Monocular Trail Detection and Tracking Aided by Visual SLAM for Small Unmanned Aerial Vehicles

TL;DR

This paper introduces a monocular vision system for small UAVs that integrates Visual SLAM data to improve trail detection and tracking in forest environments, demonstrating high success in challenging conditions.

Contribution

It extends existing monocular trail detection methods by incorporating volumetric data from Visual SLAM, enhancing robustness in complex terrains.

Findings

Achieved a 97.8% success rate in trail detection.

Demonstrated improved robustness over previous methods.

Validated with 12 real-world UAV video recordings.

Abstract

This paper presents a monocular vision system susceptible of being installed in unmanned small and medium-sized aerial vehicles built to perform missions in forest environments (e.g., search and rescue). The proposed system extends a previous monocular-based technique for trail detection and tracking so as to take into account volumetric data acquired from a Visual SLAM algorithm and, as a result, to increase its sturdiness upon challenging trails. The experimental results, obtained via a set of 12 videos recorded with a camera installed in a tele-operated, unmanned small-sized aerial vehicle, show the ability of the proposed system to overcome some of the difficulties of the original detector, attaining a success rate of $97.8\,\%$.