Mobile Robot Ego Motion Estimation using RANSAC-based Ceiling Vision
Visual odometry is a commonly used technique for recovering motion and location of the robot. In this paper, we present a robust visual odometry estimation approach based on ceiling view from 3D camera (Kinect). We extracted Speedup Robust Features (SURF) from the monocular image frames retrieved from the camera. SURF features from two consecutive frames are matched by .nding the nearest neighbor using Kdtree. 3D information of the SURF features are retrieved using the camera抯 depth map. The 3D af.ne transformation model is estimated between these two frames based on Random Sample Consensus (RANSAC) method. All inliers are then used to reestimate the relative transformation between two frames by Singular Value Decomposition (SVD). Given this, the global robot position and orientation can be calculated. Experimental results demonstrate the performance of the proposed algorithm in real environments.
Visual Odometry Ceiling vision RANSAC SURF
Han Wang Wei Mou Minh Hiep Ly M.W.S. Lau Gerald Seet Danwei Wang
School of Electrical & Electronic EngineeringNanyang Technological University, Singapore School of Electrical & Electronic Engineering Nanyang Technological University, Singapore
国际会议
The 24th Chinese Control and Decision Conference (第24届中国控制与决策学术年会 2012 CCDC)
太原
英文
1951-1955
2012-05-23（万方平台首次上网日期，不代表论文的发表时间）