Abstract—Visual surveillance in dynamic scenes, especially for humans and vehicles, is currently one of the most active research topics in computer vision. It has a wide spectrum of promising applications, including access control in special areas, human identification at a distance, crowd flux statistics and congestion analysis, detection of anomalous behaviors, and interactive surveillance using multiple cameras, etc. In general, the processing framework of visual surveillance in dynamic scenes includes the following stages: modeling of environments, detection of motion, classification of moving objects, tracking, understanding and description of behaviors, human identification, and fusion of data from multiple cameras. We review recent developments and general strategies of all these stages. Finally, we analyze possible research directions, e.g., occlusion handling, a combination of twoand three-dimensional tracking, a combination of motion analysis and biometrics, anomaly detection and behavior prediction, content-based retrieval of surveillance videos, behavior understanding and natural language description, fusion of information from multiple sensors, and remote surveillance. Index Terms—Behavior understanding and description, fusion of data from multiple cameras, motion detection, personal identification, tracking, visual surveillance.

This paper presents an overview of the issues and algorithms involved in creating this semiautonomous, multicamera surveillance system

Visual analysis of human motion is currently one of the most active research topics in computer vision. This strong interest is driven by a wide spectrum of promising applications in many areas such as virtual reality, smart surveillance, perceptual interface, etc. Human motion analysis concerns the detection, tracking and recognition of people, and more generally, the understanding of human behaviors, from image sequences involving humans. This paper provides a comprehensive survey of research on computer vision based human motion analysis. The emphasis is on three major issues involved in a general human motion analysis system, namely human detection, tracking and activity understanding. Various methods for each issue are discussed in order to examine the state of the art. Finally, some research challenges and future directions are discussed.

Detecting regions of change in multiple images of the same scene taken at different times is of widespread interest due to a large number of applications in diverse disciplines, including remote sensing, surveillance, medical diagnosis and treatment, civil infrastructure, and underwater sensing. This paper presents a systematic survey of the common processing steps and core decision rules in modern change detection algorithms, including significance and hypothesis testing, predictive models, the shading model, and background modeling. We also discuss important preprocessing methods, approaches to enforcing the consistency of the change mask, and principles for evaluating and comparing the performance of change detection algorithms. It is hoped that our classification of algorithms into a relatively small number of categories will provide useful guidance to the algorithm designer.

We propose a distributed, real-time computing platform for tracking multiple interacting persons in motion. To combat the negative effects of occlusion and articulated motion we use a multi-view implementation, where each view is first independently processed on a dedicated processor. This monocular processing uses a predictor-corrector filter to weigh re-projections of 3-D position estimates, obtained by the central processor, against observations of measurable image motion. The corrected state vectors from each view provide input observations to a Bayesian belief network, in the central processor, with a dynamic, multidimensional topology that varies as a function of scene content and feature confidence. The Bayesian net fuses independent observations from multiple cameras by iteratively resolving independency relationships and confidence levels within the graph, thereby producing the most likely vector of 3-D state estimates given the available data. To maintain temporal continuity we follow the network with a layer of Kalman filtering that updates the 3-D state estimates. We demonstrate the efficacy of the proposed system using a multi-view sequence of several people in motion. Our experiments suggest that, when compared with data fusion based on averaging, the proposed technique yields a noticeable improvement in tracking accuracy.

In this paper we propose a new representation of videos with spatiotemporal blocks. After a given video is decomposed into the spatiotemporal blocks, a dimensionality reduction technique is applied to obtain a compact vector representation of each block gray level values. The block vectors provide a joint representation of texture and motion patterns in videos. Our results on PETS repository videos show that detection and tracking of moving objects is substantially improved if based on spatiotemporal blocks instead on pixels. Thus, we go away from the standard input of pixel values that are known to be noisy and the main cause of instability of video analysis algorithms. 1.

Abstract. The usefulness of networks of surveillance cameras is primarily limited by the demand placed on human supervisors to monitor many real time video feeds simultaneously. The goal of automated visual surveillance is to reduce the burden on operators by including software in a surveillance system that can analyse video content automatically. This paper reviews progress in the field and considers some of the major remaining problems in automated video surveillance. 1

In this paper, a multisensor data fusion system for object tracking is presented. It is able to track in real-time multiple targets in outdoor environments. The system can take advantage of the redundant information coming from different sensors monitoring the same scene. The measurements (positions of the targets) obtained from the available sources are fused together to obtain a more accurate estimate. Data fusion is performed considering sensor reliability at every time instant. A confidence measure has been employed to weight sensor data in the fusion process. Compared to single camera systems, the adopted approach has produced more accurate and continuous trajectories, reducing calibration and segmentation errors.

We present a novel framework for learning patterns of motion and sizes of objects in static camera surveillance. The proposed method provides a new higher-level layer to the traditional surveillance pipeline for anomalous event detection and scene model feedback. Pixel level probability density functions (pdfs) of appearance have been used for background modelling in the past, but modelling pixel level pdfs of object speed and size from the tracks is novel. Each pdf is modelled as a multivariate Gaussian Mixture Model (GMM) of the motion (destination location & transition time) and the size (width & height) parameters of the objects at that location. Output of the tracking module is used to perform unsupervised EM-based learning of every GMM. We have successfully used the proposed scene model to detect local as well as global anomalies in object tracks. We also show the use of this scene model to improve object detection through pixel-level parameter feedback of the minimum object size and background learning rate. Most object path modelling approaches first cluster the tracks into major paths in the scene, which can be a source of error. We avoid this by building local pdfs that capture a variety of tracks which are passing through them. Qualitative and quantitative analysis of actual surveillance videos proved the effectiveness of the proposed approach. 1.

Tracking multiple agents in a monocular visual surveillance system is often challenged by the phenomenon of occlusions. Agents entering the field of view can undergo two different forms of occlusions, either caused by crowding or due to obstructions by background objects at finite distances from the camera. The agents are primarily detected as foreground blobs and are characterized by their motion history and weighted color histograms. These features are further used for localizing them in subsequent frames through motion prediction assisted mean shift tracking. A number of Boolean predicates are evaluated based on the fractional overlaps between the localized regions and foreground blobs. We construct predicates describing a comprehensive set of possible surveillance event primitives including entry/exit, partial or complete occlusions by background objects, crowding, splitting of agents and algorithm failures resulting from track loss. Instantiation of these event primitives followed by selective feature updates enables us to develop an effective scheme for tracking multiple agents in relatively unconstrained environments. I.