Abstract:

A leading-vehicle night-detection method was proposed based on millimeter-wave radar-vision, using the fusion of data from multi-sensors to investigate the intelligent warning system for avoidance vehicles collision at night with preceding vehicles. A world coordinate of the preceding vehicles was built for millimeter
wave radar target to form the region of interesting image after relationship transformation from the world coordinate to image pixels coordinate. Image processing method reduced interference from the outside environment. A general value of reliability was achieved to test vehicles in interest depending on Dempster-
Shafer Evidence Theory (D-S) which fused feature information. Several sections of video for vehicles driving on road were collected during experiment. The statistical data of frames of taillight identified were achieved and compared by subjective judgment. The results show that the method effectively eliminates the influence of illumination condition at night, accurately detect leading vehicles and determine their location.

Key words: vehicles active safety, avoidance collision warning, leading vehicle detection at night, millimeter wave radar, machine vision, data fusion, dynamic region of interest