Flexible Trinocular: Non-rigid Multi-Camera-IMU Dense Reconstruction for UAV Navigation and Mapping
This addresses the challenge of dense reconstruction for UAV navigation and mapping, representing an incremental improvement by integrating a probabilistic wing model into an existing EKF formulation.
The paper tackles the problem of estimating camera poses for a non-rigid trinocular baseline on a fast-moving UAV to enable long-range depth estimation, resulting in a computationally efficient and robust visual-inertial framework validated through extensive real-world experiments.
In this paper, we propose a visual-inertial framework able to efficiently estimate the camera poses of a non-rigid trinocular baseline for long-range depth estimation on-board a fast moving aerial platform. The estimation of the time-varying baseline is based on relative inertial measurements, a photometric relative pose optimizer, and a probabilistic wing model fused in an efficient Extended Kalman Filter (EKF) formulation. The estimated depth measurements can be integrated into a geo-referenced global map to render a reconstruction of the environment useful for local replanning algorithms. Based on extensive real-world experiments we describe the challenges and solutions for obtaining the probabilistic wing model, reliable relative inertial measurements, and vision-based relative pose updates and demonstrate the computational efficiency and robustness of the overall system under challenging conditions.