TPAMI_scene_dynamics - This article has been accepted for...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
1 Probabilistic Modeling of Scene Dynamics for Applications in Visual Surveillance Imran Saleemi, Khurram ShaFque, and Mubarak Shah 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 non-parametric probability density function of spatio-temporal 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 uniFed Markov Chain Monte-Carlo (MCMC) based framework for generating the most likely paths in the scene, improving foreground detection, persistent labelling 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. Index Terms —Vision and Scene Understanding, Machine Learning, Tracking, Markov Processes, Nonparametric statistics, Kernel Density Estimation, Metropolis Hastings, Markov Chain Monte Carlo. 1 I NTRODUCTION 1.1 Problem Description R ECENTLY, there is a major effort underway in the vi- sion community to develop fully automated surveil- lance and monitoring systems [1], [2]. Such systems have the advantage of providing continuous 24 hour active warning capabilities and are especially useful in the ar- eas of law enforcement, national defence, border control and airport security. The current systems are efFcient and robust in their handling of common issues, such as illumination changes, shadows, short-term occlusions, weather conditions, and noise in the imaging process [3]. However, most of the current systems have short or no memory in terms of the observables in the scene. Due to this memory-less behavior, these systems lack the capability of learning the environment parameters and intelligent reasoning based on these parameters. Such learning, prior modeling, and reasoning is an important characteristic of all cognitive systems that increases the adaptability and thus the practicality of such systems. A number of studies have provided strong psychophysical evidence of the importance of prior knowledge and context for scene understanding in humans, such as, handling long term occlusions, detection of anomalous behavior, and even improving the existing low-level vision tasks of object detection and tracking [4], [5].
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Image of page 2
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 06/13/2011 for the course CAP 6412 taught by Professor Staff during the Spring '08 term at University of Central Florida.

Page1 / 14

TPAMI_scene_dynamics - This article has been accepted for...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online