Efficient Monte Carlo sampler for detecting parametric objects in large scenes - Archive ouverte HAL Access content directly
Conference Papers Year : 2012

Efficient Monte Carlo sampler for detecting parametric objects in large scenes

(1, 2) , (1)
1
2

Abstract

Point processes have demonstrated e fficiency and competitiveness when addressing object recognition problems in vision. However, simulating these mathematical models is a diffi cult task, especially on large scenes. Existing samplers suff er from average performances in terms of computation time and stability. We propose a new sampling procedure based on a Monte Carlo formalism. Our algorithm exploits Markovian properties of point processes to perform the sampling in parallel. This procedure is embedded into a data-driven mechanism such that the points are non-uniformly distributed in the scene. The performances of the sampler are analyzed through a set of experiments on various object recognition problems from large scenes, and through comparisons to the existing algorithms.
Fichier principal
Vignette du fichier
camera_ready.pdf (5.33 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00742770 , version 1 (17-10-2012)

Identifiers

Cite

Yannick Verdie, Florent Lafarge. Efficient Monte Carlo sampler for detecting parametric objects in large scenes. ECCV 2012, Oct 2012, Firenze, Italy. pp.539-552, ⟨10.1007/978-3-642-33712-3_39⟩. ⟨hal-00742770⟩

Collections

INRIA INRIA2
301 View
503 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More