TY - JOUR T1 - A Constrained Probabilistic Petri Net Framework for Human Activity Detection in Video JF - Multimedia, IEEE Transactions on Y1 - 2008 A1 - Albanese, M. A1 - Chellapa, Rama A1 - Moscato, V. A1 - Picariello, A. A1 - V.S. Subrahmanian A1 - Turaga,P. A1 - Udrea,O. KW - activity KW - dataset;automated KW - detection;human KW - interactions;security KW - net;human KW - nets;image KW - Petri KW - probabilistic KW - processing;multiagent KW - processing;video KW - representation;low-level KW - representation;video KW - signal KW - Surveillance KW - surveillance; KW - systems;constrained KW - systems;surveillance KW - tarmac KW - TSA KW - videos;Petri AB - Recognition of human activities in restricted settings such as airports, parking lots and banks is of significant interest in security and automated surveillance systems. In such settings, data is usually in the form of surveillance videos with wide variation in quality and granularity. Interpretation and identification of human activities requires an activity model that a) is rich enough to handle complex multi-agent interactions, b) is robust to uncertainty in low-level processing and c) can handle ambiguities in the unfolding of activities. We present a computational framework for human activity representation based on Petri nets. We propose an extension-Probabilistic Petri Nets (PPN)-and show how this model is well suited to address each of the above requirements in a wide variety of settings. We then focus on answering two types of questions: (i) what are the minimal sub-videos in which a given activity is identified with a probability above a certain threshold and (ii) for a given video, which activity from a given set occurred with the highest probability? We provide the PPN-MPS algorithm for the first problem, as well as two different algorithms (naive PPN-MPA and PPN-MPA) to solve the second. Our experimental results on a dataset consisting of bank surveillance videos and an unconstrained TSA tarmac surveillance dataset show that our algorithms are both fast and provide high quality results. VL - 10 SN - 1520-9210 CP - 6 M3 - 10.1109/TMM.2008.2001369 ER - TY - CONF T1 - Hierarchical Part-Template Matching for Human Detection and Segmentation T2 - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on Y1 - 2007 A1 - Zhe Lin A1 - Davis, Larry S. A1 - David Doermann A1 - DeMenthon,D. KW - analysis;global KW - approach;background KW - articulations;video KW - Bayesian KW - detection;human KW - detectors;hierarchical KW - detectors;partial KW - framework;Bayesian KW - human KW - likelihood KW - MAP KW - matching;human KW - matching;image KW - methods;image KW - occlusion KW - occlusions;shape KW - part-based KW - part-template KW - re-evaluation;global KW - segmentation;image KW - segmentation;local KW - sequences; KW - sequences;Bayes KW - SHAPE KW - subtraction;fine KW - template-based AB - Local part-based human detectors are capable of handling partial occlusions efficiently and modeling shape articulations flexibly, while global shape template-based human detectors are capable of detecting and segmenting human shapes simultaneously. We describe a Bayesian approach to human detection and segmentation combining local part-based and global template-based schemes. The approach relies on the key ideas of matching a part-template tree to images hierarchically to generate a reliable set of detection hypotheses and optimizing it under a Bayesian MAP framework through global likelihood re-evaluation and fine occlusion analysis. In addition to detection, our approach is able to obtain human shapes and poses simultaneously. We applied the approach to human detection and segmentation in crowded scenes with and without background subtraction. Experimental results show that our approach achieves good performance on images and video sequences with severe occlusion. JA - Computer Vision, 2007. ICCV 2007. IEEE 11th International Conference on M3 - 10.1109/ICCV.2007.4408975 ER -