A Review of Computer Vision Techniques for the Analysis of Urban Traffic

Abstract

Automatic video analysis from urban surveillance cameras is a fast-emerging field based on computer vision techniques. We present here a comprehensive review of the state-of-the-art computer vision for traffic video with a critical analysis and an outlook to future research directions. This field is of increasing relevance for intelligent transport systems (ITSs). The decreasing hardware cost and, therefore, the increasing deployment of cameras have opened a wide application field for video analytics. Several monitoring objectives such as congestion, traffic rule violation, and vehicle interaction can be targeted using cameras that were typically originally installed for human operators. Systems for the detection and classification of vehicles on highways have successfully been using classical visual surveillance techniques such as background estimation and motion tracking for some time. The urban domain is more challenging with respect to traffic density, lower camera angles that lead to a high degree of occlusion, and the variety of road users. Methods from object categorization and 3-D modeling have inspired more advanced techniques to tackle these challenges. There is no commonly used data set or benchmark challenge, which makes the direct comparison of the proposed algorithms difficult. In addition, evaluation under challenging weather conditions (e.g., rain, fog, and darkness) would be desirable but is rarely performed. Future work should be directed toward robust combined detectors and classifiers for all road users, with a focus on realistic conditions during evaluation.

Camera re-calibration after zooming based on sets of conics

“…In many computer vision applications, including zoom lens calibration [11,16,17,21,24], surveillance [30] or traffic inspection [31], a set of cameras observes a man made environments and requires frequent recalibration. Under the hypothesis of fixed camera position and orientation, the method presented here uses a set of degenerate conics (i.e.…”

Large-scale surveillance system: detection and tracking of suspicious motion patterns in crowded traffic scenes

“…However, the literature comprises a large variety of well-established algorithms. In [5,6,7], authors provided an interesting summary of literature surveys and developments related to visual surveillance systems, including motion detection, classification of moving objects, and tracking.…”

A comparison of two Monte Carlo algorithms for 3D vehicle trajectory reconstruction in roundabouts

“…Especially in the vehicle tracking scenarios this approach represents a widespread method; indeed in the comprehensive review of vehicular trackers [17] most of the analyzed systems estimate the 3D position and usually by means of a 3D model. To simplify the tracking task, all studies in 3D tracking literature assume that the camera calibration is known, see [18]; then, they usually assume the Ground Plane Constraint, i.e., a vehicle always lies on the road plane, and tracking is executed on this plane in order to diminish the vehicle degrees of freedom to be estimated from 6 to 3.…”