What, Where & How Many? Combining Object Detectors and CRFs - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2010

What, Where & How Many? Combining Object Detectors and CRFs

Abstract

Computer vision algorithms for individual tasks such as object recognition, detection and segmentation have shown impressive results in the recent past. The next challenge is to integrate all these algorithms and address the problem of scene understanding. This paper is a step towards this goal. We present a probabilistic framework for reasoning about regions, objects, and their attributes such as object class, location, and spatial extent. Our model is a Conditional Random Field defined on pixels, segments and objects. We define a global energy function for the model, which combines results from sliding window detectors, and low-level pixel-based unary and pairwise relations. One of our primary contributions is to show that this energy function can be solved efficiently. Experimental results show that our model achieves significant improvement over the baseline methods on CamVid and PASCAL VOC datasets.
Fichier principal
Vignette du fichier
ladicky10.pdf (732.56 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01216730 , version 1 (16-10-2015)

Identifiers

Cite

Lubor Ladicky, Paul Sturgess, Karteek Alahari, Chris Russell, Philip H. S. Torr. What, Where & How Many? Combining Object Detectors and CRFs. ECCV - European Conference on Computer Vision, Sep 2010, Heraklion, Crete, Greece. ⟨10.1007/978-3-642-15561-1_31⟩. ⟨hal-01216730⟩
61 View
360 Download

Altmetric

Share

Gmail Facebook X LinkedIn More