Automated Traffic Surveillance

Intelligent transportation systems (ITS) have attracted considerable research attention in areas such as vehicle detection, recognition, and counting, and traffic parameter estimation. In light of the anticipated availability of low-cost hardware, as well as continuing progress in algorithmic research, computer vision has become a promising base technology for traffic sensing systems. Since vision sensors provide more information than the conventional sensors widely used in ITS, attention is now being focused on vision-based traffic surveillance systems.

This project aims to develop real-time traffic surveillance system for the detection, recognition, and tracking of multiple vehicles in the traffic videos. Following features can also be made s the part of this framework; Traffic Signal Light optimization using vehicle flow statistics, Identification of Speed Violation, Vehicle density estimation, Occlusive Vehicle Detection/recognition, Incident detection.


  • Large-scale automated proactive road safety analysis using video data (link)
  • Multiple Sensor Fusion and Classification for Moving Object Detection and Tracking (link)
  • Looking at Vehicles on the Road: A Survey of Vision-Based Vehicle Detection, Tracking, and Behavior Analysis (link)
  • A Review of Computer Vision Techniques for the Analysis of Urban Traffic (link)

Posted in Computer Vision, Projects.