Moving vehicle discrimination using Hough transformation

Abstract

In this paper, a vehicle detection scheme is suggested using Hough transformation where some moving vehicles are discriminated from significant clutter by using linear trajectory detection in the Hough space. In general, the received range profile for a wideband radar pulse includes many echoes from various obstacles such as guardrail. Observing the profiles with high PRF during a short duration, each echoes trajectory can be estimated employing Hough transform. For example, the trajectory is regarded as linear when the speed of echo is constant and the moving vehicles are spatially discriminated with clutter. The Doppler can also be estimated from the time-range coordinate. As a result, some significant clutters would be eliminated in the Hough space and the vehicles are expected to be detected and tracked with high range and Doppler resolution. The field measurement at 24GHz was conducted for moving vehicles and the usefulness is discussed for various scenarios.