Optimization of lateral interaction in accumulative computation on GPU-based platform

The lateral interaction in accumulative computation (LIAC) algorithm is a biologically inspired method that allows us to detect moving objects from image sequences acquired from fixed surveillance cameras. This method achieves excellent precision but requires a high processing time. Sequential imple...

Descripción completa

Detalles Bibliográficos
Autores: Bermúdez Marín, Aurelio, Montero Simarro, Francisco, López Bonal, María Teresa, Fernández Caballero, Antonio, Sánchez García, José Luis
Tipo de recurso: artículo
Fecha de publicación:2019
País:España
Institución:Universidad de Castilla-La Mancha
Repositorio:RUIdeRA. Repositorio Institucional de la UCLM
OAI Identifier:oai:ruidera.uclm.es:10578/32909
Acceso en línea:https://doi.org/10.1007/s11227-018-02736-y
https://hdl.handle.net/10578/32909
Access Level:acceso abierto
Palabra clave:Acceleration
GPU
HPC
Lateral interaction in accumulative computation
Motion detection
Optimization
Descripción
Sumario:The lateral interaction in accumulative computation (LIAC) algorithm is a biologically inspired method that allows us to detect moving objects from image sequences acquired from fixed surveillance cameras. This method achieves excellent precision but requires a high processing time. Sequential implementation is too slow and cannot achieve real-time processing. In this paper, we present several improvements to the LIAC algorithm that increase its efficiency in terms of execution time and energy consumption. In particular, a GPU-based implementation delivers the same precision and is notably faster and more energy efficient than the sequential implementation.