People Tracking Under Occlusion Using Gaussian Mixture Model and Fast Level Set Energy Minimization

Description
Title: People Tracking Under Occlusion Using Gaussian Mixture Model and Fast Level Set Energy Minimization
Authors: Moradiannejad, Ghazaleh
Date: 2013
Abstract: Tracking multiple articulated objects (such as a human body) and handling occlusion between them is a challenging problem in automated video analysis. This work proposes a new approach for accurately and steadily visual tracking people, which should function even if the system encounters occlusion in video sequences. In this approach, targets are represented with a Gaussian mixture, which are adapted to regions of the target automatically using an EM-model algorithm. Field speeds are defined for changed pixels in each frame based on the probability of their belonging to a particular person's blobs. Pixels are matched to the models using a fast numerical level set method. Since each target is tracked with its blob's information, the system is capable of handling partial or full occlusion during tracking. Experimental results on a number of challenging sequences that were collected in non-experimental environments demonstrate the effectiveness of the approach.
URL: http://hdl.handle.net/10393/24304
http://dx.doi.org/10.20381/ruor-3089
CollectionThèses, 2011 - // Theses, 2011 -
Files
Moradiannejad_Ghazaleh_2013_thesis.pdfExperiment data reading8.43 MBAdobe PDFOpen