PROJECT TITLE :

Robust visual odometry estimation of road vehicle from dominant surfaces for large-scale mapping

ABSTRACT:

Each urban setting contains a rich set of dominant surfaces that can provide a solid foundation for visual odometry estimation. During this work visual odometry is robustly estimated by computing the motion of camera mounted on a vehicle. The proposed technique initial identifies a planar region and dynamically estimates the plane parameters. The candidate region and estimated plane parameters are then tracked in the subsequent images and an incremental update of the visual odometry is obtained. The proposed technique is evaluated on a navigation dataset of stereo images taken by a automotive mounted camera that's driven in a very massive urban setting. The consistency and resilience of the tactic has also been evaluated on an enclosed robot dataset. The results counsel that the proposed visual odometry estimation will robustly recover the motion by tracking a dominant planar surface in the Manhattan surroundings. Additionally to motion estimation resolution a set of strategies are discussed for mitigating the problematic factors arising from the unpredictable nature of the atmosphere. The analyses of the results along with dynamic environmental strategies indicate a strong potential of the tactic for being half of an autonomous or semi-autonomous system.