IEEE Transactions on Geoscience & Remote Sensing. Sep2000 Part 2 of 2, Vol. 38 Issue 5, p2402. 17p. 1 Diagram, 6 Charts, 10 Graphs.
Algorithms, Spectroradiometer, and Reflectance
Presents a study which described the prototyping of multi-angle imaging spectroradiometer (MISR), leaf area index (LAI) and fraction of photosynthetically active radiation (FPAR) algorithm with the polarization and directionality of the Earth's reflectance date over Africa. Advantages of using multi-angle data over single-data of surface reflectance; Mathematical basis for multi-angle remote sensing of vegetation; Results of prototyping.
IEEE Transactions on Geoscience & Remote Sensing. Sep2000 Part 2 of 2, Vol. 38 Issue 5, p2387. 15p. 1 Diagram, 3 Charts, 9 Graphs.
Algorithms, Landsat satellites, and Vegetation & climate
Presents a study which described the concepts of the algorithm of global leaf area index (LAI) and fraction of photosynthetically active radiation (FPAR). Effects of vegetation misclassification on LAI/FPAR retrievals; Analysis on the spectral signatures of land surface reflectances and Landsat data; Importance of vegetation in studies of global climate and biogeochemical cycles.
IEEE Transactions on Geoscience & Remote Sensing. Nov2012 Part 1, Vol. 50 Issue 11, p4369-4383. 15p.
Algorithms, Land cover, Virtual prototypes, Remote sensing, and Global environmental change
Training samples are usually very scarce in land cover classification, which challenges many supervised classifiers. To deal with this problem, this work presents a new learning approach, called local softened affine hull (LSAH). One of the most attractive characters of this classifier is its ability to expand the training set through exploiting “virtual” prototypes. During classification, this method utilizes some local prototypes around the query sample to construct SAH manifolds for each class, which are then employed to determine the label ownership of the query by the nearest neighbor rule. Because each SAH represents infinite “virtual” samples that approximate the “underlying” or “possible” variants of the real prototypes, the representational capacity of the training set is greatly enlarged; LSAH thus avoids the sample scarce problem. Meanwhile, as the number of the local prototypes is usually very small relative to the total training samples of each class, LSAH can run efficiently in classification tasks. LSAH's performance is demonstrated on some land cover classification tasks using three remote sensing images, in comparison with several popular algorithms, including maximum likelihood classifier, K-nearest neighbor, backpropagation neural network, and support vector machine. Experimental results show that the accuracy of LSAH is significantly higher than those of most of others, with the classification speed being quite comparable. [ABSTRACT FROM AUTHOR]