An Automatic Machine Learning and Particle Filtering Based Approach to Real Time Human Tracking in Videos

Object Tracking is an important task in video processing because of its various applications like visual surveillance, human activity monitoring and recognition, traffic flow management etc. Multiple object detection and tracking in outdoor environment is a challenging task because of the problems raised by poor lighting conditions, occlusion and clutter. This paper proposes a noble technique for detecting and tracking the multiple humans in a video. A classifier is trained for object detection using haarlike features from the training image set. The human objects are detected with the help of this trained detector and are tracked with the help of a particle filter. The experimental results show that the propose technique can detect and track the multiple humans in a video adequately fast in the presence poor lighting conditions, clutter and partial occlusion and the technique can handle varying number of human objects in the video at various points of time.