Vehicle Identification and Counting (VIC) Using Machine Learning Algorithm- ORB

Counting vehicles is an essential function for smart city applications, traffic management, and surveillance. There are several applications for the technology used to detect vehicles in recorded video. In this research work, the Oriented FAST and Rotated BRIEF (ORB) method is used to develop a rudimentary model for vehicle detection and counting. The video clip used as input, numerous frames are retrieved, and shadow and backdrop are approximated. To identify every moving object from the estimated backdrop, the subsequent frame is subtracted. Vehicles are identified, categorized, and counted for traffic estimation based on moving objects, utilizing object detection methods and OpenCV. When used with OpenCV, the ORB algorithm offers a potential method for identifying and accumulation the number of vehicles in the video stream. The ORB method is well-suited for tracking objects in dynamic settings since it is especially supportive for feature matching.