Human Detection and Tracking for Video Surveillance A Cognitive Science Approach

TL;DR

This paper presents a novel computer vision approach combining HOG, visual saliency, and deep saliency prediction to detect and track humans in video surveillance, achieving high precision and fast processing speeds.

Contribution

The paper introduces a new method integrating HOG features, visual saliency, and deep saliency models for human detection and tracking in videos, with improved accuracy and speed.

Findings

Detection precision of 83.11%

Recall rate of 41.27%

Processing speed 76.866 times faster than traditional classification

Abstract

With crimes on the rise all around the world, video surveillance is becoming more important day by day. Due to the lack of human resources to monitor this increasing number of cameras manually new computer vision algorithms to perform lower and higher level tasks are being developed. We have developed a new method incorporating the most acclaimed Histograms of Oriented Gradients the theory of Visual Saliency and the saliency prediction model Deep Multi Level Network to detect human beings in video sequences. Furthermore we implemented the k Means algorithm to cluster the HOG feature vectors of the positively detected windows and determined the path followed by a person in the video. We achieved a detection precision of 83.11% and a recall of 41.27%. We obtained these results 76.866 times faster than classification on normal images.