This paper presents a fusion approach of PALSAR-FBS L-HH polarization and Landsat-5 TM datasets for geological
mapping and morpho-structural lineaments extraction. The study site is situated in Western Ethiopia, Benshangul-
Gumuz National Regional State, Asosa Zones; which is characterized by lithological diversity and rich mineral
resources. The TM data were calibrated radiometrically and corrected atmospherically to retrieve ground surface
reflectance. As well, the radar data were calibrated to retrieve backscatter coefficients and then filtered using the gamma
filter to reduce speckle. Moreover, the two images were geometrically corrected and topographically rectified using the
ASTER GDEM, UTM projection and WGS84 geodetic reference. Then, the images were transformed to Intensity-Hue-
Saturation (I-H-S) using three different methods, such as hexagonal, double hexagonal and cylindrical transformations.
Based on several tests integrating all the considered datasets, the SWIR and NIR bands were selected for “I”, “H” and
“S” codification using cylindrical transformation. Three color composites (named spatio-maps) were selected due to their
best results: 1) “I”, “H” and “L-HH”; 2) “I”, “H” and the blue band resulting from the fusion of TM (7, 5, 4) and LHH;
and 3) the R-G-B resulting from the fusion of “I”, “H”, “S” and “L-HH”. These derived spatio-maps show good
relationship between the topographic morphology, rock-substrate, structural variations properties, and drainage network.
In addition, the spectral variations are easily associated with lithological units. Likewise, the morpho-structural
information’s highlighted in the PALSAR image are visible without altering the radiometric integrity of the details in
TM spectral bands through the fusion process. Otherwise, the synergy between visual and automatic methods for
lineaments extraction provides the best lineaments maps. The obtained product shows that the predominant lineaments
directions are the NE-SW and the NS, and then the second dominant direction is the NW-SE. The results integration in
GIS environment provides good discrimination of fractures and details of structural attributes. This research results
highlight the importance of the PALSAR fine mode L-HH and TM data fusion to enhance geological features.
This paper reports on a comparative study between supervised pixels and objects oriented classifications in precision agriculture context using hyperspectral and multispectral high spatial resolution images; which were acquired with the hyperspectral airborne Probe-1 and IKONOS sensors. These were acquired simultaneously with the same pixel size (4 m) over agricultural experimental site. The raw data were transformed to absolute ground reflectance using calibration coefficients and corrected atmospherically using MODTRAN-4.2 radiative transfer code. As well, they were rectified geometrically. Then, pixels oriented classifications were carried out using the maximum likelihood algorithm, and objects oriented classifications with a hierarchical segmentation and nearest neighbor classifier. After segmentation, statistics comparison on the mean difference to neighbor objects confirmed that the segments had minimum mixing effects in respect to other segmentation levels and neighboring ground entities. Accuracy analysis has been done using a global and individual classes Kappa coefficients. The obtained results confirm that the objects oriented classification improve significantly (~ 8%) the accuracy for individual crop classes’ comparatively to pixels oriented classification; also the global classification Kappa coefficient was improved with 5%, independently to the used sensor. Moreover, this study highlight the potential of hyperspectral data discrimination power for classification in precision agriculture generating unique spectral signatures, maximizing separability and distinguishing clearly among the considered classes.