GOLD: a parallel real-time stereo vision system for generic obstacle and lane detection

TLDR

The paper introduces GOLD, a stereo‑vision system for generic obstacle and lane detection on moving vehicles to enhance road safety. GOLD employs a full‑custom massively parallel hardware architecture that removes perspective distortion, uses the left image for lane marking detection via morphological filters, and processes remapped stereo images to detect free space, delivering results at 10 Hz to an on‑board monitor and control panel. In field tests on the MOB‑LAB vehicle over 3000 km at speeds up to 80 km/h, GOLD proved robust against shadows, illumination changes, varied road textures, and vehicle motion.

Abstract

This paper describes the generic obstacle and lane detection system (GOLD), a stereo vision-based hardware and software architecture to be used on moving vehicles to increment road safety. Based on a full-custom massively parallel hardware, it allows to detect both generic obstacles (without constraints on symmetry or shape) and the lane position in a structured environment (with painted lane markings) at a rate of 10 Hz. Thanks to a geometrical transform supported by a specific hardware module, the perspective effect is removed from both left and right stereo images; the left is used to detect lane markings with a series of morphological filters, while both remapped stereo images are used for the detection of free-space in front of the vehicle. The output of the processing is displayed on both an on-board monitor and a control-panel to give visual feedbacks to the driver. The system was tested on the mobile laboratory (MOB-LAB) experimental land vehicle, which was driven for more than 3000 km along extra-urban roads and freeways at speeds up to 80 km/h, and demonstrated its robustness with respect to shadows and changing illumination conditions, different road textures, and vehicle movement.