Exploiting AirSim as a Cross-Dataset Benchmark for Safe UAV Landing and Monocular Depth Estimation Models
Authors:
Date: 26.10.2022
Abstract
As there is a lack of publicly available datasets with depth and surface normal information from a drone’s view, in this paper, we introduce the synthetic and photorealistic AirSimNC dataset. This dataset is used as a benchmark to test the zero-shot cross-dataset performance of monocular depth and safe drone landing area estimation models. We analysed state-of-the-art Deep Learning networks and trained them on the SafeUAV dataset. While the depth models achieved very satisfactory results in the SafeUAV dataset, they showed a scaling error in the AirSimNC benchmark. We also compared the performance of networks trained on the KITTI and NYUv2 datasets, in order to test how training the networks on a bird’s eye view affects in the performance on our benchmark. Regarding the safe landing estimation models, they surprisingly showed barely any zero-shot cross-dataset penalty when it comes to the precision of horizontal surfaces.
BIB_text
title = {Exploiting AirSim as a Cross-Dataset Benchmark for Safe UAV Landing and Monocular Depth Estimation Models},
pages = {454-462},
keywds = {
Monocular Depth Estimation, Safe Drone Landing, UAV, Synthetic Dataset, Simulation
}
abstract = {
As there is a lack of publicly available datasets with depth and surface normal information from a drone’s view, in this paper, we introduce the synthetic and photorealistic AirSimNC dataset. This dataset is used as a benchmark to test the zero-shot cross-dataset performance of monocular depth and safe drone landing area estimation models. We analysed state-of-the-art Deep Learning networks and trained them on the SafeUAV dataset. While the depth models achieved very satisfactory results in the SafeUAV dataset, they showed a scaling error in the AirSimNC benchmark. We also compared the performance of networks trained on the KITTI and NYUv2 datasets, in order to test how training the networks on a bird’s eye view affects in the performance on our benchmark. Regarding the safe landing estimation models, they surprisingly showed barely any zero-shot cross-dataset penalty when it comes to the precision of horizontal surfaces.
}
isbn = { 978-989-758-611-8},
date = {2022-10-26},
}
