چکیده مقاله
Nowadays closed circuit televisions CCTV have been highly developed andhave been utilized in most of road intersections and places with heavycongestion CCTVs are very useful for automation of traffic control by vehicledetection and computing the number of vehicles automatically from CCTVs;controlling urban roads, as well as accident management with high accuracy andspeed would be possible In this paper, a different procedure for detecting andnumerating vehicles was proposed from CCTV traffic camera movies In thisregard, at first a region of roads was detected using the frames of a short part ofCCTV movies Then in order to gather the training data in the detected region,some features were selected according to their ability in clarifying vehicles Afterwards, a support vector machine SVM and an artificial neural network ANN were proposed for detecting vehicles Finally, the number of vehicleswere computed by binary results from detected vehicles Comparing the resultsof the proposed ANN based method with the proposed SVM one reveals that theproposed SVM based method has a better performance in computing the numberof vehicles in cameras that have a long distant from vehicles
کلیدواژهها
نویسندگان
Hamed Amini
Civil Engineering Faculty, Tafresh State University, Tafresh, Iran
Parham Phlavani
Center of Excellence in Geomatic Eng in Diseater Management, Dept of Surveying andGeomatic Eng, College of Eng , University of Tehran, Tehran, Iran
Roohollah Karimi
Civil Engineering Faculty, Tafresh State University, Tafresh, Iran
شیوه ارجاع
Amini, Hamed and Phlavani, Parham and Karimi, Roohollah,1392,Detecting and Numerating Vehicles from CCTV Traffic CameraMovies Using a Support Vector Machine,The 13th International Conference on Traffic and Transportation Engineering,Tehran
ارائهشده در
مجموعه مقالات سیزدهمین کنفرانس بین المللی مهندسی حمل و نقل و ترافیک6 اسفند 1392 · تهران