Intelligent Control Algorithm for Low-altitude Target Based on Multi-sensor Data Fusion

This paper proposes an intelligent control algorithm for low-altitude targets that fuses data from multiple sensors, aiming to enhance the detection, recognition, and tracking capabilities of low-altitude vehicles such as drones. The algorithm introduces an optimized adaptive extended Kalman filter (PRO-EKF) algorithm, which dynamically adjusts the process noise covariance matrix, improving the system's robustness and accuracy in complex environments. In addition, this paper constructs a dataset containing time-domain plots, short-time Fourier transform (STFT) plots, continuous wavelet transform (CWT) plots, and Wigner-Ville distribution (WVD) plots, and uses a deep neural network to achieve feature-level fusion and training. Experimental results show that the multi-view fusion model significantly improves the accuracy of drone detection, with an average accuracy of 99.36% and a maximum accuracy of 99.85%. These results prove the effectiveness of the proposed method and provide a new solution for the safe management and rational application of low-altitude vehicles.