High-performance visual odometry with two-stage local binocular BA and GPU

Abstract

Visual odometry becomes an important method to deal the localization work in intelligent vehicle and robotics. A high performance visual odometry needs to achieve two requirements: high accuracy and high frequency. So we propose a two-stage local binocular bundle adjustment algorithm doing the optimization and construct a parallel pipeline using GPU acceleration. Finally, our system can run at about 35~40 frames per second with the maximum RMS 3D localization error less than 1%.