GDL

Traffic jam is a major traffic problem often found in big cities of Indonesia. It is because the number of vehicles increases annually. Therefore, a simulation to detect the number of vehicles in every lane of traffic is needed to monitor the traffic. Traffic control is also required in order to reduce traffic jam. This paper develops a vehicle detection and counting system using image processing. Detection is carried out using image segmentation which is processed by object filtering and blob extraction. Morphological operators are employed for blob extraction. Testing is conducted using a video obtained from the ATCS Bandung. The video is taken at the Laswi - A. Yani intersection Bandung. Software prototypes are created in C++, using Windows Forms Application as a programming library for Windows and Open CV for image processing module. The result shows that blob detection method can give good results if there is no intersection between blobs of each car. The performance is poor when this method is used for heavy traffic conditions, where the cars are close to each other. The performance level of sensitivity is 91.67%, precision is 61.11%, specificity is 80.55%, f-Measure is 73.33%, and accuracy is 83.33%. The accuracy for vehicles detection on sunny condition is 82.11% and reduced by 76.50% on rainy condition. This method works better in quiet condition, with accuracy of 83.07%, and is reduced by 67.70% in crowded condition. The average processing time is 0.042 seconds when using video, and 0.033 seconds using real camera.

Beri Komentar ?#(0) | Bookmark