Research on Improved Indoor Localization Algorithm for UAVs Based on VINS

Xi Zhang; Nianqing Tan

doi:10.54097/dnbnkp47

Authors

Xi Zhang
Nianqing Tan

DOI:

https://doi.org/10.54097/dnbnkp47

Keywords:

Feature boosting, uav indoor localization, visual-inertial odometry, vision-inertial fusion.

Abstract

To address the limitations of UAV localization accuracy in complex indoor environments, an improved vision-inertial fusion-based UAV indoor positioning method was proposed. The conventional Vision-aided Inertial Navigation System (VINS)-Fusion algorithm was constrained by performance limitations under weak texture and dynamic lighting conditions, leading to degraded system positioning accuracy. To enhance positioning performance, Shi-Tomasi feature points were replaced with ORB (Oriented FAST and Rotated BRIEF) feature points. The binary BRIEF descriptor was employed to improve feature distinctiveness, and the gray centroid method was applied to assign orientation information, ensuring rotational invariance and enhancing image matching robustness in high-speed motion scenarios. Furthermore, a deep learning-driven Feature Booster technique was innovatively introduced to optimize feature descriptors. Through self-enhancement and interactive enhancement mechanisms, the correlations among features were fully exploited, effectively improving descriptor distinctiveness. Finally, a UAV hardware platform based on the RK3588 chip was developed, and a motion capture system was utilized to fine-tune UAV attitude control parameters. Simulations using the EuRoc dataset and real-world indoor flight experiments were conducted to verify the positioning performance and feasibility of the improved algorithm. Experimental results demonstrated that, in complex indoor environments, the root mean square error (RMSE) of the improved algorithm was reduced by 12.24% compared to the original VINS-Fusion algorithm, achieving higher positioning accuracy under dynamic lighting and sparse texture conditions.

Downloads

Download data is not yet available.

References

[1] X. Y. Wang, G. Z. Gao, L. L. Gu, et al., “Study on the legal system for promoting China’s low-altitude economy,” Information & Communication Technology and Policy, no. 11, pp. 48–53, 2024.

[2] T. Xia and J. L. Zhao, “Exploration on the application of UAV technology in military logistics,” China Storage and Transportation, no. 9, pp. 132–133, 2024.

[3] L. Yang, “Analysis of the effectiveness of water conservancy engineering inspection using UAV technology,” Water Safety, no. 21, pp. 13–15, 2024.

[4] X. W. Cui, “Application of UAV technology in geological disaster monitoring,” Anhui Geology, no. 2, pp. 153–156, 2024.

[5] Z. H. Wang, “Indoor positioning and flight control of quadrotor UAV based on UWB,” M.S. thesis, Heilongjiang Univ., Harbin, China, 2024.

[6] M. Zhao, “Study on UAV autonomous positioning method based on 3D LiDAR,” M.S. thesis, North China Electric Power Univ., Beijing, China, 2020.

[7] F. Y. Li, “Design and implementation of UAV indoor positioning system based on UWB technology,” M.S. thesis, Nanchang Univ., Nanchang, China, 2022.

[8] J. F. He, T. Xi, and L. Zhang, “Design of a rotor UAV positioning system based on monocular vision,” Wireless Internet Technol. no. 21, pp. 79–81, 2022.

[9] B. Chen and Q. Li, “Application of multi-sensor fusion in UAV indoor 3D positioning,” Sensor World, no. 3, pp. 27–36, 2022.

[10] L. Y. Wang, G. T. Yang, B. Y. Li, et al., “UAV indoor positioning and autonomous navigation method based on improved VINS,” Control Eng., to be published.

[11] Y. F. Cai, Z. H. Lu, Y. C. Li, et al., “A tightly coupled SLAM system based on multi-sensor fusion,” Automot. Eng., no. 3, pp. 350–361, 2022.

[12] J. C. Li, Z. C. Zhang, B. Y. Ding, et al., “Research on visual-inertial SLAM based on small sliding window optimization,” Electronic Production, no. 22, pp. 96–99, 2022.

[13] X. Wang, Z. Liu, Y. Hu, et al., “FeatureBooster: Boosting feature descriptors with a lightweight neural network,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition, New York, NY, USA, 2023, pp. 7630–7639.

[14] W. W. Zhang, J. L. Zhao, J. He, et al., “A step array-based BRIEF feature descriptor,” Computer Technol. Dev., no. 5, pp. 81–87, 2023.

[15] S. Q. Tan and P. J. Shuai, “Research on ORB feature point extraction algorithm based on adaptive threshold,” Mod. Comput., no. 4, pp. 43–47, 2024.

[16] X. J. Ning, J. R. Li, F. Gao, et al., “Feature matching algorithm based on optimal geometric constraints and RANSAC,” J. Syst. Simul., no. 4, pp. 727–734, 2022.

[17] J. H. Lu, “Research on multi-sensor fusion SLAM based on tight coupling and graph optimization,” M.S. thesis, Chongqing Technol. and Business Univ., Chongqing, China, 2023.

[18] W. S. Chen, Y. F. Huang, and X. F. Lu, “Review of UAV detection technology based on multi-sensor fusion,” Mod. Radar, no. 6, pp. 15–29, 2020.

[19] J. W. Jiang, Y. H. Ji, J. J. Liu, et al., “A fast loop detection algorithm in visual SLAM based on lightweight CNN,” Comput. Simul., no. 8, pp. 182–188, 2024.

[20] Z. G. Shang, “Research on visual SLAM algorithm based on particle swarm optimization and deep learning,” M.S. thesis, Univ. of Electronic Sci. and Technol. of China, Chengdu, China, 2024.