Extended attribute profiles on GPU applied to hyperspectral image classification
- 105 Downloads
Extended profiles are an important technique for modelling the spatial information of hyperspectral images at different levels of detail. They are used extensively as a preprocessing stage, especially in classification schemes. In particular, attribute profiles, based on the application of morphological attribute filters to the connected components of the image, have been shown to provide very good results. In this paper we present a parallel implementation of the attribute profiles in CUDA for multispectral and hyperspectral imagery considering the attributes area and standard deviation. The profile computation is based on the max-tree approach but without building the tree itself. Instead, a matrix-based data structure is used along with a recursive flooding (component merging) and filter process. Additionally, a previous feature extraction stage based on wavelets is applied to the hyperspectral image in order to extract the most valuable spectral information, reducing the size of the resulting profile. This scheme efficiently exploits the thousands of available threads on the GPU, obtaining a considerable reduction in execution time as compared to the OpenMP CPU implementation.
KeywordsRemote sensing Hyperspectral Attribute profiles Supervised classification Real-time GPU
This work was supported in part by the Consellería de Cultura, Educación e Ordenación Universitaria [Grant numbers GRC2014/008 and ED431G/08] and Ministry of Education, Culture and Sport, Government of Spain [Grant number TIN2016-76373-P]. Both are co-funded by the European Regional Development Fund (ERDF).
- 3.Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:27:1–27:27Google Scholar
- 4.Darbon J, Akgül CB (2005) An efficient algorithm for attribute openings and closings. In: 2005 13th European Signal Processing Conference, pp 1–4Google Scholar
- 6.Ghamisi P, Maggiori E, Li S, Souza R, Tarabalka Y, Moser G, De Giorgi A, Fang L, Chen Y, Chi M, Serpico S, Benediktsson J (2018) New frontiers in spectral–spatial hyperspectral image classification: the latest advances based on mathematical morphology, markov random fields, segmentation, sparse representation, and deep learning. IEEE Geosci Remote Sens Mag 6(3):10–43CrossRefGoogle Scholar
- 8.Matas P, Dokládalová E, Akil M, Grandpierre T, Najman L, Poupa M, Georgiev V (2008) Parallel algorithm for concurrent computation of connected component tree. Springer, Berlin, pp 230–241Google Scholar
- 12.Oliveira V, de Alencar Lotufo R (2010) A study on connected components labeling algorithms using GPUs. In: Proceedings: 23rd SIBGRAPI Conference on Graphics, Patterns and ImagesGoogle Scholar
- 15.Quesada-Barriuso P, Heras DB, Argüello F, Demir B (2018) GPU computation of attribute profiles for remote sensing image classification. In: Aguiar JV (ed) Proceedings of the 18th International Conference on Computational and Mathematical Methods in Science and EngineeringGoogle Scholar
- 18.Vincent L (1993) Grayscale area openings and closings, their efficient implementation and applications. In: Proceedings of EURASIP Workshop on Mathematical Morphology and its Applications to Signal Processing, pp 22–27Google Scholar