Détail de l'auteur
Auteur Dafei Huang |
Documents disponibles écrits par cet auteur (1)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externes
Applying detection proposals to visual tracking for scale and aspect ratio adaptability / Dafei Huang in International journal of computer vision, vol 122 n° 3 (May 2017)
[article]
Titre : Applying detection proposals to visual tracking for scale and aspect ratio adaptability Type de document : Article/Communication Auteurs : Dafei Huang, Auteur ; Lei Luo, Auteur ; Zhaoyun Chen, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 524 – 541 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] appariement d'images
[Termes IGN] détection d'objet
[Termes IGN] filtre adaptatif
[Termes IGN] optimisation (mathématiques)Résumé : (auteur) The newly proposed correlation filter based trackers can achieve appealing performance despite their great simplicity and superior speed. However, this kind of object trackers is not born with scale and aspect ratio adaptability, thus resulting in suboptimal tracking accuracy. To tackle this problem, this paper integrates the class-agnostic detection proposal method, which is widely adopted in object detection area, into a correlation filter tracker. In the tracker part, optimizations such as feature integration, robust model updating and proposal rejection are applied for efficient integration. As for proposal generation, through integrating and comparing four detection proposal generators along with two baseline methods, the quality of detection proposals is found to have considerable influence on tracking accuracy. Therefore, as the most promising proposal generator, EdgeBoxes is chosen and further enhanced with background suppression. Evaluations are mainly performed on a challenging 50-sequence dataset (OTB50) and its two subsets, 28 sequences with significant scale variation and 14 sequences with obvious aspect ratio change. Among the trackers equipped with different proposal generators, state-of-the-art trackers and existing correlation filter variants, our proposed tracker reports the highest accuracy while running efficiently at an average speed of 20.4 frames per second. Additionally, numerical performance analysis in per-sequence manner and experiment results on VOT2014 dataset are also presented to enable deeper insights into our approach. Numéro de notice : A2017-379 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1007%2Fs11263-016-0974-6 En ligne : https://doi.org/10.1007/s11263-016-0974-6 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=85930
in International journal of computer vision > vol 122 n° 3 (May 2017) . - pp 524 – 541[article]