Procapra Przewalskii Tracking Autonomous Unmanned Aerial Vehicle Based on Improved Long and Short-Term Memory Kalman Filters
Wei Luo,
Yongxiang Zhao,
Quanqin Shao,
Xiaoliang Li,
Dongliang Wang,
Tongzuo Zhang,
Fei Liu,
Longfang Duan,
Yuejun He,
Yancang Wang,
Guoqing Zhang,
Xinghui Wang,
Zhongde Yu
Affiliations
Wei Luo
North China Institute of Aerospace Engineering, Langfang 065000, China
Yongxiang Zhao
North China Institute of Aerospace Engineering, Langfang 065000, China
Quanqin Shao
Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
Xiaoliang Li
North China Institute of Aerospace Engineering, Langfang 065000, China
Dongliang Wang
Key Laboratory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China
Tongzuo Zhang
University of Chinese Academy of Sciences, Beijing 101407, China
Fei Liu
Intelligent Garden and Ecohealth Laboratory (iGE), College of Biosystems Engineering and Food Science, Zhejiang University, 866 Yuhangtang Road, Hangzhou 310058, China
Longfang Duan
North China Institute of Aerospace Engineering, Langfang 065000, China
Yuejun He
North China Institute of Aerospace Engineering, Langfang 065000, China
Yancang Wang
North China Institute of Aerospace Engineering, Langfang 065000, China
Guoqing Zhang
North China Institute of Aerospace Engineering, Langfang 065000, China
Xinghui Wang
North China Institute of Aerospace Engineering, Langfang 065000, China
Zhongde Yu
North China Institute of Aerospace Engineering, Langfang 065000, China
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 (f, Q, and R) 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.
