Rain forest classification based on SAR texture Export

@article{citeulike:280388, abstract = {This paper applies the concepts of optimized texture segmentation to the classification of SAREX-92 data from the Amazon rain forest. Initially, a simple scene is classified using both SAR texture and Band 5 Landsat TM imagery, yielding forest and not-forest joint probabilities of 97.8\% and 96.5\%, respectively. When the same procedure is applied to a more complicated scene, including regenerating areas, the equivalent results are 93.8\% and 67.3\%, When predictable corrections for shadowing and the presence of a highway are introduced, the not-forest joint probability is improved to about 78\%. The residual discrepancy is then a consequence of the different ways in which the SAR texture and TM intensity respond to regenerating areas in the scene}, author = {Oliver, C. J.}, citeulike-article-id = {280388}, citeulike-linkout-0 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=841988}, journal = {Geoscience and Remote Sensing, IEEE Transactions on}, keywords = {classification, clutter, forest, k-distribution, sar, texture}, number = {2}, pages = {1095--1104}, posted-at = {2005-08-12 15:52:37}, priority = {5}, title = {Rain forest classification based on SAR texture}, url = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=841988}, volume = {38}, year = {2000} }

TY - JOUR ID - citeulike:280388 L3 - citeulike-article-id:280388 N2 - This paper applies the concepts of optimized texture segmentation to the classification of SAREX-92 data from the Amazon rain forest. Initially, a simple scene is classified using both SAR texture and Band 5 Landsat TM imagery, yielding forest and not-forest joint probabilities of 97.8% and 96.5%, respectively. When the same procedure is applied to a more complicated scene, including regenerating areas, the equivalent results are 93.8% and 67.3%, When predictable corrections for shadowing and the presence of a highway are introduced, the not-forest joint probability is improved to about 78%. The residual discrepancy is then a consequence of the different ways in which the SAR texture and TM intensity respond to regenerating areas in the scene IS - 2 JF - Geoscience and Remote Sensing, IEEE Transactions on EP - 1104 TI - Rain forest classification based on SAR texture VL - 38 SP - 1095 KW - classification KW - clutter KW - forest KW - k-distribution KW - sar KW - texture AU - Oliver, CJ PY - 2000/// UR - http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=841988 ER -