Visual detection and tracking of unknown number of objects with nonparametric clustering methods

Official URL: http://risc01.sabanciuniv.edu/record=b1630640 (Table of Contents)

Clustering methods that do not expect the number of clusters to be known a priori and infer the number of clusters are known as nonparametric clustering methods in the literature. In this thesis we propose novel approaches to common computer vision applications using nonparametric clustering. We attack the problems of multiple object tracking and people counting. Our main motivation is to approach those as data association tasks where we de ne the data association problem speci c to the nature of the application and bene t from the nonparametric nature of the clustering model. We rst propose a detection free tracking method which tracks an unknown number of objects by clustering superpixels. We de ne the clusters as targets with spatial and visual features and track their changes through time by sequential clustering. The clusters yield tracked targets through time. We also propose a method for clustering short track segments into unknown number of tracks. The clustering similarity is de ned using the spatio-temporal features of the short track segments. The clustering process yields robust tracks of objects through time. We use this approach also to improve the tracking results of the detection free tracking proposed before. Finally we cluster raw person detector outputs to obtain groups of people in a scene and estimate the number of people inside a cluster using the features already extracted for clustering with a proposed metric which is invariant to perspective distortion.