We study the problem of visually monitoring a set of points on a 2.5D terrain using an unmanned aerial vehicle (UAV) with a downward-facing camera. The goal is to find a tour of minimum length for the UAV offline to visually inspect all points of interest. Varying terrain and limited field of view of the camera restrict the visibility of the UAV and can create obstacles in the flight path, making the problem challenging. The problem is NP-hard and generalizes the traveling salesperson problem (TSP). We present several algorithms to solve this problem. Our main theoretical contribution is a constant-factor approximation algorithm (assuming fixed parameters for the terrain). We also present a practical algorithm that uses the solution to a generalized TSP (GTSP) subinstance. We benchmark the GTSP-based algorithm using a branch-and-cut integer linear programming formulation and find that the proposed algorithm scales to much larger instances and is computationally fast. We also show proof-of-concept using field deployment of a UAV to visually monitor points of interest in the environment.
Visual Monitoring of Points of Interest on a 2.5D Terrain Using a UAV With Limited Field-of-View Constraint
IEEE Transactions on Aerospace and Electronic Systems ; 57 , 6 ; 3661-3672
2021-12-01
2757084 byte
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Visual-servoed Parking with Limited View Angle
Springer Verlag | 2003
|Nonlinear Visual Servoing Control for VTOL UAVs with Field of View Constraint
Springer Verlag | 2015
|Online Contents | 1999
British Library Online Contents | 2011
|