Visible to the public Human Detection and Tracking for Video Surveillance: A Cognitive Science Approach

TitleHuman Detection and Tracking for Video Surveillance: A Cognitive Science Approach
Publication TypeConference Paper
Year of Publication2017
AuthorsGajjar, V., Khandhediya, Y., Gurnani, A.
Conference Name2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
KeywordsClustering algorithms, cognitive science approach, Computational modeling, Computer vision, computer vision algorithms, deep multilevel network, feature extraction, histograms of oriented gradients, HOG feature vectors, Human Behavior, human being detection, human detection, human resources, human tracking, image classification, k-means algorith, object detection, positively detected windows, Prediction algorithms, pubcrawl, Resiliency, saliency prediction model, Scalability, Support vector machines, video sequences, video surveillance, visual saliency, visualization

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.

Citation Keygajjar_human_2017