Comprehensive Research and Discussion on Multi-Sensor Fusion Technology in UAV Vision System

Ziyang Liu

doi:10.54097/fd154v91

Authors

Ziyang Liu

DOI:

https://doi.org/10.54097/fd154v91

Keywords:

Unmanned aerial vehicle vision system; multi-source sensor data fusion technology; real-world application scenarios; efficacy validation methods.

Abstract

This study comprehensively examines and analyses the application of multi-sensor fusion techniques within UAV vision systems. The study opens with an overview of current research advances in UAV vision systems and multi-sensor fusion technologies and specifies the methodological framework and experimental configuration of this study. Subsequently, the paper explains in detail the fundamental theoretical framework and constituent elements of UAV vision systems, as well as the basic definitions of multi-sensor fusion technologies, their classifications and their significant advantages. On this basis, the authors discuss in depth the specific application scenarios and realisation strategies of multi-sensor fusion technology in UAV vision systems, confirming the effectiveness of this technology in enhancing the effectiveness of UAV vision systems. In the epilogue, the key contributions and results of this study are summarised, and the innovations of the UAV vision system and the multi-sensor fusion technology are discussed, while the limitations are objectively pointed out, and a prospective outlook on potential future research paths is given.

Downloads

Download data is not yet available.

References

[1] Research on Autonomous Flight Control of Foreign UAVs [J]. TANG Qiang, ZHU Zhiqiang, WANG Jianyuan. System Engineering and Electronic Technology, 2004(03):418-422.

[2] Multiple View Motion Estimation and Control for Landing an Unmanned Aerial Vehicle. Omid Shakernia. 2002

[3] Research on altimetry technology of shipborne UAV recovery system based on quaternion method [J]. Gao ZF. Aerospace Return and Remote Sensing. 2013(06)

[4] Research on data fusion methods on data level and feature level [D]. Zhang Baomei. Lanzhou University of Science and Technology, 2005.

[5] Data fusion techniques for super-resolution imaging [J]. Deepu Rajan,Subhasis Chaudhuri. Information Fusion. 2002 (1)

[6] A review of multi-sensor fusion [J]. WANG Jun,SU Jianbo,XI Yugeng. Data Acquisition and Processing, 2004(01):72-77.

[7] A mathematical method to improve the positioning accuracy of matched guidance [J]. Wang Gensheng. Tactical Missile Technology, 1992(04):30-34.

[8] An Introduction to the Kalman Filter. Greg Welch, Gary Bishop. 2006

[9] A Kalman filter model for an integrated land vehicle navigation system. Ramjattan, A. N. and Gross, P. A. The Journal of Neuroscience. 1995

[10] A review of multi-sensor image fusion techniques [J]. Mao Shiyi, Zhao Wei. Journal of Beijing University of Aeronautics and Astronautics, 2002(05):512-518.

[11] Fundamentals and applications of Kalman filtering [J]. Peng Dingcong. Software Guide, 2009, 8(11):32-34.

[12] Consideration of time-correlated errors in a Kalman filter applicable to GNSS [J]. M. G. Petovello, K. O’Keefe, G. Lachapelle, M. E. Cannon. Journal of Geodesy. 2009 (1)

[13] Research and application of target detection and tracking technology based on deep learning [D]. Wang Xiaolong. Hubei University of Technology, 2020.

[14] Multisensor Data Fusion Architecture Based on Adaptive Kalman Filter sand Fuzzy Logic Performance Assessment. Escamilla-Ambrosio P J, Mort N. Proceedings of the Fifth International Conference on Information Fusion. 2002.