Background Subtraction Based on Codebook Model and Texture Feature
Geng-Cheng Lin, Sheng-Chih Yang, Chuin-Mu Wang, Che-Fu Lin · 2016
As technology developed, the surveillance system has been widely used in our daily lives. Monitoring systems, background filtering is a very important technology. Even so, in that respect are different dynamics in the surrounding ground for background filtering is a challenging problem, for example: leaves of the shaking, water fluctuations, the display flashes, the light changes to easily filter out background on error analysis. We indicate a coding book model combining the background removing algorithm of texture and background model using a coded book to benefit is the ability to effectively compress information to achieve the best focal ratio. Built using local binary pattern, texture because the local binary pattern, texture description quite well, but is computationally quite fast. And so, based along the texture of the connected object model results should be commingled with the code book can effectively raise the accuracy and scale down the error rate. In addition, in order to adjust to the current environment, added a short term information model to improve the background model update. And global change, grounded on the gradient Time difference method to work it. Experimental results indicate that our proposed algorithm for real time processing and better adaptability, tested in a different environment, and can get good credit rate.