Feature based simultaneous localization and semi-dense mapping with monocular camera

摘要

Recently, Simultaneous Localization And Mapping (SLAM) has been getting more and more popular on the applications of mobile robot and unmanned aerial vehicles. If combined with semi-dense mapping, monocular SLAM will have a good prospect for multi-applications such as visual navigation. In addition, robust tracking is a pivotal role in complex and volatile situation and also it determines the quality of whole SLAM system's performance and accuracy. Because feature based tracking method has better error-tolerance on variety of light intensity and dynamic scene, this paper using feature-based tracking method plus depth update and propagation's mechanism achieved a higher-quality tracking and semi-dense mapping in real time. Then the accuracy of tracking trajectory was measured and evaluated in TUM RGB-D benchmark. As a result, the new system can not only rebuild semi-dense 3D scene in real time but also has a higher accuracy.