A low-cost visual navigation and mapping system for Unmanned Aerial Vehicle using LSD-SLAM algorithm

The growing need of Disaster management requires some specialties in sophisticated technologies. Navigating an Unmanned Aerial Vehicle (UAV) in an unknown indoor environment is a complex task. This work tries to implement an autonomous system, which navigates the Low-cost Quadcopter with an on-board computer, sensors and Ground station which carries out a spatially consistent probabilistic model for its navigation and 3D mapping. The Simultaneous Localization and Mapping (SLAM) is also implemented in this work in an efficient way such that, it utilizes much fewer resources than other algorithms in order to operate on lower Footprint processors. It also gives a comprehensive analysis of performance-cost tradeoffs for the improved system.