Diferenzas
Isto amosa as diferenzas entre a revisión seleccionada e a versión actual da páxina.
| Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
| hiperespectral:eadp_gpu [2019/04/17 09:27] – alvaro.accion | hiperespectral:eadp_gpu [2020/07/20 17:26] (actual) – [Extended Anisotropic Diffusion Profiles in GPU for Hyperspectral Imagery] alvaro.accion | ||
|---|---|---|---|
| Liña 2: | Liña 2: | ||
| Experimental results related to the paper Extended Anisotropic Diffusion Profiles in GPU for Hyperspectral Imagery by Álvaro Acción, Francisco Argüello, and Dora B. Heras. | Experimental results related to the paper Extended Anisotropic Diffusion Profiles in GPU for Hyperspectral Imagery by Álvaro Acción, Francisco Argüello, and Dora B. Heras. | ||
| + | https:// | ||
| ===== Abstract ===== | ===== Abstract ===== | ||
| Morphological profiles are common approach for extracting spatial information from hyperspectral images by extracting structural features. Additional kinds of profiles can be built based on different approaches as, for example, differential morphological profiles, or attribute profiles. Another technique used for characterizing spatial information on the images at different scales is based on computing edge-preserving filters such as anisotropic diffusion filters. Their main advantage is to preserve the distinctive morphological features of the images at a the cost of an iterative calculation. In this paper, the high computational cost associated to the construction of Anisotropic Diffusion Profiles (ADPs) is drastically reduced with the usage of GPUs. In particular, we propose a low cost computational approach for computing ADPs in Nvidia GPUs as well as a detailed characterization of the method, comparing it in terms of accuracy and structural similarity to other existing alternatives. | Morphological profiles are common approach for extracting spatial information from hyperspectral images by extracting structural features. Additional kinds of profiles can be built based on different approaches as, for example, differential morphological profiles, or attribute profiles. Another technique used for characterizing spatial information on the images at different scales is based on computing edge-preserving filters such as anisotropic diffusion filters. Their main advantage is to preserve the distinctive morphological features of the images at a the cost of an iterative calculation. In this paper, the high computational cost associated to the construction of Anisotropic Diffusion Profiles (ADPs) is drastically reduced with the usage of GPUs. In particular, we propose a low cost computational approach for computing ADPs in Nvidia GPUs as well as a detailed characterization of the method, comparing it in terms of accuracy and structural similarity to other existing alternatives. | ||
| Liña 16: | Liña 17: | ||
| The image below these lines corresponds to the EADP generated with the parameters detailed in the previous paragraph. Each row corresponds to one of the principal components extracted from the original hyperspectral image. The first column contains the principal component, and each subsequent column shows the filtered images produced by one iteration of the algorithm for a given process time. The process time is the same for all the images represented in the same column. | The image below these lines corresponds to the EADP generated with the parameters detailed in the previous paragraph. Each row corresponds to one of the principal components extracted from the original hyperspectral image. The first column contains the principal component, and each subsequent column shows the filtered images produced by one iteration of the algorithm for a given process time. The process time is the same for all the images represented in the same column. | ||
| {{ : | {{ : | ||
| + | |||
| + | The average results for 100 classification experiments using the EADP are as follows: | ||
| + | |||
| + | ^ Metric ^ Value ^ Std ^ | ||
| + | | OA | 92.45% | 1.18 | | ||
| + | | AA | 95.27% | 0.72 | | ||
| + | | Kappa | 91.34% | 1.34 | | ||
| + | |||
| + | |||
| + | ^ # ^ Class ^ Accuracy | ||
| + | | 1 | Alfalfa | ||
| + | | 2 | Corn-notill | ||
| + | | 3 | Corn-mintill | ||
| + | | 4 | Corn | 0.987 | | ||
| + | | 5 | Grass/ | ||
| + | | 6 | Grass-trees | ||
| + | | 7 | Grass-pasture-mowed | ||
| + | | 8 | Hay-windrowed | ||
| + | | 9 | Oats | 1 | | ||
| + | | 10 | Soybean-notill | ||
| + | | 11 | Soybean-mintill | ||
| + | | 12 | Soybean-clean | ||
| + | | 13 | Wheat | 0.994 | | ||
| + | | 14 | Woods | 0.998 | | ||
| + | | 15 | Bld-Grass-Trees | ||
| + | | 16 | Stone-Steel | ||