EC-Libros e capítulos de libros
http://hdl.handle.net/10347/15730
2024-03-28T14:19:18ZScene Recognition through Visual Attention and Image Features: A Comparison between SIFT and SURF Approaches
http://hdl.handle.net/10347/32541
Scene Recognition through Visual Attention and Image Features: A Comparison between SIFT and SURF Approaches
López García, Fernando; Fernández Vidal, Xosé Ramón; Pardo, Xosé Manuel; Dosil, Raquel
Phuong Cao, Tam
In this work we study how we can use a novel model of spatial saliency (visual attention)
combined with image features to significantly accelerate a scene recognition application
and, at the same time, preserve recognition performance. To do so, we use a mobile robotlike
application where scene recognition is carried out through the use of image features to
characterize the different scenarios, and the Nearest Neighbor rule to carry out the
classification. SIFT and SURF are two recent and competitive alternatives to image local
featuring that we compare through extensive experimental work. Results from the
experiments show that SIFT features perform significantly better than SURF features
achieving important reductions in the size of the database of prototypes without significant
losses in recognition performance, and thus, accelerating scene recognition. Also, from the
experiments it is concluded that SURF features are less distinctive when using very large
databases of interest points, as it occurs in the present case.
2011-01-01T00:00:00ZAlineamiento de imágenes multiespectrales de teledetección en un clúster de GPUs
http://hdl.handle.net/10347/29327
Alineamiento de imágenes multiespectrales de teledetección en un clúster de GPUs
Ordóñez Iglesias, Álvaro; Blanco Heras, Dora; Argüello Pedreira, Francisco Santiago
El registro o alineamiento de imágenes de teledetección multiespectrales o hiperespectrales es una tarea fundamental tras la captura de dichas imágenes, ya que permite alinear las diferentes bandas de la imagen o diferentes imágenes entre sí para construir escenas de mayor tamaño o para construir imágenes de mayor resolución. En los casos en los que es necesario registrar las bandas de una o varias imágenes y posteriormente diferentes imágenes, el tiempo de ejecución es muy alto debido no solo a la complejidad del proceso de registrado sino también a que es necesario ejecutar muchas veces dicho proceso. En este artículo se presenta una implementación multinodo-multiGPU para el registro de bandas e imágenes multiespectrales utilizando el algoritmo HSI-KAZE. Los distintos conjuntos de datos son distribuidos entre los nodos disponibles de un clúster de GPUs usando MPI y a su vez, cada nodo, distribuye las bandas e imágenes de un mismo conjunto entre las distintas GPUs del nodo utilizando OpenMP. Las GPUs son programadas mediante CUDA
Jornadas de la Sociedad de Arquitectura y Tecnología de Computadores (SARTECO 2022)
2022-01-01T00:00:00ZComparing area–based and feature–based methods for co–registration of multispectral bands on GPU
http://hdl.handle.net/10347/27070
Comparing area–based and feature–based methods for co–registration of multispectral bands on GPU
Ordóñez Iglesias, Álvaro; Blanco Heras, Dora; Argüello Pedreira, Francisco Santiago
Registration is required as a previous step for processing multispectral images. The different bands captured by each sensor for each image, as well as the different images corresponding to the same area, need to be aligned. In this paper, a 2– level registration scheme comparing the results obtained by the hyperspectral Fourier–Mellin (HYFM) and hyperspectral KAZE (HSI–KAZE) registration methods is proposed. It is designed for efficient implementation in a multi-GPU system in which different scenes are registered in parallel on different GPUs
This a post-print of the article “Comparing Area-Based and Feature-Based Methods for CoRegistration of Multispectral Bands on GPU” published in the Proceedings of IGARSS 2021 - 2021 IEEE International Geoscience and Remote Sensing Symposium
2021-01-01T00:00:00ZTexture-based analysis of hydrographical basins with multispectral imagery
http://hdl.handle.net/10347/26960
Texture-based analysis of hydrographical basins with multispectral imagery
González Bascoy, Pedro; Suárez Garea, Jorge Alberto; Blanco Heras, Dora; Argüello Pedreira, Francisco Santiago; Ordóñez Iglesias, Álvaro
In this paper the problem of studying the presence of different vegetation species and artificial structures in the riversides by using multispectral remote sensing information is studied. The information provided contributes to control the water resources in a region in northern Spain called Galicia. The problem is solved as a supervised classification computed over five-band multispectral images obtained by an Unmanned Aerial Vehicle (UAV). A classification scheme based on the extraction of spatial, spectral and textural features previous to a hierarchical classification by Support Vector Machine (SVM) is proposed. The scheme extracts the spatial-spectral information by means of a segmentation algorithm based on superpixels and by computing morphological operations over the bands of the image in order to generate an Extended Morphological Profile (EMP). The texture features extracted help in the classification of vegetation classes as the spatial-spectral features for these classes are not discriminant enough. The classification is computed over segments instead of pixels, thus reducing the computational cost. The experimental results over four real multispectral datasets from Galician riversides show that the proposed scheme improves over a standard classification method achieving very high accuracy results
2019-01-01T00:00:00Z