Real-time model based geometric reasoning for vision-guided navigation

This paper describes results of a real-time model based geometric reasoning module for autonomous vision-guided road following. Vision-guided road following requires extracting road boundaries from images in real time to guide the navigation of autonomous vehicles on a roadway. The detected road region boundary is error prone due to imperfect image segmentation. To achieve robust system performance, a geometric reasoning module that uses spatial and temporal constraints to perform model based reasoning is used. Local geometric supports for each road edge segment are collected and recorded and a global consistency checking is performed to obtain a consistent interpretation of the raw data. Cases involving incomplete sensor data, curved roads where only one side of the road is visible, and incorrect segmentation due to shadows, road patches, or unusual road conditions, can usually be detected and corrected. The image segmentation results are what the vision system “sees”. The geometric reasoning results are what the vision system “perceives”. This reasoning module has been integrated into a road following system which is capable of supporting autonomous robot road following at 24 km/hr.