Fast sparse subspace identification tools with applications to dynamic vision
Mustafa Ayazoğlu · 2012
Dynamic vision, a sub-area of computer vision, focuses on the problems where some sort of gradual evolution of some variables in time (or space) exists. So the evolution of the variables contains important information. However the utilization of this extra information in the variable evolution brings added complexity and it is mathematically hard to exploit without specially tailored tools. Hence usually the existing methods for dynamic vision, either discard the dynamics information or use it in a limited manner. However when used wisely it helps to solve the problems and increases the robustness of the methods.