Detection of traffic flow volume is needed to get information about the number of vehicles on a street section. This information is required for traffic control. This study uses video data taken from four adjution street section in Manado City. Video data are processed using the background subtraction method in the segmentation process. Then morphological operation techniques are applied to improve segmentation results. The binarization method with a threshold value of 220 to eliminate shadows on vehicle objects. Vehicle shadows must be removed because it can reduce system accuracy especially if vehicle shadows are too large and connected to other vehicles. Accuracy results from vehicle detection are 95.04% for the Toar street, 94.62% for the Diponegoro street, 91.47% for the Lumimuut street and 95.18% for the 14 Februari street. Vehicle detection results will be calculated to get the number of vehicles then divided by the duration of observation time to get the traffic flow volume. The results of the traffic flow volume information are expected to be implemented on Smart Traffic Light.
Copyrights © 2025