Méthodes probabiliste pour le suivi de points et l'analyse d'images biologiques
Maël Primet · HAL (Le Centre pour la Communication Scientifique Directe) · 2011
The subject of this thesis is the problem of object tracking, that we approached using statistical methods. The first contribution of this work is the conception of a tracking algorithm of bacterial cells in a sequence of image, to recover their lineage; this work has led to the implementation of a software suite that is currently in use in a research laboratory. The second contribution is a theoretical study of the detection of trajectories in a cloud of points. We define a trajectory detector using the a-contrario statistical framework, which requires essentially no parameter to run. This detector yields remarkable results, and is in particular able to detect trajectories in sequences containing a large number of noise points, while keeping a very low number of false detections. We then study more specifically the correspondence problem between two point clouds, a problem often encountered for the detection of trajectories or the matching of stereographic images. We first introduce a theoretically optimal model for the point correspondence problem that makes it possible to study the performances of several classical algorithms in a variety of conditions. We then formulate a parameterless point correspondence algorithm using the a-contrario framework, that enables us to define a new trajectory tracking algorithm.