spectral band. Moreover, not all spectral bands contribute equally to classification and hence, identifying the bands necessary to have a good classification is necessary to reduce sensor cost and problem in data transmission from the satellite. The work presents the spectral bands selected using a PCA-Based Forward Sequential band selection algorithm.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2009-08-01 | 2009 First Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing |