CVSep 22, 2020

OpenREALM: Real-time Mapping for Unmanned Aerial Vehicles

arXiv:2009.10492v1Has Code
Originality Synthesis-oriented
AI Analysis

It addresses the need for up-to-date surface information in UAV applications, but appears incremental as it builds on existing mapping techniques with added real-time features.

This paper tackles real-time mapping for UAVs by developing OpenREALM, a framework that processes camera images to generate georeferenced maps, including 2D mosaics and 3D surface reconstructions, with live viewing capabilities for operators.

This paper presents OpenREALM, a real-time mapping framework for Unmanned Aerial Vehicles (UAVs). A camera attached to the onboard computer of a moving UAV is utilized to acquire high resolution image mosaics of a targeted area of interest. Different modes of operation allow OpenREALM to perform simple stitching assuming an approximate plane ground, or to fully recover complex 3D surface information to extract both elevation maps and geometrically corrected orthophotos. Additionally, the global position of the UAV is used to georeference the data. In all modes incremental progress of the resulting map can be viewed live by an operator on the ground. Obtained, up-to-date surface information will be a push forward to a variety of UAV applications. For the benefit of the community, source code is public at https://github.com/laxnpander/OpenREALM.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes