The adaptive urban traffic signal control (TSC) system became a development trend of intelligent transportation system (ITS). We investigated the vision based surveillance and to keep sight of the unpredictable and hardly measurable disturbances may perturb the traffic flow. We integrated and performed the vision based methodologies that include the object segmentation, classify and tracking methodologies to know well the real time measurements in urban road. According to the real time traffic measurement, we derived the adaptive traffic signal control algorithm to settle the red-green switchings of traffic lights both in "go straight or turn right" and "turn left" situations". By comparing the experimental result obtained by original traffic signal control system which improves the traffic queuing situation, we confirm the efficiency of our vision based adaptive TSC approach.