Adaptive Background Extraction for Video Based Traffic Counter Application Using Gaussian Mixture Models Algorithm

The big cities in the world always face the traffic jam. This problem is caused by the increasing number of vehicle from time to time and the increase of vehicle is not anticipated with the development of new road section that is adequate. One important aspect in the traffic management concept is the need of traffic density data of every road section. Therefore, the purpose of this paper is to analyze the possibility of optimization on the use of video file recorded from CCTV camera for the visual observation and the tool for counting traffic density. The used method in this paper is adaptive background extraction with Gaussian Mixture Models algorithm. It is expected to be the alternative solution to get the data of traffic density with a quite adequate accuracy as one of aspects for decision making process in the traffic engineering