University of Minnesota Center for Transportation Studies
It is well known that vehicle tracking processes are very computationally intensive. Traditionally, vehicle tracking algorithms have been implemented using software approaches. The software approaches have a large computational delay, which causes low frame rate vehicle tracking. However, real-time vehicle tracking is highly desirable to improve not only tracking accuracy but also response time, in some ITS (Intelligent Transportation System) applications such as security monitoring and hazard warning. For this purpose, this project proposes a hardware based vehicle tracking system for real-time high frame rate tracking. The proposed tracking algorithm is based on motion estimation by full-search block matching algorithm. Motion estimation is implemented in a hardware processor, which could significantly reduce the computational delay compared to traditional software approaches. In this project, the hardware processor is first designed and verified using Cadence software in CMOS (Complementary Metal Oxide Semiconductor) IBM 0.13μm technology, and then mapped to the Xilinx Spartan-3A DSP Development Board for quick implementation. Test results have shown the hardware processor functions correctly with sequences of traffic images. We also design the algorithms to post-process the motion vectors output from the hardware processor to complete the overall vehicle tracking process.
Development of a New Tracking System based on CMOS Vision Processor Hardware: Phase I.
University of Minnesota Center for Transportation Studies.
Retrieved from the University of Minnesota Digital Conservancy,
Content distributed via the University of Minnesota's Digital Conservancy may be subject to additional license and use restrictions applied by the depositor.