检索结果-内蒙古大学图书馆

A new target tracking filter based on deep learning

Chinese Journal of Aeronautics 2022年第5期35卷 11-24页

作者： Yaqi CUI You HE Tiantian TANG Yu LIU Naval Aviation University Yantai 264001China

At present,current filters can basically solve the filtering problem in target tracking,but there are still many problems such as too many filtering variants,too many filtering forms,loosely coupled with the target motion model,and so *** solve the above problems,we carry out crossapplication research of artificial intelligence theory and methods in the field of tracking *** firstly analyze the computation graphs of typical a-βand *** analysis,it is concluded that a-βand Kalman have the same computation structures analogous to a typical recurrent neural network and can be considered as a kind of recurrent neural network with constrained ***,given this and considering that a recurrent neural network has the recognition capability for target motion patterns,a new filter is developed in a unified neural network architecture and specifically constructed using feedforward neural network,recurrent neural network,and attention *** the unified tracking filter proposed in this paper can generate three aspects of unity:a unified target motion model,an adaptive filter method,and an overall track filtering ***,Simulation results show that the proposed filter is effective and useful,of which the overall performance is superior to those of compared filters.

关键词： Attention mechanism Feedforward neural network interactive multiple model Recurrent neural network Tracking filter

来源：评论

学校读者我要写书评

暂无评论

Adaptive Hybrid Robust Filter for Multi-Sensor Relative Navigation System

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2022年第8期23卷 11026-11040页

作者： Xiong, Jun Cheong, Joon Wayn Xiong, Zhi Dempster, Andrew G. Tian, Shiwei Wang, Rong Nanjing Univ Posts & Telecommun Sch Internet Things Nanjing 210049 Peoples R China Univ New South Wales Sch Elect Elect & Telecommun Engn Sydney NSW 2052 Australia Nanjing Univ Aeronaut & Astronaut Coll Automat Nanjing 210016 Jiangsu Peoples R China Natl Innovat Inst Def Technol Beijing 100000 Peoples R China

This paper provides an adaptive hybrid robust filter (AHRF) for multi-sensor relative navigation systems that can be used to support cooperative intelligent transport systems. It is known that Huber's M-estimation based robust filter and the fault detection and exclusion (FDE) based RAIM filter each has its own drawbacks, depending on the nature of the observation error biases. Based on the interactive multiple model (IMM) framework, our proposed AHRF in this paper can take advantage of both filters in a complementary sense. A new adaptive IMM (AIMM) algorithm with Markov transition probability prediction is proposed to allow AHRF to switch efficiently between the two filters. We consider the relative navigation system with Global Navigation Satellite System (GNSS) and ultra-wideband (UWB) as observations to verify AHRF in three cases of possible failure modes and multipath-induced errors. Our results show that AHRF outperforms both the FDE and robust filter in all cases. AHRF framework can be further adapted to include many other fault-tolerant filters to improve the robustness of multi-sensor relative navigation system even further.

关键词： Global navigation satellite system Navigation Distance measurement Satellites Receivers Switches Kalman filters Robust filter RAIM GNSS interactive multiple model

来源：评论

学校读者我要写书评

暂无评论

IMM/EKF filter based classification of real-time freeway video traffic without learning

引用

TRANSPORTATION LETTERS-THE INTERNATIONAL JOURNAL OF TRANSPORTATION RESEARCH 2022年第6期14卷 610-621页

作者： Ouessai, Asmaa Keche, Mokhtar Univ Sci & Technol Mohamed Boudiaf USTOMB Fac Elect Engn Dept Elect Signals & Images Lab Bir El Djir Oran Algeria

This paper addresses the problem of traffic variable estimation and traffic state classification of highway traffic, from video. To solve this problem, we propose to use the interactive multiple model (IMM) filter with a multi-class macroscopic model. This filter runs two Extended Kalman Filters (EKF) to smooth the measured traffic parameters. In addition, the models' probabilities that it provides are exploited to simply classify the traffic state as either free or congested, without the need for a training phase. The evaluation of the proposed system using simulated traffic parameters shows that it achieves a very accurate traffic state classification. The system was also tested in the real world, using video data acquired on a freeway by camera sensors. The obtained classification rates are comparable to those obtained by SVM classification, but at a significantly lower computational load.

关键词： Highway video traffic classification traffic estimation extended Kalman filter interactive multiple model learning

来源：评论

学校读者我要写书评

暂无评论

The Tracking Estimation of Maneuvering UAVs Based on Enhanced Convergence IMM-EKF

The Tracking Estimation of Maneuvering UAVs Based on Enhance...

引用

International Conference on Autonomous Unmanned Systems (ICAUS)

作者： Chen, Hanwen Hu, Qi Liu, Yaobo Tian, Qiang Zhang, Zhao Nanjing Res Inst Elect Technol Nanjing 210012 Peoples R China China Univ Min & Technol Sch Geosci & Surveying Engn Beijing Peoples R China

ISBN: (纸本)9789819904815;9789819904792;9789819904785

Efficient and accurate state estimation of maneuvering targets is a key step in radar surveillance systems. Especially in the unmanned aerial vehicles (UAVs) tracking scenes, the estimation of UAV's position and velocity is not enough, and more details, such as heading angle and turning rate, are required in the estimated state space. In this paper, our effort is to establish a novel estimator that incorporates an enhanced extended Kalman filter (EKF) into the interactive multiple model (IMM) to improve the effectiveness of maneuvering UAV tracking. More specifically, a time-varying scaling process noise is introduced into the EKF to increase the filers' convergence rate without losing its persistent estimation performance. And the nearly constant speed horizontal turn (NCSHT) model, as a special maneuvering model, is introduced to ensure the tracking performance during maneuver. Applied into the ground-to-air UAVs' tracking experiment, the real-time results demonstrate the effectiveness of the proposed algorithm in convergence and accuracy.

关键词： interactive multiple model Extended Kalman Filter Nearly constant speed horizontal turn Time-varying scales

来源：评论

学校读者我要写书评

暂无评论

Research on Computer Artificial Intelligence interactive Labor Education and Training System 3

Research on Computer Artificial Intelligence Interactive Lab...

引用

2023 IEEE 3rd International Conference on Data Science and Computer Application, ICDSCA 2023

作者： Yin, Xingmei Shi, Xing Zhenjiang Vocational Technical College Zhenjiang China Jiangsu Aviation Technical College Zhenjiang China

ISBN: (纸本)9798350341546

In this paper, virtual reality technology is embedded into the virtual skill assessment model, and a comprehensive training system framework is built. OpenCV's and Multigene are selected as the development platforms of the virtual training system. A set of immersive virtual cooperative training system is developed through structural framework design, functional module design, database design and multi-person collaborative design. This paper proposes a vocational skill personalized learning based on tabu parallel genetic algorithm. The whole system implementation process from scene modeling to scene driven is discussed in detail. The application of the system can further improve the maintenance ability of the enterprise to the equipment, basic fault troubleshooting ability and overhaul ability, and reduce the loss caused by the wrong use and improper operation of the equipment. © 2023 IEEE.

关键词： artificial intelligence Computer interactive multiple model labor education and training system personalized learning tabu-parallel genetic algorithm vocational skills

来源：评论

学校读者我要写书评

暂无评论

Distributed IMM-information Kalman filter based on consensus filter for maneuvering target tracking in wireless sensor networks

引用

TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL 2024年

作者： Zamani, Zahra Safarinejadian, Behrouz Shiraz Univ Technol Dept Elect Engn Modarres BlvdPOB 71555-313 Shiraz Iran

This paper discusses distributed estimation in discrete linear systems for target tracking by wireless sensor networks. First, a distributed Kalman filter is presented in the form of an information filter based on consensus theory. In the distributed approach, each sensor node communicates only with its neighbors and there is no central node. In the next step, considering the maneuverability of the target and the absence of a single motion model, the algorithm of the interactive multiple model (IMM) based on the distributed information filter (DIMMIKF) is designed. Moreover, the Lyapunov stability of the proposed algorithm is proved. Finally, the simulation results show that this algorithm performs better than similar algorithms.

关键词： Target tracking interactive multiple model distributed Kalman filter consensus filter distributed information filter wireless sensor network

来源：评论

学校读者我要写书评

暂无评论

Advancing Sea Surface Height Retrieval through Global Navigation Satellite System Reflectometry: A model Interaction Approach with Cyclone Global Navigation Satellite System and FengYun-3E Measurements

引用

REMOTE SENSING 2024年第11期16卷 1896页

作者： Xing, Jin Yang, Dongkai Zhang, Zhibo Wang, Feng Beihang Univ Sch Elect & Informat Engn Beijing 100191 Peoples R China Beihang Univ Int Innovat Inst Hangzhou 311115 Peoples R China

The measurement of sea surface height (SSH), which is of great importance in the field of oceanography, can be obtained through the innovative technique of GNSS-R for remote sensing. This research utilizes the dataset from spaceborne GNSS-R platforms, the Cyclone Global Navigation Satellite System (CYGNSS) and FengYun-3E (FY-3E), as the primary source of data for retrieving sea surface height (SSH). The utilization of artificial neural networks (ANNs) allows for the accurate estimation of ocean surface height with a precision of meter-level accuracy throughout the period of 1-17 August 2022. As a traditional machine learning method, an ANN is employed to extract pertinent data features, facilitating the acquisition of precise sea surface height estimations. Additionally, separate models are devised for both GNSS-R platforms, one based on constant velocity (CV) and the other on constant acceleration (CA). The interactive multiple model (IMM) is utilized as the main method to combine the four models and convert the likelihood of each model. The transition between the models allows the filters to effectively adapt to dynamic changes and complex environments. This approach relies on the fundamental notion of the Kalman filter (KF), which showcases robust noise handling capabilities in predicting the SSH, separately. The results demonstrate that the model interaction technology is capable of efficiently filtering and integrating SSH data, yielding a Root Mean Square Error (RMSE) of 1.03 m. This corresponds to a 9.84% enhancement compared to the retrieved height from CYGNSS and a 37.19% enhancement compared to the retrieved height from FY-3E. The model proposed in this paper provides a potential scheme for the GNSS-R data fusion of multiple platforms and multiple models. In the future, more data sources and more models can be added to achieve more accurate adaptive fusion.

关键词： spaceborne GNSS-R CYGNSS and FY-3E interactive multiple model Kalman filter

来源：评论

学校读者我要写书评

暂无评论

CAMTrack: a combined appearance-motion method for multiple-object tracking

引用

MACHINE VISION AND APPLICATIONS 2024年第4期35卷 62-62页

作者： Bui, Duy Cuong Nguyen, Ngan Linh Hoang, Anh Hiep Yoo, Myungsik Soongsil Univ Dept Informat Commun Convergence Technol Seoul South Korea Soongsil Univ Dept Elect Engn Seoul South Korea Soongsil Univ Sch Elect Engn Seoul South Korea

Object tracking has emerged as an essential process for various applications in the field of computer vision, such as autonomous driving. Recently, object tracking technology has experienced rapid growth, particularly its applications in self-driving vehicles. Tracking systems typically follow the detection-based tracking paradigm, which is affected by the detection results. Although deep learning has led to significant improvements in object detection, data association remains dependent on factors such as spatial location, motion, and appearance, to associate new observations with existing tracks. In this study, we introduce a novel approach called Combined Appearance-Motion Tracking (CAMTrack) to enhance data association by integrating object appearances and their corresponding movements. The proposed tracking method utilizes an appearance-motion model using an appearance-affinity network and an interactive multiple model (IMM). We deploy the appearance model to address the visual affinity between objects across frames and employed the motion model to incorporate motion constraints to obtain robust position predictions under maneuvering movements. Moreover, we also propose a Two-phase association algorithm which is an effective way to recover lost tracks back from previous frames. CAMTrack was evaluated on the widely recognized object tracking benchmarks-KITTI and MOT17. The results showed the superior performance of the proposed method, highlighting its potential to contribute to advances in object tracking.

关键词： Autonomous vehicles Object detection multiple-object tracking Appearance affinity network interactive multiple model

来源：评论

学校读者我要写书评

暂无评论

Multi-Fault Diagnosis of Interacting multiple model Batteries Based on Low Inertia Noise Reduction

引用

IEEE ACCESS 2021年 9卷 18465-18480页

作者： Wang, Yongchao Meng, Dawei Li, Ran Zhou, Yongqin Zhang, Xiaoyu Harbin Univ Sci & Technol Sch Elect & Elect Engn Harbin 150080 Peoples R China Nankai Univ Coll Artificial Intelligence Tianjin 300071 Peoples R China

In view of the problems of declined estimation and diagnostic accuracy, as well as diagnosis delay caused by the fixed model transformation probability of the interacting multiple model (IMM) fault diagnosis algorithm, an IMM algorithm based on low inertia noise reduction (LN-IMM) was presented in this paper. The proposed algorithm realized the multi-fault diagnosis of lithium-ion batteries in combination with strong tracking Kalman filter (STKF). In the non-model transformation stage, a transition probability correction function was constructed using the difference of the n-th order based on model probability to suppress the effect of noise on the estimation accuracy of the algorithm. In the model transformation stage, a model jump threshold was introduced in order to reduce inertia when the matched model was switched and realized quick model transformation. Accordingly, the final experiment proved that the LN-IMM-STKF algorithm efficiently completed the state estimation of lithium-ion batteries and improved the diagnostic accuracy of faults while reducing diagnosis delay and attaining accurate detection as well as rapid separation of battery fault information.

关键词： Batteries Circuit faults Fault diagnosis Integrated circuit modeling Switches Kalman filters Filtering algorithms interactive multiple model low inertia noise reduction strong tracking Kalman filter lithium-ion battery

来源：评论

学校读者我要写书评

暂无评论

Weighted Maximum Correntropy Criterion-Based Interacting multiple-model Filter for Maneuvering Target Tracking

引用

REMOTE SENSING 2023年第18期15卷 4513-4513页

作者： Huai, Liangliang Li, Bo Yun, Peng Song, Chao Wang, Jiayuan Northwestern Polytech Univ Sch Elect & Informat Xian 710072 Peoples R China AVIC Leihua Elect Technol Res Inst Wuxi 214063 Peoples R China Xi An Jiao Tong Univ Sch Automat Sci & Engn Xian 710049 Peoples R China

During the process of maneuvering target tracking, the measurement may be disturbed by outliers, which leads to a decrease in the state estimation performance of the classic interacting multiple-model (IMM) filter. To solve this problem, a weighted maximum correntropy criterion (WMCC)-based IMM filter is proposed. In the proposed filter, the fusion state is used as the input of each sub-model to reduce the computational complexity of state interaction and the WMCC is adopted to derive the sub-model state update and state fusion to improve the state estimation performance under outlier interference. Through principal analysis, the superiority of the proposed filter over the classic IMM filter in fusion strategy is revealed. The specific form of the proposed filter in radar maneuvering target tracking is provided. Two experimental cases of maneuvering target tracking are tested to illustrate the effectiveness of the proposed filter.

关键词： outlier interference interactive multiple model weighted maximum correntropy criterion maneuvering target tracking

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：