Probabilistic Modeling of Scene Dynamics for Applications in Visual Surveillance

Authors:
Imran Saleemi;Khurram Shafique;Mubarak Shah
Affiliations:
University of Central Florida, Orlando;Object Video Inc., Reston;University of Central Florida, Orlando
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
2009

Citing 0
Cited 19

Time-Delayed Correlation Analysis for Multi-Camera Activity Understanding

International Journal of Computer Vision
A hybrid moving object detection method for aerial images

PCM'10 Proceedings of the 11th Pacific Rim conference on Advances in multimedia information processing: Part I
Why did the person cross the road (there)? scene understanding using probabilistic logic models and common sense reasoning

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part II
Abnormality detection using low-level co-occurring events

Pattern Recognition Letters
Anomalous video event detection using spatiotemporal context

Computer Vision and Image Understanding
Learning rare behaviours

ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part II
Prediction of collisions between vehicles using attainable region

Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication
Detecting anomalies in people's trajectories using spectral graph analysis

Computer Vision and Image Understanding
Trajectory Analysis and Semantic Region Modeling Using Nonparametric Hierarchical Bayesian Models

International Journal of Computer Vision
Deriving implicit indoor scene structure with path analysis

Proceedings of the 3rd ACM SIGSPATIAL International Workshop on Indoor Spatial Awareness
Building semantic scene models from unconstrained video

Computer Vision and Image Understanding
Video Behaviour Mining Using a Dynamic Topic Model

International Journal of Computer Vision
Abnormal event detection via multi-instance dictionary learning

IDEAL'12 Proceedings of the 13th international conference on Intelligent Data Engineering and Automated Learning
Towards unsupervised semantic segmentation of street scenes from motion cues

Proceedings of the 27th Conference on Image and Vision Computing New Zealand
A fully online and unsupervised system for large and high-density area surveillance: Tracking, semantic scene learning and abnormality detection

ACM Transactions on Intelligent Systems and Technology (TIST) - Special section on agent communication, trust in multiagent systems, intelligent tutoring and coaching systems
M4L: Maximum margin Multi-instance Multi-cluster Learning for scene modeling

Pattern Recognition
CrowdWatch: enabling in-network crowd-sourcing

Proceedings of the second ACM SIGCOMM workshop on Mobile cloud computing
Summarizing high-level scene behavior

Machine Vision and Applications
An Improved Hierarchical Dirichlet Process-Hidden Markov Model and Its Application to Trajectory Modeling and Retrieval

International Journal of Computer Vision

Quantified Score

Hi-index	0.14

Visualization

Abstract

We propose a novel method to model and learn the scene activity, observed by a static camera. The proposed model is very general and can be applied for solution of a variety of problems. The motion patterns of objects in the scene are modeled in the form of a multivariate nonparametric probability density function of spatiotemporal variables (object locations and transition times between them). Kernel Density Estimation is used to learn this model in a completely unsupervised fashion. Learning is accomplished by observing the trajectories of objects by a static camera over extended periods of time. It encodes the probabilistic nature of the behavior of moving objects in the scene and is useful for activity analysis applications, such as persistent tracking and anomalous motion detection. In addition, the model also captures salient scene features, such as the areas of occlusion and most likely paths. Once the model is learned, we use a unified Markov Chain Monte Carlo (MCMC)-based framework for generating the most likely paths in the scene, improving foreground detection, persistent labeling of objects during tracking, and deciding whether a given trajectory represents an anomaly to the observed motion patterns. Experiments with real-world videos are reported which validate the proposed approach.