Ph.D
Group : Parallel Systems

Study and optimization of color object tracking algorithms

Starts on 01/10/2009
Advisor : ETIEMBLE, Daniel

Funding :
Affiliation : Université Paris-Saclay
Laboratory : LRI PARALLELISME

Defended on 27/09/2013, committee :

Research activities :

Abstract :
The work of this thesis focuses on the improvement and optimization of the color object
tracking algorithm Mean-Shift with both a strength point of view to improve the accuracy
and an architectural point of view to improve execution speed.

In this method, the tracked object is modeled by its color characteristics. The first
part of the work consisted in improving the robustness of the tracking. For this, the
impact of color space representation on the quality of tracking has been studied, and a
method for the selection of the color space that best represents the object to be tracked
has been proposed. The method has been coupled with a strategy determining the
appropriate time to recalculate the model. Color space selection method was also used in
collaboration with another object tracking algorithm - the covariance tracking - to
further improve the tracking robustness for particularly difficult sequences.

The final goal is to obtain a complete system to be implement on an embedded and real-time
operating system using commercial off-the-shelf product. Hardware targets are multi-core
processors SIMD.

Specific change have been made to the algorithm to better match the target architecture.
We use multiple parameters to customise their complexity and ensure they run in real time
on different platforms and various sizes of images or objects. Such compromise between
speed and performance makes real-time tracking possible on ARM processors like Cortex A9.

CAUSAL LEARNING FOR DIAGNOSTIC SUPPORT


CAUSAL UNCERTAINTY QUANTIFICATION UNDER PARTIAL KNOWLEDGE AND LOW DATA REGIMES


MICRO VISUALIZATIONS: DESIGN AND ANALYSIS OF VISUALIZATIONS FOR SMALL DISPLAY SPACES
The topic of this habilitation is the study of very small data visualizations, micro visualizations, in display contexts that can only dedicate minimal rendering space for data representations. For several years, together with my collaborators, I have been studying human perception, interaction, and analysis with micro visualizations in multiple contexts. In this document I bring together three of my research streams related to micro visualizations: data glyphs, where my joint research focused on studying the perception of small-multiple micro visualizations, word-scale visualizations, where my joint research focused on small visualizations embedded in text-documents, and small mobile data visualizations for smartwatches or fitness trackers. I consider these types of small visualizations together under the umbrella term ``micro visualizations.'' Micro visualizations are useful in multiple visualization contexts and I have been working towards a better understanding of the complexities involved in designing and using micro visualizations. Here, I define the term micro visualization, summarize my own and other past research and design guidelines and outline several design spaces for different types of micro visualizations based on some of the work I was involved in since my PhD.