Designing CMOS hardware processor for vehicle tracking

Hua Tang, Taek M Kwon, Yi Zheng, Hairong Chang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

It is well known that vehicle tracking processes are very computationally intensive. Traditionally, vehicle tracking algorithms have been implemented using software approaches. The goal of this paper is to investigate the feasibility of developing a hardware-based tracking system. We propose a tracking algorithm with vehicle motion detection based on block matching algorithm, which is well suited to customized hardware implementation. The proposed tracking algorithm is first simulated in MATLAB and the CMOS circuit design was simulated in Cadence. When tested on traffic images captured from an intersection, it is found that vehicle movements can be accurately identified in spite of some noisy motion. Also, the estimated computational time for the hardware based tracking system is much reduced compared to traditional software-based tracking system.

Original languageEnglish (US)
Title of host publication2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference Proceedings
Pages1328-1331
Number of pages4
DOIs
StatePublished - Dec 1 2007
Event2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference - Montreal, QC, Canada
Duration: Aug 5 2007Aug 8 2007

Publication series

NameMidwest Symposium on Circuits and Systems
ISSN (Print)1548-3746

Other

Other2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference
CountryCanada
CityMontreal, QC
Period8/5/078/8/07

Fingerprint Dive into the research topics of 'Designing CMOS hardware processor for vehicle tracking'. Together they form a unique fingerprint.

Cite this