Abstract | ||
---|---|---|
This paper presents an algorithm for object localization and segmentation. The algorithm uses machine learning, and statistical and combinatorial optimization tools to build a tracker that is robust to noise and occlusions. The method is based on a novel energy formulation and its dual use for object localization and segmentation. The energy uses kernel principal component analysis to incorporate shape and appearance constraints of the target object and the background. The energy arising from the procedure is equivalent to an un-normalized density function, thus providing a probabilistic interpretation to the procedure. Mean-shift optimization finds the most probable location of the target object. Graph-cut maximization on the localized object window in the image generates the globally optimal segmentation. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1109/ICMLA.2009.105 | Miami Beach, FL |
Keywords | Field | DocType |
combinatorial optimization tool,robust target localization,target object,mean-shift optimization,object localization,graph cut,optimal segmentation,dual use,localized object window,appearance constraint,graph-cut maximization,novel energy formulation,kernel principal component analysis,machine learning,mean shift,learning artificial intelligence,global optimization,principal component analysis,image segmentation,data mining,feature extraction,kernel,pixel,mathematical model,graph theory,shape,combinatorial optimization | Cut,Scale-space segmentation,Computer science,Segmentation-based object categorization,Image segmentation,Kernel principal component analysis,Artificial intelligence,Computer vision,Pattern recognition,Segmentation,Combinatorial optimization,Mean-shift,Machine learning | Conference |
ISBN | Citations | PageRank |
978-0-7695-3926-3 | 0 | 0.34 |
References | Authors | |
14 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Omar Arif | 1 | 22 | 5.87 |
Patricio Antonio Vela | 2 | 11 | 2.30 |