A successful Video-based Simultaneous Localization And Mapping (VSLAM) implementation usually requires a vast amount of feature points to be detected in the environment, which makes the VSLAM problem s computationally demanding operation in mobile robot navigation. This paper presents a VSLAM implementation that is based on a sparse distribution of high-informative artificial landmark features. Additionally, our approach combines the video system analysis results and the inertial measurement unit (IMU) measurements that define the orientation of the video camera. Successful implementation of the VSLAM system can enable autonomous quadrocopter navigation in the structured environment without the presence of the additional external positioning systems.
展开▼
