Monocular visual SLAM for tactical situational awareness

Abstract

Tactical situational awareness for military applications should be based on infrastructure-free systems and should be able to form knowledge of the previously unknown environment. Simultaneous Localization and Mapping (SLAM) is a key technology for providing an accurate and reliable infrastructure-free solution for indoor situational awareness. However, indoor environments and the requirements , especially the size and weight limits of the system, make the implementation of SLAM using existing algorithms challenging. In particular, we aim to implement SLAM using a monocular camera, due to size limitations, whereas most existing algorithms use stereo images. The two major obstacles to be overcome are the unknown scale of translation observed using a monocular camera and the shortage of features indoors, complicating visual perception. Herein, a Kalman filter based SLAM solution is discussed, utilizing a concept called visual odometry that provides absolute translation information with a reduced number of features. The results show that our solution is feasible for performing SLAM indoors using a monocular camera.