Yuxuan Zhou
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yuxuan Zhou has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Xingxing Li
Wuhan University
51 shared publications - Shengyu Li
Wuhan University
43 shared publications - Zhiheng Shen
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
16 shared publications - Chunxi Xia
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
13 shared publications - Shuolong Chen
School of Geodesy and Geomatics, Wuhan University, Wuhan, China
13 shared publications - Xuanbin Wang
Unmanned System Research Institute/School of Artificial Intelligence, Northwestern Polytechnical University, Xi'an, Shaanxi, China
13 shared publications
Latest Publications
- 25 June 2026
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 239, 698-712
MASt3R-Fusion: Integrating feed-forward visual model with IMU, GNSS for high-functionality SLAM
- 25 June 2026
- Published by Elsevier in ISPRS Journal of Photogrammetry and Remote Sensing
- Vol. 239, 698-712
MASt3R-Fusion: Integrating feed-forward visual model with IMU, GNSS for high-functionality SLAM
- 17 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 7714-7730
Improving Single-Frequency PPP With Multilayer Perceptron-Based Ionospheric Delay Model
Ionospheric delay, as a significant error source in GNSS raw observations, deserves rigorous handling in single-frequency precise point positioning (SF-PPP). Currently, SF-PPP commonly employs global ionospheric maps (GIM) from IGS analysis centers, obtaining slant delays through spatiotemporal interpolation and oblique projection. However, constrained by inaccuracies in phase-smoothed pseudorange-derived slant total electron content (STEC) and truncation errors during fitting procedures, GIM products achieve only 0.32-1.28 m equivalent ranging accuracy at GPS L1 frequency, offering limited enhancement for SF-PPP. In this paper, we propose a lightweight multilayer perceptron (MLP)-based ionospheric modeling approach to enhance SF-PPP. The proposed method utilizes undifferenced and uncombined PPP to generate raw slant ionospheric delays as training labels. The input features are constructed from satellite-related parameters (e.g. time, locations of the ionosphere pierce points, elevation and azimuth angles) that are readily available during precise positioning computation. By leveraging the exceptional nonlinear fitting capability of MLP, the proposed model can effectively capture the relationship between the slant ionospheric delay and satellite-related parameters to enhance SF-PPP. Experimental results demonstrate that the MLP-based approach achieves slant delay mean absolute error below 0.3 m. Compared to final ionospheric products from Center for Orbit Determination in Europe (CODE), the proposed method demonstrates a 14.9% to 52.6% reduction in slant ionospheric delay root mean square error across different time periods. Furthermore, the proposed method significantly reduces convergence time while enhancing positioning accuracy, with 95th percentile horizontal and vertical positioning errors below 0.527 m and 0.831 m respectively - corresponding to 41.5% and 43.3% reductions compared to CODE GIM-enhanced SF-PPP.
- 17 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 62 (00189251) , 7714-7730
Improving Single-Frequency PPP With Multilayer Perceptron-Based Ionospheric Delay Model
Ionospheric delay, as a significant error source in GNSS raw observations, deserves rigorous handling in single-frequency precise point positioning (SF-PPP). Currently, SF-PPP commonly employs global ionospheric maps (GIM) from IGS analysis centers, obtaining slant delays through spatiotemporal interpolation and oblique projection. However, constrained by inaccuracies in phase-smoothed pseudorange-derived slant total electron content (STEC) and truncation errors during fitting procedures, GIM products achieve only 0.32-1.28 m equivalent ranging accuracy at GPS L1 frequency, offering limited enhancement for SF-PPP. In this paper, we propose a lightweight multilayer perceptron (MLP)-based ionospheric modeling approach to enhance SF-PPP. The proposed method utilizes undifferenced and uncombined PPP to generate raw slant ionospheric delays as training labels. The input features are constructed from satellite-related parameters (e.g. time, locations of the ionosphere pierce points, elevation and azimuth angles) that are readily available during precise positioning computation. By leveraging the exceptional nonlinear fitting capability of MLP, the proposed model can effectively capture the relationship between the slant ionospheric delay and satellite-related parameters to enhance SF-PPP. Experimental results demonstrate that the MLP-based approach achieves slant delay mean absolute error below 0.3 m. Compared to final ionospheric products from Center for Orbit Determination in Europe (CODE), the proposed method demonstrates a 14.9% to 52.6% reduction in slant ionospheric delay root mean square error across different time periods. Furthermore, the proposed method significantly reduces convergence time while enhancing positioning accuracy, with 95th percentile horizontal and vertical positioning errors below 0.527 m and 0.831 m respectively - corresponding to 41.5% and 43.3% reductions compared to CODE GIM-enhanced SF-PPP.
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-15
Camera-Ground Geometry Enhanced Monocular Thermal–Inertial Odometry With Point-Line Fusion
Recently, thermal-inertial odometry (TIO) using in-frared cameras has garnered the attention of some scholars due to its all-weather working ability. However, infrared cameras, with high noise and poor imaging quality, seriously affecting the performance of TIO. This issue is particularly pronounced in the application of monocular infrared camera on unmanned ground vehicles (UGV). Thus, we propose a multi-information enhanced monocular TIO for UGV using point and line features based on the specific thermal imaging characteristics of infrared cameras. Firstly, a real-time TIO with point line combination is achieved using more advanced line feature extraction and tracking scheme. Secondly, a parallel front-end for ground point feature process is developed to overcome the scale degradation issue of monocular TIO using camera-ground constraints. Besides, the redundancy in ground line feature modeling was resolved based on the geometric relationship between the camera and the ground. Finally, a common back-end is developed to perform real-time optimization within a sliding window framework in-cluding IMU pre-integration factors, point feature reprojection factors, line feature reprojection factors, camera-ground con-straint factors, and ground line constraint factors. The proposed system was validated on real-world datasets and compared with the current state-of-the-art algorithm. Experimental results show that the proposed system exhibits superior performance and can achieve accurate scale estimation in monocular TIO under insuf-ficient excitation of UGV. The accuracy of MIE-TIO has been improved by 67.88%~96.73%, 64.89%~98.15%, 73.91%~98.78%, and 47.41%~95.59%, respectively, compared with VINS-Fusion, PL-VINS, EPLF-VINS, and POL-VIO. The dataset is available at https://github.com/Fireflyatcode/MIE-TIO.
- 23 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-15
Camera-Ground Geometry Enhanced Monocular Thermal–Inertial Odometry With Point-Line Fusion
Recently, thermal-inertial odometry (TIO) using in-frared cameras has garnered the attention of some scholars due to its all-weather working ability. However, infrared cameras, with high noise and poor imaging quality, seriously affecting the performance of TIO. This issue is particularly pronounced in the application of monocular infrared camera on unmanned ground vehicles (UGV). Thus, we propose a multi-information enhanced monocular TIO for UGV using point and line features based on the specific thermal imaging characteristics of infrared cameras. Firstly, a real-time TIO with point line combination is achieved using more advanced line feature extraction and tracking scheme. Secondly, a parallel front-end for ground point feature process is developed to overcome the scale degradation issue of monocular TIO using camera-ground constraints. Besides, the redundancy in ground line feature modeling was resolved based on the geometric relationship between the camera and the ground. Finally, a common back-end is developed to perform real-time optimization within a sliding window framework in-cluding IMU pre-integration factors, point feature reprojection factors, line feature reprojection factors, camera-ground con-straint factors, and ground line constraint factors. The proposed system was validated on real-world datasets and compared with the current state-of-the-art algorithm. Experimental results show that the proposed system exhibits superior performance and can achieve accurate scale estimation in monocular TIO under insuf-ficient excitation of UGV. The accuracy of MIE-TIO has been improved by 67.88%~96.73%, 64.89%~98.15%, 73.91%~98.78%, and 47.41%~95.59%, respectively, compared with VINS-Fusion, PL-VINS, EPLF-VINS, and POL-VIO. The dataset is available at https://github.com/Fireflyatcode/MIE-TIO.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-14
Enhancing PPP/INS Navigation by Tightly Integrating Visual Map Matching Based on Heterogeneous Road Markings
High-precision and robust positioning is crucial for ensuring safety and reliability of autonomous driving. The combination of precise point positioning (PPP) technology and inertial navigation system (INS) offers a globally available solution for continuous outdoor positioning. However, due to satellite signal degradation and error accumulation of low-cost INS, the positioning performance is challenged in complex urban environments. To address this issue, leveraging visual perception of specific prior map elements is an effective and applicable complementary approach. In this work, we tightly integrate visual map matching into PPP/INS navigation through a centralized extended Kalman filter (EKF). For map matching, heterogeneous road markings that structure urban roads are considered for constraint construction, whose observations are compactly modelled in 3D space and can be flexibly associated with the prior map. The complementary characteristics of map matching and PPP are fully exploited through tightly coupled integration, offering fast convergence, robustness against outliers, and sustained accuracy. The positioning performance and influencing factors of the proposed system are evaluated in both simulation and realistic urban road experiments. The results indicate that with the incorporation of map matching measurements, the proposed method exhibits superior performance in terms of accuracy and convergence, maintaining sub-decimeter to decimeter level positioning accuracy even under harsh GNSS observation conditions.
- 23 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-14
Enhancing PPP/INS Navigation by Tightly Integrating Visual Map Matching Based on Heterogeneous Road Markings
High-precision and robust positioning is crucial for ensuring safety and reliability of autonomous driving. The combination of precise point positioning (PPP) technology and inertial navigation system (INS) offers a globally available solution for continuous outdoor positioning. However, due to satellite signal degradation and error accumulation of low-cost INS, the positioning performance is challenged in complex urban environments. To address this issue, leveraging visual perception of specific prior map elements is an effective and applicable complementary approach. In this work, we tightly integrate visual map matching into PPP/INS navigation through a centralized extended Kalman filter (EKF). For map matching, heterogeneous road markings that structure urban roads are considered for constraint construction, whose observations are compactly modelled in 3D space and can be flexibly associated with the prior map. The complementary characteristics of map matching and PPP are fully exploited through tightly coupled integration, offering fast convergence, robustness against outliers, and sustained accuracy. The positioning performance and influencing factors of the proposed system are evaluated in both simulation and realistic urban road experiments. The results indicate that with the incorporation of map matching measurements, the proposed method exhibits superior performance in terms of accuracy and convergence, maintaining sub-decimeter to decimeter level positioning accuracy even under harsh GNSS observation conditions.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23, 13330-13342
GREAT Dataset: A Multi-Sensor Raw Observation Dataset for High-Precision Urban Navigation
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23, 13330-13342
GREAT Dataset: A Multi-Sensor Raw Observation Dataset for High-Precision Urban Navigation
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (1) , 767-778
Enhancing GNSS RTK Positioning Performance in Challenging Urban Environments With Prior Road Surface Map
High-precision global navigation satellite system (GNSS) positioning is critical for autonomous vehicles and intelligent transportation systems. However, it faces significant challenges in urban canyons and signal-obstructed environments, where multipath effects and poor satellite geometry lead to accuracy degradation. In such cases, additional auxiliary information is required. Existing map-aided localization methods either focus on meter-level positioning through road network matching or turning to high-definition (HD) maps with higher maintenance costs. To address this, we propose a lightweight system that constructs road surface maps using only vehicle trajectories and integrates the map information with GNSS real-time kinematic (RTK) to enhance positioning accuracy. Our method leverages geometric constraints by iteratively optimizing the distance from the GNSS antenna to the road surface, applying elevation priors to mitigate vertical uncertainty and improve horizontal accuracy simultaneously, which also enables online calibration of antenna height differences. Experiments were conducted in both controlled test field environments and complex urban road scenario. The results demonstrate notable improvements in positioning accuracy in both horizontal and vertical dimensions. In complex and challenging scenarios, the use of prior road surface constraints led to average improvements of 59.43% in horizontal precision and 89.70% in vertical precision. The proposed road surface map, with its compact data and crowdsourcing compatibility, offers a cost-effective solution for high-precision urban navigation without reliance on expensive HD maps or high-end sensors.
- 21 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (1) , 767-778
Enhancing GNSS RTK Positioning Performance in Challenging Urban Environments With Prior Road Surface Map
High-precision global navigation satellite system (GNSS) positioning is critical for autonomous vehicles and intelligent transportation systems. However, it faces significant challenges in urban canyons and signal-obstructed environments, where multipath effects and poor satellite geometry lead to accuracy degradation. In such cases, additional auxiliary information is required. Existing map-aided localization methods either focus on meter-level positioning through road network matching or turning to high-definition (HD) maps with higher maintenance costs. To address this, we propose a lightweight system that constructs road surface maps using only vehicle trajectories and integrates the map information with GNSS real-time kinematic (RTK) to enhance positioning accuracy. Our method leverages geometric constraints by iteratively optimizing the distance from the GNSS antenna to the road surface, applying elevation priors to mitigate vertical uncertainty and improve horizontal accuracy simultaneously, which also enables online calibration of antenna height differences. Experiments were conducted in both controlled test field environments and complex urban road scenario. The results demonstrate notable improvements in positioning accuracy in both horizontal and vertical dimensions. In complex and challenging scenarios, the use of prior road surface constraints led to average improvements of 59.43% in horizontal precision and 89.70% in vertical precision. The proposed road surface map, with its compact data and crowdsourcing compatibility, offers a cost-effective solution for high-precision urban navigation without reliance on expensive HD maps or high-end sensors.
- 13 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (3) , 2414-2425
SF-Loc: A Visual Mapping and Geo-Localization System Based on Sparse Visual Structure Frames
For high-level geo-spatial applications and intelligent robotics, accurate global pose information is of crucial importance. Map-aided localization is a generally applicable approach to overcome the limitations of global navigation satellite system (GNSS) in challenging environments. However, current solutions face challenges in terms of mapping efficiency, storage burden, and re-localization performance. In this work, we present SF-Loc, a lightweight visual mapping and map-aided localization system, which is built upon the image-based map representation with dense but compact depth, termed as visual structure frames. In the mapping phase, multisensor dense bundle adjustment (MS-DBA) with global optimization is applied to construct geo-referenced visual structure frames. Besides, a co-visibility-based mechanism is developed to achieve incremental mapping and keep the map sparsity. In the localization phase, coarse-to-fine vision-based localization is performed, in which multiframe information and the map distribution are fully leveraged. To be specific, spatiotemporally associated similarity (SAS) is proposed to overcome the place ambiguity, and pairwise frame matching is applied for robust pose estimation. Experimental results on the real-world cross-temporal dataset verify the effectiveness of the system. In complex urban road scenarios, the map size is down to 3 MB per kilometer and stable decimeter-level relocalization can be achieved.
- 13 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 31 (3) , 2414-2425
SF-Loc: A Visual Mapping and Geo-Localization System Based on Sparse Visual Structure Frames
For high-level geo-spatial applications and intelligent robotics, accurate global pose information is of crucial importance. Map-aided localization is a generally applicable approach to overcome the limitations of global navigation satellite system (GNSS) in challenging environments. However, current solutions face challenges in terms of mapping efficiency, storage burden, and re-localization performance. In this work, we present SF-Loc, a lightweight visual mapping and map-aided localization system, which is built upon the image-based map representation with dense but compact depth, termed as visual structure frames. In the mapping phase, multisensor dense bundle adjustment (MS-DBA) with global optimization is applied to construct geo-referenced visual structure frames. Besides, a co-visibility-based mechanism is developed to achieve incremental mapping and keep the map sparsity. In the localization phase, coarse-to-fine vision-based localization is performed, in which multiframe information and the map distribution are fully leveraged. To be specific, spatiotemporally associated similarity (SAS) is proposed to overcome the place ambiguity, and pairwise frame matching is applied for robust pose estimation. Experimental results on the real-world cross-temporal dataset verify the effectiveness of the system. In complex urban road scenarios, the map size is down to 3 MB per kilometer and stable decimeter-level relocalization can be achieved.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
MI-Odometry: Real-Time Attitude Estimation of Multiple IMUs With Online Spatiotemporal Calibration
Nowadays, micro-electromechanical systems (MEMS) Inertial Measurement Units (IMUs) have gained significant attention in both academia and industry areas due to the advanced development in circuit manufacturing technology. Benefiting from these technological advancements, it is natural to fuse multiple low-cost and miniaturized MEMS-IMUs to overcome the error accumulation of a single IMU. However, existing methods generally rely on known spatiotemporal parameters or specific assumptions. To fill this up, we propose a real-time attitude estimation method termed MI-Odometry that only uses randomly distributed IMUs. Meanwhile, a coarse-to-fine online calibration approach is also proposed to eliminate the need of exhaustive offline spatiotemporal calibration without using any prior knowledge. The proposed method is extensively evaluated in both simulation and real-world experiments to validate its effectiveness and superiority over state-of-the-art methods. The source code are available at https://github.com/GREAT-WHU/MI-Odom to benefit the research community.
- 3 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
MI-Odometry: Real-Time Attitude Estimation of Multiple IMUs With Online Spatiotemporal Calibration
Nowadays, micro-electromechanical systems (MEMS) Inertial Measurement Units (IMUs) have gained significant attention in both academia and industry areas due to the advanced development in circuit manufacturing technology. Benefiting from these technological advancements, it is natural to fuse multiple low-cost and miniaturized MEMS-IMUs to overcome the error accumulation of a single IMU. However, existing methods generally rely on known spatiotemporal parameters or specific assumptions. To fill this up, we propose a real-time attitude estimation method termed MI-Odometry that only uses randomly distributed IMUs. Meanwhile, a coarse-to-fine online calibration approach is also proposed to eliminate the need of exhaustive offline spatiotemporal calibration without using any prior knowledge. The proposed method is extensively evaluated in both simulation and real-world experiments to validate its effectiveness and superiority over state-of-the-art methods. The source code are available at https://github.com/GREAT-WHU/MI-Odom to benefit the research community.
- 17 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (23) , 50693-50707
Toward Centimeter-Level Positioning in Urban Environments With an Optimization-Based Tightly Coupled PPP-RTK/INS System
Precise position information plays a crucial role in industries such as intelligent autonomous systems and autonomous driving. Combining the advantages of traditional precise point positioning (PPP) and real-time kinematic (RTK) technologies, the emerging PPP-RTK technique is able to provide real-time centimeter-level positioning in open environments. However, its stability is often insufficient in complex environments due to frequent interference of satellite signals. To enhance the continuity and robustness of positioning results in such challenging environments, an inertial navigation system (INS), which can perceive the motion information of the carrier, is commonly integrated with a global navigation satellite system (GNSS). In this article, an optimization-based tightly coupled multi-GNSS PPP-RTK/INS system is proposed to achieve continuous and reliable positioning in urban environments. In the proposed algorithm, an estimator based on maximum a posteriori (MAP) estimation is utilized to integrate multi-GNSS raw observations, inertial measurements, and precise atmospheric information. Moreover, the outlier detection algorithm based on standardized residuals is applied in the proposed method to reject gross errors introduced by GNSS observations, making the positioning results more consistent with observations to get reliable ambiguity-float solutions. Then, a cascaded ambiguity resolution is conducted to obtain final, precise ambiguity-fixed solutions. The experimental results show that the proposed method achieves centimeter-level horizontal position estimates in urban environments, with an accuracy improvement of over 80% compared to PPP-RTK. Besides, the proposed optimization-based algorithm represents an accuracy improvement of approximately 30% compared to the traditional extended Kalman filter (EKF)-based method.
- 17 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (23) , 50693-50707
Toward Centimeter-Level Positioning in Urban Environments With an Optimization-Based Tightly Coupled PPP-RTK/INS System
Precise position information plays a crucial role in industries such as intelligent autonomous systems and autonomous driving. Combining the advantages of traditional precise point positioning (PPP) and real-time kinematic (RTK) technologies, the emerging PPP-RTK technique is able to provide real-time centimeter-level positioning in open environments. However, its stability is often insufficient in complex environments due to frequent interference of satellite signals. To enhance the continuity and robustness of positioning results in such challenging environments, an inertial navigation system (INS), which can perceive the motion information of the carrier, is commonly integrated with a global navigation satellite system (GNSS). In this article, an optimization-based tightly coupled multi-GNSS PPP-RTK/INS system is proposed to achieve continuous and reliable positioning in urban environments. In the proposed algorithm, an estimator based on maximum a posteriori (MAP) estimation is utilized to integrate multi-GNSS raw observations, inertial measurements, and precise atmospheric information. Moreover, the outlier detection algorithm based on standardized residuals is applied in the proposed method to reject gross errors introduced by GNSS observations, making the positioning results more consistent with observations to get reliable ambiguity-float solutions. Then, a cascaded ambiguity resolution is conducted to obtain final, precise ambiguity-fixed solutions. The experimental results show that the proposed method achieves centimeter-level horizontal position estimates in urban environments, with an accuracy improvement of over 80% compared to PPP-RTK. Besides, the proposed optimization-based algorithm represents an accuracy improvement of approximately 30% compared to the traditional extended Kalman filter (EKF)-based method.