Detecting parametric objects in large scenes by Monte Carlo sampling

被引:17
作者
Verdie, Yannick [1 ]
Lafarge, Florent [1 ]
机构
[1] INRIA, Sophia Antipolis, France
基金
欧洲研究理事会;
关键词
Stochastic modeling; Monte Carlo sampling; Object detection; Large scenes; Energy minimization; Point processes; Markov random fields; MARKED POINT PROCESS; ENERGY MINIMIZATION; IMAGE SEGMENTATION; EXTRACTION;
D O I
10.1007/s11263-013-0641-0
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Point processes constitute a natural extension of Markov random fields (MRF), designed to handle parametric objects. They have shown efficiency and competitiveness for tackling object extraction problems in vision. Simulating these stochastic models is however a difficult task. The performances of the existing samplers are limited in terms of computation time and convergence stability, especially on large scenes. We propose a new sampling procedure based on a Monte Carlo formalism. Our algorithm exploits the Markovian property of point processes to perform the sampling in parallel. This procedure is embedded into a data-driven mechanism so that the points are distributed in the scene in function of spatial information extracted from the input data. The performances of the sampler are analyzed through a set of experiments on various object detection problems from large scenes, including comparisons to the existing algorithms. The sampler is also tested as optimization algorithm for MRF-based labeling problems.
引用
收藏
页码:57 / 75
页数:19
相关论文
共 39 条
[1]  
[Anonymous], 2011, P MACHINE LEARNING R
[2]  
Baddeley A., 1993, STAT IMAGES, V1, P231, DOI DOI 10.1080/02664769300000065
[3]  
Benchmark, 2013, DATASETS RESULTS EVA
[4]  
BESAG J, 1986, J R STAT SOC B, V48, P259
[5]   Fast approximate energy minimization via graph cuts [J].
Boykov, Y ;
Veksler, O ;
Zabih, R .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2001, 23 (11) :1222-1239
[6]  
Byrd J., 2010, IEEE INT S PAR DISTR
[7]  
Chai D., 2012, INT SOC PHOT REM SEN
[8]  
Chai D., 2013, RECOVERING LINE NETW
[9]  
Descombes X., 2011, STOCHASTIC GEOMETRY
[10]   Object Extraction Using a Stochastic Birth-and-Death Dynamics in Continuum [J].
Descombes, Xavier ;
Minlos, Robert ;
Zhizhina, Elena .
JOURNAL OF MATHEMATICAL IMAGING AND VISION, 2009, 33 (03) :347-359