TY - JOUR
T1 - Absolute pose estimation of UAV based on large-scale satellite image
AU - WANG, Hanyu
AU - SHEN, Qiang
AU - DENG, Zilong
AU - CAO, Xinyi
AU - Wang, Xiaokang
N1 - Publisher Copyright:
© 2024
PY - 2024/6
Y1 - 2024/6
N2 - Obtaining absolute pose based on pre-loaded satellite images is one of the important means of autonomous navigation for small Unmanned Aerial Vehicles (UAVs) in Global Navigation Satellite System (GNSS) denied environments. Most of the previous works have tended to build Convolutional Neural Networks (CNNs) to extract features and then directly regress the pose, which will fail when solving the challenges caused by the huge viewpoint and size differences between “UAV-satellite” image pairs in real-world scenarios. Therefore, this paper proposes a probability distribution/regression integrated deep model with the attention-guided triple fusion mechanism, which estimates discrete distributions in pose space and three-dimensional vectors in translation space. In order to overcome the shortage of the relevant dataset, this paper simulates image datasets captured by UAVs with forward-facing cameras during target searching and autonomous attacking. The effectiveness, superiority, and robustness of the proposed method are verified by simulated datasets and flight tests.
AB - Obtaining absolute pose based on pre-loaded satellite images is one of the important means of autonomous navigation for small Unmanned Aerial Vehicles (UAVs) in Global Navigation Satellite System (GNSS) denied environments. Most of the previous works have tended to build Convolutional Neural Networks (CNNs) to extract features and then directly regress the pose, which will fail when solving the challenges caused by the huge viewpoint and size differences between “UAV-satellite” image pairs in real-world scenarios. Therefore, this paper proposes a probability distribution/regression integrated deep model with the attention-guided triple fusion mechanism, which estimates discrete distributions in pose space and three-dimensional vectors in translation space. In order to overcome the shortage of the relevant dataset, this paper simulates image datasets captured by UAVs with forward-facing cameras during target searching and autonomous attacking. The effectiveness, superiority, and robustness of the proposed method are verified by simulated datasets and flight tests.
KW - Deep neural networks
KW - Satellite imagery
KW - Unmanned Aerial Vehicle (UAV)
KW - Vision navigation
KW - von Mises-Fisher distribution
UR - http://www.scopus.com/inward/record.url?scp=85192792067&partnerID=8YFLogxK
U2 - 10.1016/j.cja.2023.12.028
DO - 10.1016/j.cja.2023.12.028
M3 - Article
AN - SCOPUS:85192792067
SN - 1000-9361
VL - 37
SP - 219
EP - 231
JO - Chinese Journal of Aeronautics
JF - Chinese Journal of Aeronautics
IS - 6
ER -