普氏原羚跟踪自主无人机基于改进的长短期记忆卡尔曼滤波器。

Procapra Przewalskii Tracking Autonomous Unmanned Aerial Vehicle Based on Improved Long and Short-Term Memory Kalman Filters.

机构信息

North China Institute of Aerospace Engineering, Langfang 065000, China.

Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China.

出版信息

Sensors (Basel). 2023 Apr 13;23(8):3948. doi: 10.3390/s23083948.

DOI:10.3390/s23083948

PMID:37112289

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC10144096/

Abstract

This paper presents an autonomous unmanned-aerial-vehicle (UAV) tracking system based on an improved long and short-term memory (LSTM) Kalman filter (KF) model. The system can estimate the three-dimensional (3D) attitude and precisely track the target object without manual intervention. Specifically, the YOLOX algorithm is employed to track and recognize the target object, which is then combined with the improved KF model for precise tracking and recognition. In the LSTM-KF model, three different LSTM networks (, , and ) are adopted to model a nonlinear transfer function to enable the model to learn rich and dynamic Kalman components from the data. The experimental results disclose that the improved LSTM-KF model exhibits higher recognition accuracy than the standard LSTM and the independent KF model. It verifies the robustness, effectiveness, and reliability of the autonomous UAV tracking system based on the improved LSTM-KF model in object recognition and tracking and 3D attitude estimation.

摘要

本文提出了一种基于改进长短时记忆（LSTM）卡尔曼滤波器（KF）模型的自主无人机（UAV）跟踪系统。该系统可以在无需人工干预的情况下估计三维（3D）姿态并精确跟踪目标物体。具体来说，采用 YOLOX 算法对目标物体进行跟踪和识别，然后与改进的 KF 模型结合进行精确跟踪和识别。在 LSTM-KF 模型中，采用三个不同的 LSTM 网络（、、和）来对非线性传递函数进行建模，以使模型能够从数据中学习到丰富而动态的 Kalman 分量。实验结果表明，改进的 LSTM-KF 模型在识别准确率方面优于标准的 LSTM 和独立的 KF 模型。这验证了基于改进的 LSTM-KF 模型的自主 UAV 跟踪系统在目标识别和跟踪以及 3D 姿态估计方面的鲁棒性、有效性和可靠性。