JVLDLoc: a Joint Optimization of Visual-LiDAR Constraints and Direction Priors for Localization in Driving Scenario
This addresses localization accuracy for autonomous driving applications, but it is incremental as it builds on existing SLAM methods with added constraints.
The paper tackles drift in multi-sensor localization for autonomous driving by fusing map priors and vanishing points into a visual-LiDAR SLAM system, achieving lower localization error on datasets like KITTI and Oxford Radar Robotcar.
The ability for a moving agent to localize itself in environment is the basic demand for emerging applications, such as autonomous driving, etc. Many existing methods based on multiple sensors still suffer from drift. We propose a scheme that fuses map prior and vanishing points from images, which can establish an energy term that is only constrained on rotation, called the direction projection error. Then we embed these direction priors into a visual-LiDAR SLAM system that integrates camera and LiDAR measurements in a tightly-coupled way at backend. Specifically, our method generates visual reprojection error and point to Implicit Moving Least Square(IMLS) surface of scan constraints, and solves them jointly along with direction projection error at global optimization. Experiments on KITTI, KITTI-360 and Oxford Radar Robotcar show that we achieve lower localization error or Absolute Pose Error (APE) than prior map, which validates our method is effective.