Development of a New Tracking System based on CMOS Vision Processor Hardware: Phase I - FY08 NATSRL
Principal Investigator:
Hua Tang, Assistant Professor, UMD-Electrical & Computer Eng
Project Summary:
This project is developing a hardware-based vehicle tracking system, retaining key elements of video-based tracking system design and using customized hardware whenever possible to shorten execution time, ultimately enabling real-time tracking at a high frame rate. Vehicle tracking processes on roads are computationally intensive. In the past, the different algorithms employed in vehicle tracking have been implemented using various software-based approaches. While software approaches have the advantage of flexibility in implementation and future modifications, the long computational time of these approaches often prevents real-time vehicle tracking from high-resolution spatial or temporal data. The goal of this project is to build a tracking system with a new algorithm based on vehicle motion detection, which is implemented in hardware whenever possible so that the computation time for tracking is minimized. The tracking system consists of two major components: a hardware processor for vehicle motion detection, and a tracking algorithm based on motion estimation. Developing this hardware-based tracking system requires three steps: first, validation of the tracking algorithm using realistic video inputs; second, implementing the algorithm in hardware; third, construction and testing. To date, tracking results have been largely validated and technical issues identified. Sensitivity to camera jitter requires improvements to the algorithm to make it more robust. The design of custom hardwear is currently underway. Testing will be carried out in the next phase of the project.
Sponsors:
- ITS Institute (RITA)
Project Details:
- Start date: 06/2007
- Project Status: Completed
- Research Area: Transportation Safety and Traffic Flow