A non-smooth, non-local variational approach to saliency detection in real time

In this paper, we propose and solve numerically a general non-smooth, non-local variational model to tackle the saliency detection problem in natural images. In order to overcome the typical drawback of the non-local methods in image processing, which mainly is the inherent computational complexity...

Descripción completa

Detalles Bibliográficos
Autores: Alcaín, Eduardo, Muñoz Montalvo, Ana Isabel, Schiavi, Emanuele, S. Montemayor, Antonio
Tipo de recurso: artículo
Fecha de publicación:2023
País:España
Institución:Universidad Rey Juan Carlos
Repositorio:BURJC-Digital. Repositorio Institucional de la Universidad Rey Juan Carlos
OAI Identifier:oai:burjcdigital.urjc.es:10115/26897
Acceso en línea:https://hdl.handle.net/10115/26897
Access Level:acceso abierto
Palabra clave:Variational methods
Convex analysis
Primal-dual
Non-local image processing
Saliency segmentation
GPU
Superpixels
Descripción
Sumario:In this paper, we propose and solve numerically a general non-smooth, non-local variational model to tackle the saliency detection problem in natural images. In order to overcome the typical drawback of the non-local methods in image processing, which mainly is the inherent computational complexity of non-local calculus, as the non-local derivatives are computed w.r.t every point of the domain, we propose a diferent scenario. We present a novel convex energy minimization problem in the feature space, which is eficiently solved by means of a non-local primal-dual method. Several implementations and discussions are presented taking care of the computing platforms, CPU and GPU, achieving up to 33 fps and 62 fps respectively for 300×400 image resolution, making the method eligible for real time applications.