Authors - Kashyap Patel, Urvashi Chaudhari, Chirag Patel, Nirav Bhatt Abstract - Automatic traffic surveillance has a hard time finding and classifying vehicles that are trying to get in the way. To keep an eye on things in real time, you need to be able to tell the difference between cars, trucks, buses, and other types of vehicles. Traffic management systems need to be able to accurately identify vehicles as the number of cars on the road grows. This paper examines various machine learning (ML) and deep learning (DL) techniques employed to identify and categorize vehicles in images and videos. The authors emphasize the significance of algorithms, such as CNNs, YOLO, and AdaBoost, in enhancing detection accuracy and efficiency. This paper examines various published re-search studies to discern methodologies, datasets, and future research directions in vehicle detection and classification, offering insights into the existing techno-logical landscape and its prospective developments.
Open Zoom