Spatio-Temporal Object Detection Proposals - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Spatio-Temporal Object Detection Proposals

Dan Oneata
  • Fonction : Auteur
  • PersonId : 946916
Jérôme Revaud
  • Fonction : Auteur
  • PersonId : 946914
Jakob Verbeek
Cordelia Schmid
  • Fonction : Auteur
  • PersonId : 831154

Résumé

Spatio-temporal detection of actions and events in video is a challenging problem. Besides the difficulties related to recognition, a major challenge for detection in video is the size of the search space defined by spatio-temporal tubes formed by sequences of bounding boxes along the frames. Recently methods that generate unsupervised detection proposals have proven to be very effective for object detection in still images. These methods open the possibility to use strong but computationally expensive features since only a relatively small number of detection hypotheses need to be assessed. In this paper we make two contributions towards exploiting detection proposals for spatio-temporal detection problems. First, we extend a recent 2D object proposal method, to produce spatio-temporal proposals by a randomized supervoxel merging process. We introduce spatial, temporal, and spatio-temporal pairwise supervoxel features that are used to guide the merging process. Second, we propose a new efficient supervoxel method. We experimentally evaluate our detection proposals, in combination with our new supervoxel method as well as existing ones. This evaluation shows that our supervoxels lead to more accurate proposals when compared to using existing state-of-the-art supervoxel methods.
Fichier principal
Vignette du fichier
proof.pdf (1.39 Mo) Télécharger le fichier
Vignette du fichier
oneata14eccv.png (443.86 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Loading...

Dates et versions

hal-01021902 , version 1 (09-07-2014)
hal-01021902 , version 2 (26-09-2014)

Identifiants

Citer

Dan Oneata, Jérôme Revaud, Jakob Verbeek, Cordelia Schmid. Spatio-Temporal Object Detection Proposals. ECCV - European Conference on Computer Vision, Sep 2014, Zurich, Switzerland. pp.737-752, ⟨10.1007/978-3-319-10578-9_48⟩. ⟨hal-01021902v2⟩
2368 Consultations
8058 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More