Scene context is more than a Bayesian prior: Competitive vehicle detection with restricted detectors - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2014

Scene context is more than a Bayesian prior: Competitive vehicle detection with restricted detectors

Résumé

We present a new approach for making use of scene or situation context in object detection, aiming for state-of-the-art performance while dramatically reducing computa-tional cost. While existing approaches are inspired by Bayes' rule, training context-independent detectors and combining them with context priors in hindsight, we propose to integrate these context priors already into detector design, through algorithmic choices and/or pre-selection of training examples. Although such restricted detectors will, as a consequence, be valid only in regions compatible with context priors, the corresponding simplification of the object-vs-background de-cision problem will lead to reduced computation time and/or increased detection performance. We verify this experimentally by analyzing vehicle detection performance in a realistically simulated inner-city environment where context priors are defined by a road surface mask obtained from the simulation tool. Comparing a restricted detector, based on horizontal gradient detection refined by neural network confirmation, to a generic HOG+SVM-based approach taking into account the road context prior, we show that the restricted detector shows superior vehicle detection performance at a vastly reduced computational cost. We show qualitative results that permit the conclusion that the restricted detector will perform well on real-world scenes if appropriate road context priors are available.
Fichier principal
Vignette du fichier
hecht2014scene.pdf (707.52 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01098707 , version 1 (28-12-2014)

Identifiants

Citer

Thomas Hecht, Mrinal Mohit, Egor Sattarov, Alexander Gepperth. Scene context is more than a Bayesian prior: Competitive vehicle detection with restricted detectors. IEEE International Symposium on Intelligent Vehicles(IV), May 2014, Detroit, United States. pp.1358 - 1364, ⟨10.1109/IVS.2014.6856542⟩. ⟨hal-01098707⟩
1038 Consultations
2462 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More