Centre dedocumentation
scientifique

Hierarchical cellular automata for visual saliency / Yao Qin in International journal of computer vision, vol 126 n° 7 (July 2018)  

Public [article]  inInternational journal of computer vision > vol 126 n° 7 (July 2018) . - pp 751 - 770 Titre : Hierarchical cellular automata for visual saliency Type de document : Article/Communication Auteurs : Yao Qin, Auteur ; Mengyang Feng, Auteur ; Huchuan Lu, Auteur ; Garrison W. Cottrell, Auteur Année de publication : 2018 Article en page(s) : pp 751 - 770 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] apprentissage profond [Termes IGN] automate cellulaire [Termes IGN] classification bayesienne [Termes IGN] réseau neuronal artificiel [Termes IGN] zone saillante 3D Résumé : (Auteur) Saliency detection, finding the most important parts of an image, has become increasingly popular in computer vision. In this paper, we introduce Hierarchical Cellular Automata (HCA)—a temporally evolving model to intelligently detect salient objects. HCA consists of two main components: Single-layer Cellular Automata (SCA) and Cuboid Cellular Automata (CCA). As an unsupervised propagation mechanism, Single-layer Cellular Automata can exploit the intrinsic relevance of similar regions through interactions with neighbors. Low-level image features as well as high-level semantic information extracted from deep neural networks are incorporated into the SCA to measure the correlation between different image patches. With these hierarchical deep features, an impact factor matrix and a coherence matrix are constructed to balance the influences on each cell’s next state. The saliency values of all cells are iteratively updated according to a well-defined update rule. Furthermore, we propose CCA to integrate multiple saliency maps generated by SCA at different scales in a Bayesian framework. Therefore, single-layer propagation and multi-scale integration are jointly modeled in our unified HCA. Surprisingly, we find that the SCA can improve all existing methods that we applied it to, resulting in a similar precision level regardless of the original results. The CCA can act as an efficient pixel-wise aggregation algorithm that can integrate state-of-the-art methods, resulting in even better results. Extensive experiments on four challenging datasets demonstrate that the proposed algorithm outperforms state-of-the-art conventional methods and is competitive with deep learning based approaches. Numéro de notice : A2018-413 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s11263-017-1062-2 Date de publication en ligne : 23/02/2018 En ligne : https://doi.org/10.1007/s11263-017-1062-2 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90896 [article]