Abstract | ||
---|---|---|
In this letter, we formulate a land-use (LU) classification problem within a compressive sensing (CS) fusion framework. CS aims at providing a compact representation form after a given query image has been processed with an opportune feature extraction type. In particular, residuals are generated from the image reconstruction with dictionaries associated with the available set of possible LUs and gathered to form a single-feature image pattern. The patterns obtained from different types of features are then fused to provide the final LU estimate. Two simple fusion strategies are adopted for such purpose. As demonstrated by experiments ran on the basis of a public benchmark database, the proposed method can achieve substantial classification accuracy gains over reference methods. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/LGRS.2015.2453130 | Geoscience and Remote Sensing Letters, IEEE |
Keywords | Field | DocType |
Compressive sensing (CS),cooccurrence of adjacent local binary patterns (CoALBP),data fusion,gradient local autocorrelations (GLAC),histogram of oriented gradients (HOG),land-use (LU) classification | Data mining,Histogram,Image fusion,Feature detection (computer vision),Fusion,Artificial intelligence,Compressed sensing,Matching pursuit algorithms,Iterative reconstruction,Computer vision,Pattern recognition,Feature extraction,Mathematics | Journal |
Volume | Issue | ISSN |
PP | 99 | 1545-598X |
Citations | PageRank | References |
16 | 0.58 | 20 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mohamed Lamine Mekhalfi | 1 | 62 | 8.01 |
Farid Melgani | 2 | 1100 | 80.98 |
Yakoub Bazi | 3 | 672 | 43.66 |
Naif Alajlan | 4 | 839 | 50.51 |