2021
DOI: 10.1186/s40648-021-00196-3
|View full text |Cite
|
Sign up to set email alerts
|

EKF-based self-attitude estimation with DNN learning landscape information

Abstract: This paper presents an EKF-based self-attitude estimation with a DNN (deep neural network) learning landscape information. The method integrates gyroscopic angular velocity and DNN inference in the EKF. The DNN predicts a gravity vector in a camera frame. The input of the network is a camera image, the outputs are a mean vector and a covariance matrix of the gravity. It is trained and validated with a dataset of images and corresponded gravity vectors. The dataset is collected in a flight simulator because we … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
2
2

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(1 citation statement)
references
References 16 publications
0
1
0
Order By: Relevance
“…The experimental results show that the method can predict the gravity vector from a single-shot image and obtain the attitude information of the landscape. At the same time, the use of the simulator breaks the limit of real data acquisition on the ground [28]. The EKF architecture is shown in Figure 16.…”
Section: Application Analysis Of Pose Estimation Based On Visualmentioning
confidence: 99%
“…The experimental results show that the method can predict the gravity vector from a single-shot image and obtain the attitude information of the landscape. At the same time, the use of the simulator breaks the limit of real data acquisition on the ground [28]. The EKF architecture is shown in Figure 16.…”
Section: Application Analysis Of Pose Estimation Based On Visualmentioning
confidence: 99%