Object Detection in Traffic Videos

In recent times, there has been an increase in demand in the automobile industry, particularly in driverless cars. The vehicles should automatically detect the objects and make decisions very fast, roughly in a span of milliseconds, without human intervention. The task of detecting objects contains several operations like object classification of live or non-live objects, detection, and position estimation from the source. This work focuses on detecting objects in traffic videos. Using YOLO5 model, predicted the locations, size, and confidence scores of potential places where an object can be in real time videos.