Combining Appearance and Structure from Motion Features for Road Scene Understanding

Abstract : In this paper we present a framework for pixel-wise object segmentation of road scenes that combines motion and appearance features. It is designed to handle street-level imagery such as that on Google Street View and Microsoft Bing Maps. We formulate the problem in a CRF framework in order to probabilistically model the label likelihoods and the a priori knowledge. An extended set of appearance-based features is used, which consists of textons, colour, location and HOG descriptors. A novel boosting approach is then applied to combine the motion and appearance-based features. We also incorporate higher order potentials in our CRF model, which produce segmentations with precise object boundaries. We evaluate our method both quantitatively and qualitatively on the challenging Cambridge-driving Labeled Video dataset. Our approach shows an overall recognition accuracy of 84% compared to the state-of-the-art accuracy of 69%.
Type de document :
Communication dans un congrès
BMVC - British Machine Vision Conference, Sep 2009, London, United Kingdom. BMVA, 2009, 〈10.5244/C.26.127〉
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01216879
Contributeur : Karteek Alahari <>
Soumis le : samedi 17 octobre 2015 - 23:32:39
Dernière modification le : lundi 28 mai 2018 - 15:10:04
Document(s) archivé(s) le : jeudi 27 avril 2017 - 07:20:12

Fichier

sturgess09.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Paul Sturgess, Karteek Alahari, Lubor Ladicky, Philip H. S. Torr. Combining Appearance and Structure from Motion Features for Road Scene Understanding. BMVC - British Machine Vision Conference, Sep 2009, London, United Kingdom. BMVA, 2009, 〈10.5244/C.26.127〉. 〈hal-01216879〉

Partager

Métriques

Consultations de la notice

470

Téléchargements de fichiers

384