Fusion of a panoramic camera and 2D laser scanner data for constrained bundle adjustment in GPS-denied environments
作者:
Highlights:
• Accurate scale is estimated with laser data and features extracted from camera.
• Many more loop closures are detected by sensor than that of camera-only methods.
• Scale and loop closure geometric constraints are enforced on Constrained Bundle Adjustment, which produces a robust pose estimate.
• Experiments show that the proposed method is practicable and more accurate than vision-only methods.
摘要
•Accurate scale is estimated with laser data and features extracted from camera.•Many more loop closures are detected by sensor than that of camera-only methods.•Scale and loop closure geometric constraints are enforced on Constrained Bundle Adjustment, which produces a robust pose estimate.•Experiments show that the proposed method is practicable and more accurate than vision-only methods.
论文关键词:Panoramic camera,Laser,Sensor fusion,Constrained bundle adjustment
论文评审过程:Received 15 November 2013, Revised 24 April 2015, Accepted 10 June 2015, Available online 18 June 2015, Version of Record 27 June 2015.
论文官网地址:https://doi.org/10.1016/j.imavis.2015.06.002