Home People Research Publications Demos
         
News Jobs Prospective
Students 		About Internal

Distributed Crowd Analytics on a Dynamic and Open Video Database

The automated monitoring and surveillance of crowded scenes is a remarkable challenge for current image and video understanding technology. It has environmental application in areas such as security, natural disaster prevention, research in herd and flocking behavior, population monitoring, entertainment, urban architecture, and marketing. It has recently acquired strong societal significance, due to the possibility of terrorist attacks on events involving large concentrations of people, a problem for which there are currently no effective solutions.

This project 1) implements a platform for automated monitoring and surveillance of crowded scenes, 2) provides a common experimental environment in which to test crowd analytics continuously and in real-time, all while 3) overcoming common limiting constraints such as static databases applicable only to subsets of problems. This project paves a pathway for new and extended crowd analytic evaluation, including: visualizing distributed crowd dynamics across an expansive spatial area as well as temporally yielding trends over extended durations. Furthermore, this project elucidates new avenues of crowd research such as 1) crowd interpolation of unmonitored network pathways, 2) object and person tracking across fields of view, and 3) crowd analysis of areas with simultaneous multiple perspectives.

Acquisition: Module responsible for interfacing video surveillance system and computational system. The openness of our database is attributed to the real-time streams from our live system. The dynamics of the database are attributed to dynamic devices such as our PTZ cameras. [Overview]
Analysis:

Pedestrian Crowd Counting
Primary analytic used in project. We estimate the size of moving crowds in a privacy preserving manner, i.e. without people models or tracking. The system first segments the crowd by its motion, extracts simple features from each segment, and estimates the crowd count in each segment using a Gaussian process.
[project | demo]

Anomaly Detection
Candidate analytic. Anomaly detection in crowded scenes using a mixture of dynamic textures representation. [project]

Visualizations: Realtime visualizations and historic trends. [demos] NEW!
Related
Projects:

Understanding Video of Crowded Environments
This project lays the foundation for the technology that enables our automated system for monitoring and surveillance of crowded scenes, by modeling their video as a visual texture that deforms itself in stochastic but predictable ways, in response to certain events. In particular, this project aims to produce 1) a suite of generative probabilistic models for the video produced by various types of crowded scenes, and optimal algorithms for the estimation of their parameters, 2) a family of classifiers that build on these models to design detectors of important events, and 3) a collection of algorithms for crowd video stabilization, segmentation, and parsing. [project | demo]

Modeling video with Mixtures of Dynamic Textures
We introduce the mixture of dynamic textures, which models a collection of video as samples from a set of dynamic textures. We use the model for video clustering and motion segmentation. [project]

Related
Publications:		 Analysis of Crowded Scenes using Holistic Properties
A. B. Chan, M. Morrow, and N. Vasconcelos
In 11th IEEE Intl. Workshop on Performance Evaluation of Tracking and Surveillance (PETS 2009), Miami, June 2009. IEEE [pdf]

Contact: MulloyMorrow, Nuno Vasconcelos





© SVCL