Dual-SLAM demo on KITTI00

Описание: Dual-SLAM: A framework for robust single camera navigation
Abstract—SLAM (Simultaneous Localization And Mapping) seeks to provide a moving agent with real-time self localization. To achieve real-time speed, SLAM incrementally propagates position estimates. This makes SLAM fast but also makes it vulnerable to local pose estimation failures. As local pose estimation is ill-conditioned, local pose estimation failures happen regularly, making the overall SLAM system brittle. This paper attempts to correct this problem. We observe that while local pose estimation is ill-conditioned, pose estimation over longer sequences is well-conditioned. Thus, local pose estimation errors eventually manifest themselves as mapping inconsistency. When this occurs, we save the current map and activate two new SLAM threads. One processes incoming frames to create a new map and the other, called recovery thread, backtracks to link the new and old maps together. This creates a Dual-SLAM framework that is robust to local pose estimation failures while still maintaining real-time performance. Evaluation on benchmark datasets show that Dual-SLAM reduces failures by a dramatic 88%.