Efficient monte carlo sampler for detecting parametric objects in large scenes

Authors:
Yannick Verdié;Florent Lafarge
Affiliations:
INRIA Sophia Antipolis, France;INRIA Sophia Antipolis, France
Venue:
ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part III
Year:
2012

Citing 10
Cited 1

Image Segmentation by Data-Driven Markov Chain Monte Carlo

IEEE Transactions on Pattern Analysis and Machine Intelligence
Range Image Segmentation by an Effective Jump-Diffusion Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
Point Processes for Unsupervised Line Network Extraction in Remote Sensing

IEEE Transactions on Pattern Analysis and Machine Intelligence
Higher Order Active Contours

International Journal of Computer Vision
Depth Map Calculation for a Variable Number of Moving Objects using Markov Sequential Object Processes

IEEE Transactions on Pattern Analysis and Machine Intelligence
Object Extraction Using a Stochastic Birth-and-Death Dynamics in Continuum

Journal of Mathematical Imaging and Vision
Marked point process for vascular tree extraction on angiogram

EMMCVPR'07 Proceedings of the 6th international conference on Energy minimization methods in computer vision and pattern recognition
Geometric Feature Extraction by a Multimarked Point Process

IEEE Transactions on Pattern Analysis and Machine Intelligence
A marked point process for modeling lidar waveforms

IEEE Transactions on Image Processing
A 3-D marked point process model for multi-view people detection

CVPR '11 Proceedings of the 2011 IEEE Conference on Computer Vision and Pattern Recognition

Detecting parametric objects in large scenes by Monte Carlo sampling

International Journal of Computer Vision

Quantified Score

Hi-index	0.00

Visualization

Abstract

Point processes have demonstrated efficiency and competitiveness when addressing object recognition problems in vision. However, simulating these mathematical models is a difficult task, especially on large scenes. Existing samplers suffer 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.