A Monocular Ground Plane Estimation System

This paper describes the design of a system for estimating the pose of a camera mounted on a vehicle which moves over a flat floor. The system has been designed to work in conjunction with an obstacle avoidance scheme. Measurements are derived from a sequence of images captured by a single camera rigidly mounted on the vehicle and looking at the floor, and combined with measurements of the vehicle position in an extended Kalman filter (EKF). The filter is tested using simulation data.

[1]  Jan-Olof Eklundh,et al.  Object detection using model based prediction and motion parallax , 1990, ECCV.

[2]  David W. Murray,et al.  Experiments in the machine interpretation of visual motion , 1990 .

[3]  A.H. Haddad,et al.  Applied optimal estimation , 1976, Proceedings of the IEEE.

[4]  Giulio Sandini,et al.  A stereo vision system for real time obstacle avoidance in unknown environment , 1990, EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications.

[5]  Giulio Sandini,et al.  Uncertainty Analysis In Visual Motion And Depth Estimation From Active Egomotion , 1989, Defense, Security, and Sensing.