High-Dimensional Statistical Measure for Region-of-Interest Tracking

• Published in: IEEE transactions on image processing 2009-06, Vol.18 (6), p.1266-1283
• Main Authors: Boltz, S., Debreuve, E., Barlaud, M.
• Format: Article
• Language: English
• Subjects: Applied sciences; Colored noise; Computer Science; Costs; Density measurement; Divergence; Engineering Sciences; Exact sciences and technology; Gabor filters; High-dimensional probability density function (PDF); Image processing; Information, signal and communications theory; k th nearest neighbor; Kullback-Leibler divergence; Luminance; Mathematical models; Motion pictures; Nearest neighbor searches; nonparametric estimation; Obstacles; Probability density function; Probability density functions; region-of-interest (ROI) tracking; Signal and Image processing; Signal processing; Similarity; Studies; Telecommunications and information theory; Testing; Tracking; Video sequences
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2009.2015158

This paper deals with region-of-interest (ROI) tracking in video sequences. The goal is to determine in successive frames the region which best matches, in terms of a similarity measure, a ROI defined in a reference frame. Some tracking methods define similarity measures which efficiently combine several visual features into a probability density function (PDF) representation, thus building a discriminative model of the ROI. This approach implies dealing with PDFs with domains of definition of high dimension. To overcome this obstacle, a standard solution is to assume independence between the different features in order to bring out low-dimension marginal laws and/or to make some parametric assumptions on the PDFs at the cost of generality. We discard these assumptions by proposing to compute the Kullback-Leibler divergence between high-dimensional PDFs using the k th nearest neighbor framework. In consequence, the divergence is expressed directly from the samples, i.e., without explicit estimation of the underlying PDFs. As an application, we defined 5, 7, and 13-dimensional feature vectors containing color information (including pixel-based, gradient-based and patch-based) and spatial layout. The proposed procedure performs tracking allowing for translation and scaling of the ROI. Experiments show its efficiency on a movie excerpt and standard test sequences selected for the specific conditions they exhibit: partial occlusions, variations of luminance, noise, and complex motion.