Search

Your search keyword '"Li, Zengke"' showing total 134 results
Start Over Author "Li, Zengke"
134 results on '"Li, Zengke"'

1. SuperVINS: A visual-inertial SLAM framework integrated deep learning features

Author

Luo, Hongkun, Guo, Chi, Liu, Yang, and Li, Zengke

Subjects
Computer Science - Robotics
Abstract

In this article, we propose enhancements to VINS-Fusion by incorporating deep learning features and deep learning matching methods. We implemented the training of deep learning feature bag of words and utilized these features for loop closure detection. Additionally, we introduce the RANSAC algorithm in the deep learning feature matching module to optimize matching. SuperVINS, an improved version of VINS-Fusion, outperforms it in terms of positioning accuracy, robustness, and more. Particularly in challenging scenarios like low illumination and rapid jitter, traditional geometric features fail to fully exploit image information, whereas deep learning features excel at capturing image features.To validate our proposed improvement scheme, we conducted experiments using open source datasets. We performed a comprehensive analysis of the experimental results from both qualitative and quantitative perspectives. The results demonstrate the feasibility and effectiveness of this deep learning-based approach for SLAM systems.To foster knowledge exchange in this field, we have made the code for this article publicly available. You can find the code at this link: https://github.com/luohongk/SuperVINS.

Published
2024

2. Research of Precise Point Positioning Model Based on Smartphone

Author

Ge, Yuxiang, Li, Zengke, Liu, Zan, Wang, Yifan, Wang, Yangyang, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Tan, Kay Chen, Series Editor, Yang, Changfeng, editor, and Xie, Jun, editor

Published
2024
Full Text
View/download PDF

9. Magnetic Matching/PDR Combined Positioning Method Under the Constraint of Error Ellipse

Author

Shao, Kefan, Li, Zengke, Wang, Zhaoyuan, Liu, Zhenbin, Guo, Qiang, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Oneto, Luca, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zamboni, Walter, Series Editor, Zhang, Junjie James, Series Editor, Yang, Changfeng, editor, and Xie, Jun, editor

Published
2022
Full Text
View/download PDF

14. Assessment of GPS/BDS Precise Point Positioning Performance with BDS-3 New Signals

Author

Liu, Zan, Li, Zengke, Wang, Chengcheng, Yang, Zhehua, Yang, Xiangsheng, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Rüdiger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Li, Yong, Series Editor, Liang, Qilian, Series Editor, Martín, Ferran, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Speidel, Joachim, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zhang, Junjie James, Series Editor, Yang, Changfeng, editor, and Xie, Jun, editor

Published
2021
Full Text
View/download PDF

15. System and Method for Reducing NLOS Errors in UWB Indoor Positioning.

Author

Wang, Yifan, Zhang, Di, Li, Zengke, Lu, Ming, Zheng, Yunfei, and Fang, Tianye

Subjects
INDOOR positioning systems
Abstract

The ultra-wideband (UWB) technology has been increasingly recognized as an efficacious strategy for Indoor Positioning Systems (IPSs). However, the accuracy of the UWB system can be severely degraded by non-line-of-sight (NLOS) errors. In this study, we proposed a new method to reduce the UWB positioning error in such an indoor environment. We developed a system consisting of a Robotic Total Station (RTS), four UWB base stations, a moving target (including a prism and a UWB tag), and a PC. The observed coordinates of the moving target, captured using millimeter precision from an RTS device, served as the ground truth for calculating the positioning errors of the UWB tag. In a significant NLOS scenario, the UWB's three-dimensional positioning error was identified to exceed the nominal value declared by the manufacturer by a factor of more than three. A detailed analysis revealed that each coordinate component's error distribution pattern demonstrated considerable variance. To reduce the NLOS error, we designed a combined multilayer neural network that simultaneously fits errors on all three coordinate components and three separate multilayer networks, each dedicated to optimizing errors on a single coordinate component. All networks were trained and verified by benchmark errors obtained from the RTS. The results showed that neural networks outperform the traditional methods, attributed to their strong nonlinear modelling ability, thereby significantly improving the external accuracy by an average reduction in RMSE by 61% and 72%. It is evident that the proposed separate networks would be more suitable for NLOS positioning problems than a combined network. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

23. Stratified Weighting Method Based on Posterior Residual Error

Author

Li, Fangchao, Gao, Jingxiang, Li, Zengke, Yao, Yifei, Wang, Ren, Li, Ruoxi, Angrisani, Leopoldo, Series Editor, Arteaga, Marco, Series Editor, Panigrahi, Bijaya Ketan, Series Editor, Chakraborty, Samarjit, Series Editor, Chen, Jiming, Series Editor, Chen, Shanben, Series Editor, Chen, Tan Kay, Series Editor, Dillmann, Ruediger, Series Editor, Duan, Haibin, Series Editor, Ferrari, Gianluigi, Series Editor, Ferre, Manuel, Series Editor, Hirche, Sandra, Series Editor, Jabbari, Faryar, Series Editor, Jia, Limin, Series Editor, Kacprzyk, Janusz, Series Editor, Khamis, Alaa, Series Editor, Kroeger, Torsten, Series Editor, Liang, Qilian, Series Editor, Ming, Tan Cher, Series Editor, Minker, Wolfgang, Series Editor, Misra, Pradeep, Series Editor, Möller, Sebastian, Series Editor, Mukhopadhyay, Subhas, Series Editor, Ning, Cun-Zheng, Series Editor, Nishida, Toyoaki, Series Editor, Pascucci, Federica, Series Editor, Qin, Yong, Series Editor, Seng, Gan Woon, Series Editor, Veiga, Germano, Series Editor, Wu, Haitao, Series Editor, Zhang, Junjie James, Series Editor, Sun, Jiadong, editor, Yang, Changfeng, editor, and Guo, Shuren, editor

Published
2018
Full Text
View/download PDF

26. Location Accuracy Indicator Enhanced Method Based on MFM/PDR Integration Using Kalman Filter for Indoor Positioning

Author

Wu, Qi, Li, Zengke, and Shao, Kefan

Abstract

Based on the complementary advantages of integrated positioning methods, the multisource integrated positioning technology has become one of the mainstream technologies in the field of indoor navigation and positioning. However, little literature is available on the estimating for positioning accuracy of different sources in the integration. The negative benefits of integrated positioning method are caused by inaccurately estimated accuracy, which frequently occur in two sources integrated positioning without any correction. To study how to estimate the positioning accuracy of different sources in the integration, we propose a location accuracy indicator enhanced method based on magnetic field matching (MFM) and pedestrian dead reckoning (PDR) integration using Kalman filter (KF): the prior covariance based on PDR and the posterior covariance based on MFM are adopted to calculate noise matrixes of the KF and established the location accuracy indicator enhanced filtering system. From the results, the proposed method, which was less affected by changing the matching range of the magnetic field and broadening the interval of the fingerprint database, obtained 2.746 and 1.881 m for 90% error and root-mean-square error (RMSE), respectively, and the error was 24%–27% lower than the best empirical model, including weighted nearest ${k}$ -neighborhood (WKNN)/PDR (3.776 and 2.523 m) and integrated weight nearest neighborhood (IWNN)/PDR (3.712 and 2.485 m). It was verified by the experiments that the proposed method could accurately calculate noise matrixes of the KF and provide accurate weights, having stronger positioning performance and robustness than the others.

Published
2024
Full Text
View/download PDF

27. Fingerprint Accuracy Indication Geomagnetic/PDR Indoor Adaptive Integrated Positioning Based on Smartphones

Author

Shao, Kefan, Li, Zengke, Guo, Qiang, Liu, Zhenbin, and Wu, Qi

Abstract

Geomagnetic (magnetic)/pedestrian dead reckoning (PDR) integrated positioning, used in smartphone-based indoor positioning of pedestrians, is popular owing to its autonomous positioning and lack of a need for additional equipment. Single-point magnetic matching (SPMM) involves minimal computation and localization but is limited by its poor adaptability to diverse environments, few magnetic field features, and device heterogeneity. To solve these problems, we propose an improved SPMM/PDR based on the extended Kalman filter (EKF). First, we present a dynamic ${K}$ estimation for the weighted ${k}$ -nearest neighbor (WKNN) without previous information to compensate for the shortage of the WKNN with fixed ${K}$ when different signal distributions exist in different locations. Then, we propose a stochastic measurement model construction method with combined fingerprint accuracy indicators (CFAIs) to improve the adaptability to diverse environments. Finally, we fully exploit PDR’s high-accuracy relative localization to achieve adaptive compensation of the stochastic measurement model—adaptive EKF (AEKF)—to improve the accuracy and robustness of positioning. We compare three common methods based on five different smartphones, and the decrease in the positioning root mean square error (RMSE) values of the proposed AEKF-CFAI exceeds 16%, with the RMSE being lower than 0.9 m. Moreover, we investigate the influencing factors of the stochastic model construction and the impact of walking speed on AEKF-CFAI, finding that AEKF-CFAI is less affected by device heterogeneity and that AEKF has better robustness for different walking speeds than the CFAI-based method.

Published
2023
Full Text
View/download PDF

29. Application of Improved Robust Kalman Filter in Data Fusion for PPP/INS Tightly Coupled Positioning System

Author

Li Zengke, Yao Yifei, Wang Jian, and Gao Jingxiang

Subjects
PPP/INS tightly coupled positioning, robust filter, IGG scheme, Mahalanobis distance, Technology
Abstract

A robust Kalman filter improved with IGG (Institute of Geodesy and Geophysics) scheme is proposed and used to resist the harmful effect of gross error from GPS observation in PPP/INS (precise point positioning/inertial navigation system) tightly coupled positioning. A new robust filter factor is constructed as a three-section function to increase the computational efficiency based on the IGG principle. The results of simulation analysis show that the robust Kalman filter with IGG scheme is able to reduce the filter iteration number and increase efficiency. The effectiveness of new robust filter is demonstrated by a real experiment. The results support our conclusion that the improved robust Kalman filter with IGG scheme used in PPP/INS tightly coupled positioning is able to remove the ill effect of gross error in GPS pseudorange observation. It clearly illustrates that the improved robust Kalman filter is very effective, and all simulated gross errors added to GPS pseudorange observation are successfully detected and modified.

Published
2017
Full Text
View/download PDF

30. The next wave of GNSS tropospheric sounding – perspective and retrospective

Author

Zhang, Kefei, Liu, Zhizhao, Song, Shuli, Zheng, Nanshan, Zhang, Shubi, Wu, Suqin, Zhang, Qiuzhao, Li, Zengke, Wang, Xiaoming, Li, Longjiang, Sun, Peng, Li, Haobo, Zhu, Dantong, He, Qimin, and Zhang, Minghao

Abstract

As one of the most important parameters, water vapor is very valuable for the studies of extreme weather events and climatic phenomena. The GNSS have been proven to be a relatively new technique for sounding atmospheric water vapor which has experienced unprecedented developments over the past decade due to the rapid deployment of wide-spread space- and ground-based infrastructures. This significant development and the long-term accumulation of GNSS data, has offered a strong data support and new opportunity to advance our understanding of climate change and extreme weather events. In the meanwhile, the fifth resurgence of artificial intelligence (AI) technology has empowered us in the ability of big geodetic data analytics and data mining. All these have helped us in the understanding the atmospheric dynamic process, and mining the detailed information of the formation, evolution, development and dissolution of extreme weather events and complicated atmospheric process.This contribution presents a summary of our 10-year relevant research in the area that involves a full spatial domain of ground-, air- and space-based systems and a comprehensive technological domain of GNSS/geodesy, remote sensing, meteorology and atmosphere. First, the background, current status and recent international frontier developments of the GNSS tropospheric sounding technique are summarized. Then, the theory, technical features and major advancement of the GNSS-derived atmospheric products in the applications of climate analyses and extreme weather forecasting are presented. Finally, the challenges, opportunities and future prospectives in terms of the technique and its innovative applications of national and international significance are provided., The 28th IUGG General Assembly (IUGG2023) (Berlin 2023)

Published
2023

35. Deep neural network‐based Wi‐Fi/pedestrian dead reckoning indoor positioning system using adaptive robust factor graph model

Author

Long Zhao, Li Zengke, Jingxiang Gao, and Yifan Wang

Subjects
Artificial neural network, Computer science, business.industry, Posterior probability, 020206 networking & telecommunications, Gyroscope, 02 engineering and technology, Radio navigation, law.invention, Indoor positioning system, law, Dead reckoning, 0202 electrical engineering, electronic engineering, information engineering, Computer vision, Artificial intelligence, Electrical and Electronic Engineering, Hidden Markov model, business, Factor graph
Abstract

A deep neural network (DNN)-based Wi-Fi/pedestrian dead reckoning (PDR) indoor positioning system using an adaptive robust factor-graph model is proposed in this study for the indoor positioning of smartphones. In Wi-Fi positioning, the authors use a DNN to extract robust features from fluctuant Wi-Fi signals in the off-line phase, and obtain more accurate positioning results by computing posterior probabilities in online positioning. Acceleration, gyroscope, and magnetometer data are used to calculate attitude angle, step frequency, and step length, respectively. Received Wi-Fi signal strength is susceptible in complex indoor environments, and PDR errors accumulate over time. A factor-graph model with adaptive robust adjustment is proposed to fuse the positioning results of Wi-Fi and PDR, and it overcomes such shortcomings as slow update frequency and gross errors of Wi-Fi and PDR errors accumulated over time, respectively. When the absence of PDR occurs, hidden Markov model is introduced to smooth multiple DNN-based Wi-Fi positioning estimates at the unknown point to obtain the optimal solution. Experimental results show that the proposed system is more robust and has better accuracy under different motion gestures (held-in-hand, dangling, and calling).

Published
2020

47. The Application of Adaptive Federated Filter in GPS-INS-Odometer Integrated Navigation

Author

LI Zengke, WANG Jian, GAO Jingxiang, and YAO Yifei

Subjects
information allocation factor, adaptive factor, federated filter, GPS-INS-Odometer integrated navigation, lcsh:Mathematical geography. Cartography, lcsh:GA1-1776
Abstract

In multi-sensor integrated navigation, extensive observation information, low computational efficiency and weak robust ability will lead to poor navigation performance. An adaptive federated filter is proposed and applied in GPS-INS-Odometer integrated navigation. First the dynamical model and observation model of GPS-INS-Odometer integrated navigation are introduced. Information allocation factor and adaptive factor are compared to find out their common characteristic. The equivalence property between federated filter and adaptive filter is proved and the condition of equivalence is built. The information allocation factor of adaptive federated filter is constructed. Finally an actual calculation was performed to test the validity of new algorithm. The results of the experiment indicate that compared with the information allocation factor constructed by initial variance of GPS and Odometer in classical federated filter, adaptive federated filter shows well robust performance and high computational efficiency. It can weaken the influence of multi-sensor dynamical model disturbance on navigation resolution. The proposed method plays a positive role in improving the accuracy of directly measurable parameters and indirectly measurable parameters.

Published
2016

Catalog

Books, media, physical & digital resources
See catalog results