Performance is essential for video analytic applications since algorithms are usually computationally heavy and such systems are supposed to work almost in real time. From one side it can be increased by improving & changing algorithms. This is a major way since it allows to increase performance dramatically. From another side performance can be increased little bit more by relatively simple way – using of good compiler and by tuning of compile options. Let see how it can be done in real programs.

A modern video analytic system depending on business/customer requirements should work in different situations/conditions. Complex, noisy background with many different objects/textures, changing lighting conditions, shadows, lack of light, weather conditions (for outdoor system installations) like rain, snow, fog and others, motion blur, camera movements, cameral sensor quality, camera resolution, camera focus issues, camera internal optimizations, color temperature, end many other factors make development of the good object recognition software a challenging, almost impossible task. In addition, the usual requirement is that the system should work in real time, which makes this task even more difficult.