<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>The attitude angles of UAV, as the input parameters of the target localization process, influence the accuracy of geo-targeting. In order to improve the accuracy of target localization, this paper compensates the attitude angle errors of the UAV based on learning prediction compensation. Firstly, considering the airborne equipment and the metadata provided by the UAV, we combine rear intersection with GPS/INS to calculate the error of each platform and aircraft attitude angle. Then the error prediction model to compensate each platform and aircraft attitude error is derived by analyzing the error distribution and polynomial regression. Afterwards, because of the limit of the UAV aerial image amount and the similar influence of each attitude angle error on targeting and geometric correction, we use equivalent optical axis angle to represent platform and aircraft attitudes. Furthermore, we also predict and compensate the error of the equivalent angle. In this process, we adopt SVM and regression to classify and obtain error prediction model of equivalent optical axis angle. Finally, the actual data is used to verify the compensation algorithm. The results show that the method can improve the accuracy of target localization efficiently, and has a certain value of engineering guidance and practical application</p>
</abstract>

The attitude angles of UAV, as the input parameters of the target localization process, influence the accuracy of geo-targeting. In order to improve the accuracy of target localization, this paper compensates the attitude angle errors of the UAV based on learning prediction compensation. Firstly, considering the airborne equipment and the metadata provided by the UAV, we combine rear intersection with GPS/INS to calculate the error of each platform and aircraft attitude angle. Then the error prediction model to compensate each platform and aircraft attitude error is derived by analyzing the error distribution and polynomial regression. Afterwards, because of the limit of the UAV aerial image amount and the similar influence of each attitude angle error on targeting and geometric correction, we use equivalent optical axis angle to represent platform and aircraft attitudes. Furthermore, we also predict and compensate the error of the equivalent angle. In this process, we adopt SVM and regression to classify and obtain error prediction model of equivalent optical axis angle. Finally, the actual data is used to verify the compensation algorithm. The results show that the method can improve the accuracy of target localization efficiently, and has a certain value of engineering guidance and practical application

High Precision Target Localization Method Based On Compensation Of Attitude Angle Errors

Beijing University of Aeronautics and Astronautics

International Journal on Smart Sensing and Intelligent Systems

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

The attitude angles of UAV, as the input parameters of the target localization process, influence the accuracy of geo-targeting. In order to improve the...

High Precision Target Localization Method Based On Compensation Of Attitude Angle Errors

Online veröffentlicht: 01. März 2016

Seitenbereich: 169 - 190

Eingereicht: 17. Nov. 2016

Akzeptiert: 23. Jan. 2016

DOI: https://doi.org/10.21307/ijssis-2017-865

Schlüsselwörter
UAV, Geo-targeting technology, Attitude Angles, Rear intersection, Regression, Learning

© 2016 Jialiang Liu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

High Precision Target Localization Method Based On Compensation Of Attitude Angle Errors

Online veröffentlicht: 01. März 2016

Seitenbereich: 169 - 190

Eingereicht: 17. Nov. 2016

Akzeptiert: 23. Jan. 2016

DOI: https://doi.org/10.21307/ijssis-2017-865

SchlüsselwörterUAV, Geo-targeting technology, Attitude Angles, Rear intersection, Regression, Learning

© 2016 Jialiang Liu et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Schlüsselwörter
UAV, Geo-targeting technology, Attitude Angles, Rear intersection, Regression, Learning