Towards hash similarity and geometric-based image filtering to lighten underwater photo-mosaicing

This paper presents a novel strategy to filter out images that contain redundant information when building photomosaics from the sea bottom. The goal is to alleviate computational resources and processing time in their construction. The algorithm operates in a set of sequential steps, extracting ima...

Descripción completa

Detalles Bibliográficos
Autores: Baños Castelló, Pol|||0000-0003-0780-3255, Bonín-Font, Francisco
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/392127
Acceso en línea:https://hdl.handle.net/2117/392127
Access Level:acceso abierto
Palabra clave:Image processing
Photo-mosaicing
Image hash
SIFT features
Imatges -- Processament
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
Descripción
Sumario:This paper presents a novel strategy to filter out images that contain redundant information when building photomosaics from the sea bottom. The goal is to alleviate computational resources and processing time in their construction. The algorithm operates in a set of sequential steps, extracting images from video sequences following camera translation and rotation pre-defined constraints and removing redundant data using hash similarity and SIFT feature matching techniques.