Abstract—This paper presents two different types of visual activity analysis modules based on vehicle tracking. The highway monitoring module accurately classifies vehicles into eight different types and collects traffic flow statistics by leveraging tracking information. These statistics are continuously accumulated to maintain daily highway models that are used to categorize traffic flow in real time. The path modeling block is a more general analysis tool that learns the normal motions encountered in a scene in an unsupervised fashion. The spatiotemporal motion characteristics of these motion paths are encoded by a hidden Markov model. With the path definitions, abnormal trajectories are detected and future intent is predicted. These modules add realtime situational awareness to highway monitoring for high-level activity and behavior analysis. Index Terms—Anomaly detection, comparative flow analysis, highway efficiency, real-time tracking analysis, trajectory learning and prediction, vehicle type classification. I.

Abstract—This paper presents a survey of trajectory-based activity analysis for visual surveillance. It describes techniques that use trajectory data to define a general set of activities that are applicable to a wide range of scenes and environments. Events of interest are detected by building a generic topographical scene description from underlying motion structure as observed over time. The scene topology is automatically learned and is distinguished by points of interest and motion characterized by activity paths. The methods we review are intended for real-time surveillance through definition of a diverse set of events for further analysis triggering, including virtual fencing, speed profiling, behavior classification, anomaly detection, and object interaction. Index Terms—Event detection, motion analysis, situational awareness, statistical learning. Fig. 1. Relationship between analysis levels and required knowledge: highlevel activity analysis requires large amounts of domain knowledge while lowlevel analysis assumes very little. I.

Abstract—Society is rapidly accepting the use of video cameras in many new and varied locations, but effective methods to utilize and manage the massive resulting amounts of visual data are only slowly developing. This paper presents a framework for live video analysis in which the behaviors of surveillance subjects are described using a vocabulary learned from recurrent motion patterns, for real-time characterization and prediction of future activities, as well as the detection of abnormalities. The repetitive nature of object trajectories is utilized to automatically build activity models in a 3-stage hierarchical learning process. Interesting nodes are learned through Gaussian mixture modeling, connecting routes formed through trajectory clustering, and spatio-temporal dynamics of activities probabilistically encoded using hidden Markov models. Activity models are adapted to small temporal variations in an online fashion using maximum likelihood regression and new behaviors are discovered from a periodic re-training for long-term monitoring. Extensive evaluation on various datasets, typically missing from other work, demonstrates the efficacy and generality of the proposed framework for surveillance-based activity analysis. Index Terms—Trajectory clustering, real-time activity analysis, abnormality detection, trajectory learning, activity prediction 1

thesis, including any required final revisions, as accepted by my examiners. I understand that my thesis may be made electronically available to the public. There has been a growth in demand for advancing algorithms in surveillance applications concerning moving vehicles where analysis of traffic has a potential application to security, traffic management (congestion and accident detection), speed measurement, car counting and statistics, as well as turning movement at intersections. This research focuses on multiple-vehicle detection, recognition, and tracking in urban environments based on video sequences obtained from a single CCD camera mounted on a pole at urban highways and crossroads. The proposed system integrates several modules including segmentation, object detection, object recognition and classification, and tracking. Background segmentation, based on Gaussian Mixture models, is used to extract moving objects from images using the respective foreground object information such as location, size, and color distribution. To recognize vehicles, a 3D polyhedral car model described by a set

The efficient and safe movement of freight is one of the important goals of urban transportation systems and vital to not only the local economy, but nationally as well. Given the importance of the freight transportation system, opportunities to utilize state of the art Intelligent Transportation Systems (ITS) technologies are increasing to improve the operation of the existing infrastructure to promote the efficient and safe transportation of freight. Among these technologies, a Truck Signal Priority (TkSP) strategy gives priority to a traffic signal approach when trucks are detected. By using the rich data available through the use of video sensors, the use such a strategy can improve the efficiency and safety of freight movement by reducing truck travel time and the number of truck stops at the intersection. This paper presents a prototype TkSP system using video sensors to detect, identify and track trucks. A classification module takes the road users ' trajectories as input, and classifies them as either truck or non-truck. Using a mixture of Gaussians to model the background, the appearance and shape of road users in each frame is extracted. Using labeled shape data, a classifier is trained. A road user will be classified as a truck if its shape is classified as such in

� Topic Computer vision for urban road traffic managements � Bottleneck Human resources for observing hundreds of cameras