A non-smooth non-local variational approach to saliency detection in real time
| Autor: | Emanuele Schiavi, Ana I. Muñoz, Eduardo Alcain, Antonio S. Montemayor |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Computational complexity theory
Computer science Feature vector 020207 software engineering Image processing 02 engineering and technology Energy minimization Domain (software engineering) Pattern recognition (psychology) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Point (geometry) Algorithm Image resolution Information Systems |
| Zdroj: | Journal of Real-Time Image Processing. 18:739-750 |
| ISSN: | 1861-8219 1861-8200 |
| DOI: | 10.1007/s11554-020-01016-4 |
| Popis: | 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 different scenario. We present a novel convex energy minimization problem in the feature space, which is efficiently 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 $$\times$$ 400 image resolution, making the method eligible for real time applications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink