Utilize este identificador para referenciar este registo:
https://hdl.handle.net/10316/93988
Título: | Fast Scale-Invariant Feature Transform on GPU | Outros títulos: | Fast Scale-Invariant Feature Transform on GPU | Autor: | Barreiros, João Carlos da Costa | Orientador: | Fernandes, Gabriel Falcão Paiva | Palavras-chave: | Feature extraction; Scale-invariant feature transform; GPGPU; CUDA; Parallel Programming; Feature extraction; Scale-invariant feature transform; GPGPU; CUDA; Parallel Programming | Data: | 17-Dez-2020 | Título da revista, periódico, livro ou evento: | Fast Scale-Invariant Feature Transform on GPU | Local de edição ou do evento: | DEEC | Resumo: | Feature extraction of high-resolution images is a challenging procedure in low-power signal processing applications. This thesis describes how to optimize and efficiently parallelize the scale-invariant feature transform (SIFT) feature detection algorithm and maximize the use of bandwidth on the GPUsubsystem. Together with the minimization of data communications between host and device, the successful parallelization of all the main kernels used in SIFT allowed a global speedup in high-resolution images above 78x while being more than an order of magnitude energy efficient (FPS/W) than its serial counterpart. From the 3 GPUs tested, the low-power GPU has shown superior energy efficiency -- 44 FPS/W. Feature extraction of high-resolution images is a challenging procedure in low-power signal processing applications. This thesis describes how to optimize and efficiently parallelize the scale-invariant feature transform (SIFT) feature detection algorithm and maximize the use of bandwidth on the GPUsubsystem. Together with the minimization of data communications between host and device, the successful parallelization of all the main kernels used in SIFT allowed a global speedup in high-resolution images above 78x while being more than an order of magnitude energy efficient (FPS/W) than its serial counterpart. From the 3 GPUs tested, the low-power GPU has shown superior energy efficiency -- 44 FPS/W. |
Descrição: | Dissertação de Mestrado Integrado em Engenharia Electrotécnica e de Computadores apresentada à Faculdade de Ciências e Tecnologia | URI: | https://hdl.handle.net/10316/93988 | Direitos: | openAccess |
Aparece nas coleções: | UC - Dissertações de Mestrado |
Ficheiros deste registo:
Ficheiro | Descrição | Tamanho | Formato | |
---|---|---|---|---|
DissertacaoJoaoBarreiros_23 versão definitiva.pdf | 12.74 MB | Adobe PDF | Ver/Abrir |
Google ScholarTM
Verificar
Este registo está protegido por Licença Creative Commons