A Real-Time Monocular Visual SLAM Based on the Bundle Adjustment with Adaptive Robust Kernel

The key constituent of simultaneous localization and mapping (SLAM) is the joint optimization of sensor trajectory estimation and 3D map construction. The multivariable optimization process in SLAM is mainly carried out through bundle adjustment (BA). However, the method of handling outliers in actual data directly affects the accuracy of BA optimization and further affects the tracking performance of the system. In addition, in monocular initialization process, when the feature points are coplanar or have low parallax, their fundamental matrix will degrade and greatly affects the initial pose estimation results. To further surmount the above challenges, this paper presents a real time monocular visual SLAM optimization based on BA with adaptive robust kernel (ARK-SLAM): 1) a model selection mechanism with geometric robust information content is designed to improve the robustness of monocular initialization; 2) an adaptive robust kernel based BA is proposed to reduce the interference of outliers and improve the accuracy of optimal pose estimation; 3) a loop closure candidate verification scheme based on adaptive robust kernel is introduced to jointly minimize the geometric error term and the relative pose constraints. The position tracking performance of developed ARK-SLAM method is verified using TUM RGB-D benchmark dataset and KITTI dataset, and experimental results illustrate the favorable performances of ARK-SLAM by comparing with ORB-SLAM, ORB-SLAM3, LSD-SLAM and PTAM.