Chenglin Cai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Chenglin Cai has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
HaiTao Wu
Chinese Academy of Sciences
4 shared publicationsXiaoHui Li
Chinese Academy of Sciences
4 shared publications- Zexian Li
School of Mathematics and Computational Science, Xiangtan University, Xiangtan, China
4 shared publications Zexian Li
School of Materials Science and Engineering, Xiangtan University, Xiangtan, China
3 shared publicationsDongbo Zhang
School of Automation and Electronic Information, Xiangtan University, Xiangtan, China
2 shared publications- Feng Yin
College of Automation and Electronic Information, Xiangtan University, Xiangtan, China
2 shared publications
Latest Publications
- Open Access
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 13348-13358
Regional Tropospheric Delay Prediction Model Based on LSTM-Enhanced Encoder Network
Precise modeling of Zenith Tropospheric Delay (ZTD) is essential for real-time high-precision positioning in global navigation satellite systems (GNSS). Due to the stochastic variability of atmospheric water vapor across different regions, tropospheric delay exhibits strong regional characteristics. Empirical tropospheric delay models built on reanalysis of meteorological data often show significant accuracy discrepancies across regions, failing to meet the needs for precise regional ZTD forecasting. Deep learning methods excel in learning complex patterns and dependencies from time series data. Our study utilized ZTD data from 178 NGL stations in Australia during 2023 as ground truth values and modeled them using an LSTM-Enhanced encoder network. This model incorporated both spatial and temporal information as well as correlations with GPT3 ZTD. Predictions were compared with those from GPT3 ZTD, ERA5 ZTD, ANN ZTD, GRNN ZTD and LSTM ZTD. The results showed that the LSTM-Enhanced encoder ZTD achieved an RMSE of 14.43 mm, a mean bias close to zero, with mean absolute error and mean correlation coefficient of 12.42 mm and 0.95, respectively. The proposed model outperforms the GPT3, ERA5, ANN, GRNN, and LSTM models, with respective RMSE improvements of approximately 62.3%, 12.3%, 61%, 59.9%, and 60%. In addition, we compared the spatial and temporal properties of the proposed model with those of the GPT3 model and the ERA5 model. The discussion section further analyzed the prediction performance of different neural network approaches under different prediction periods.
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 18 (19391404) , 13348-13358
Open AccessRegional Tropospheric Delay Prediction Model Based on LSTM-Enhanced Encoder Network
Precise modeling of Zenith Tropospheric Delay (ZTD) is essential for real-time high-precision positioning in global navigation satellite systems (GNSS). Due to the stochastic variability of atmospheric water vapor across different regions, tropospheric delay exhibits strong regional characteristics. Empirical tropospheric delay models built on reanalysis of meteorological data often show significant accuracy discrepancies across regions, failing to meet the needs for precise regional ZTD forecasting. Deep learning methods excel in learning complex patterns and dependencies from time series data. Our study utilized ZTD data from 178 NGL stations in Australia during 2023 as ground truth values and modeled them using an LSTM-Enhanced encoder network. This model incorporated both spatial and temporal information as well as correlations with GPT3 ZTD. Predictions were compared with those from GPT3 ZTD, ERA5 ZTD, ANN ZTD, GRNN ZTD and LSTM ZTD. The results showed that the LSTM-Enhanced encoder ZTD achieved an RMSE of 14.43 mm, a mean bias close to zero, with mean absolute error and mean correlation coefficient of 12.42 mm and 0.95, respectively. The proposed model outperforms the GPT3, ERA5, ANN, GRNN, and LSTM models, with respective RMSE improvements of approximately 62.3%, 12.3%, 61%, 59.9%, and 60%. In addition, we compared the spatial and temporal properties of the proposed model with those of the GPT3 model and the ERA5 model. The discussion section further analyzed the prediction performance of different neural network approaches under different prediction periods.
- Open Access
- 10 July 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1
Author Correction: A static precise single-point positioning method based on carrier phase zero-baseline self-differencing
- 10 July 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1
Open AccessAuthor Correction: A static precise single-point positioning method based on carrier phase zero-baseline self-differencing
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-9
Lightweight Segmentation Neural Networks for Measuring Vickers Hardness
The automatic measurement algorithm for Vickers hardness indentation has been widely applied. Among these, the neural network-based method has received attention for its excellent segmentation performance. However, high storage space and computation requirements hinder its promotion on edge computing devices. To address this issue, this study proposes two lightweight Vickers indentation segmentation networks: VSNLite4M and VSNLite1M. Compared with previous methods, the proposed networks achieve a reduction of$35.2\times $ in terms of computational cost with up to$38\times $ fewer parameters, while maintaining the same level of segmentation accuracy.- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-9
Lightweight Segmentation Neural Networks for Measuring Vickers Hardness
The automatic measurement algorithm for Vickers hardness indentation has been widely applied. Among these, the neural network-based method has received attention for its excellent segmentation performance. However, high storage space and computation requirements hinder its promotion on edge computing devices. To address this issue, this study proposes two lightweight Vickers indentation segmentation networks: VSNLite4M and VSNLite1M. Compared with previous methods, the proposed networks achieve a reduction of$35.2\times $ in terms of computational cost with up to$38\times $ fewer parameters, while maintaining the same level of segmentation accuracy.- 2 December 2023
- Published by Taylor & Francis in Remote Sensing Letters
- Vol. 14 (12) , 1357-1367
A robust and adaptable high-precision method for matching flipped SAR images based on an oriented descriptor
- 2 December 2023
- Published by Taylor & Francis in Remote Sensing Letters
- Vol. 14 (12) , 1357-1367
A robust and adaptable high-precision method for matching flipped SAR images based on an oriented descriptor
- Open Access
- 14 July 2023
- Published by Darcy & Roy Press Co. Ltd. in Highlights in Science, Engineering and Technology
- Vol. 56, 590-595
A model for converging tropospheric delay corrections
In response to the current problem that tropo-spheric delay correction is constrained by the measured meteorological parameters, resulting in low efficiency and limited application, this paper proposes a GE-Sa fusion model combining GPT2w and EGNOS models. The algorithm provides high-precision meteorological data through GPT2w and EGNOS models, and uses the Saastamoinen model to achieve the zenith tropospheric delay (ZTD) correction, the ZTD series of 2017 from 20 stations acquired by the Global Geodetic Observing System (GGOS) Atmosphere product data were used as the standard approximation to calculate the bias and RMS values of the model respectively, and the experimental results showed that the accuracy of the GE-Sa model was higher than that of the EGNOS model, GPT2w+Saastamoinen model, and 68.12% and 16.33%, respectively. The model improves the accuracy of calculating ZTD and expands the scope of application while getting rid of the limitation of measured meteorological parameters.
- 14 July 2023
- Published by Darcy & Roy Press Co. Ltd. in Highlights in Science, Engineering and Technology
- Vol. 56, 590-595
Open AccessA model for converging tropospheric delay corrections
In response to the current problem that tropo-spheric delay correction is constrained by the measured meteorological parameters, resulting in low efficiency and limited application, this paper proposes a GE-Sa fusion model combining GPT2w and EGNOS models. The algorithm provides high-precision meteorological data through GPT2w and EGNOS models, and uses the Saastamoinen model to achieve the zenith tropospheric delay (ZTD) correction, the ZTD series of 2017 from 20 stations acquired by the Global Geodetic Observing System (GGOS) Atmosphere product data were used as the standard approximation to calculate the bias and RMS values of the model respectively, and the experimental results showed that the accuracy of the GE-Sa model was higher than that of the EGNOS model, GPT2w+Saastamoinen model, and 68.12% and 16.33%, respectively. The model improves the accuracy of calculating ZTD and expands the scope of application while getting rid of the limitation of measured meteorological parameters.
- Open Access
- 14 July 2023
- Published by Darcy & Roy Press Co. Ltd. in Highlights in Science, Engineering and Technology
- Vol. 56, 596-602
Cycle Slip Detection By Combining TECR And Reconstructed Doppler Integral Method
Poor observation environment and other factors lead to the whole cycle slips of carrier phase observation value, which affects the positioning accuracy. There are detection loopholes in the traditional cycle slips detection methods, especially the small value cycle slips, equivalent cycle slips and special value cycle slips are difficult to detect. A method combining Total Electron Contents Rate (TECR) and Doppler Value Reconstruction is proposed to solve the deficiency of cycle slip detection. Based on Doppler observations and Doppler detection method, the Doppler observations are reconstructed. This method improves the accuracy of Doppler observations. The proposed method has been verified that the reconstructed Doppler observations can improve the detection accuracy of small cycle slips, and can accurately detect any large value, small value of 1 cycle, Both frequency equivalent cycle slips and special value cycle slips can be accurately detected.
- 14 July 2023
- Published by Darcy & Roy Press Co. Ltd. in Highlights in Science, Engineering and Technology
- Vol. 56, 596-602
Open AccessCycle Slip Detection By Combining TECR And Reconstructed Doppler Integral Method
Poor observation environment and other factors lead to the whole cycle slips of carrier phase observation value, which affects the positioning accuracy. There are detection loopholes in the traditional cycle slips detection methods, especially the small value cycle slips, equivalent cycle slips and special value cycle slips are difficult to detect. A method combining Total Electron Contents Rate (TECR) and Doppler Value Reconstruction is proposed to solve the deficiency of cycle slip detection. Based on Doppler observations and Doppler detection method, the Doppler observations are reconstructed. This method improves the accuracy of Doppler observations. The proposed method has been verified that the reconstructed Doppler observations can improve the detection accuracy of small cycle slips, and can accurately detect any large value, small value of 1 cycle, Both frequency equivalent cycle slips and special value cycle slips can be accurately detected.
- Open Access
- 28 December 2022
- Published by MYU K.K. in Sensors and Materials
- Vol. 34 (12) , 4705-4715
Rapid Subpixel Matching Method for Spaceborne Synthetic Aperture Radar Images
- 28 December 2022
- Published by MYU K.K. in Sensors and Materials
- Vol. 34 (12) , 4705-4715
Open AccessRapid Subpixel Matching Method for Spaceborne Synthetic Aperture Radar Images
- 9 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. PP (00189456) , 1
Automatic Vickers hardness measurement with neural network segmentation
The Vickers hardness test is widely used for metal materials. The hardness given by the test is inversely proportional to the ratio of the test force to the indentation area. Since it is inconvenient to measure the area of the indentation manually, it is usually approximated by measuring its diagonal length. On this basis, we propose a new indentation segmentation network based on existing work. Taking advantage of its high segmentation accuracy, we use the indentation area to calculate the Vickers hardness directly, rather than relying on the measurement of the diagonal length. Experimental results show that the indentation areas obtained by this method are well below the ISO standard and very close to those from manual measurements. In some cases, this method can be a good alternative to manual measurements.
- 9 December 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. PP (00189456) , 1
Automatic Vickers hardness measurement with neural network segmentation
The Vickers hardness test is widely used for metal materials. The hardness given by the test is inversely proportional to the ratio of the test force to the indentation area. Since it is inconvenient to measure the area of the indentation manually, it is usually approximated by measuring its diagonal length. On this basis, we propose a new indentation segmentation network based on existing work. Taking advantage of its high segmentation accuracy, we use the indentation area to calculate the Vickers hardness directly, rather than relying on the measurement of the diagonal length. Experimental results show that the indentation areas obtained by this method are well below the ISO standard and very close to those from manual measurements. In some cases, this method can be a good alternative to manual measurements.
- Open Access
Geometric Self-Calibration of YaoGan-13 Images Using Multiple Overlapping Images
Geometric calibration is an important means of improving the absolute positioning accuracy of space-borne synthetic aperture radar imagery. The conventional calibration method is based on a calibration field, which is simple and convenient, but requires a great deal of manpower and material resources to obtain ground control points. Although newer cross-calibration methods do not require ground control points, calibration accuracy still depends on a periodically updated reference image. Accordingly, this study proposes a geometric self-calibration method based on the positioning consistency constraint of conjugate image points to provide rapid and accurate calibration of the YaoGan-13 satellite. The proposed method can accurately calibrate geometric parameters without requiring ground control points or high-precision reference images. To verify the absolute positioning accuracy obtained using the proposed self-calibration method, YaoGan-13 Stripmap images of multiple regions were collected and evaluated. The results indicate that high-accuracy absolute positioning can be achieved with a plane accuracy of 3.83 m or better for Stripmap data, without regarding elevation error. Compared to the conventional calibration method using high-accuracy control data, the difference between the two methods is only about 2.53 m, less than the 3-m resolution of the image, verifying the effectiveness of the proposed self-calibration method.
Open AccessGeometric Self-Calibration of YaoGan-13 Images Using Multiple Overlapping Images
Geometric calibration is an important means of improving the absolute positioning accuracy of space-borne synthetic aperture radar imagery. The conventional calibration method is based on a calibration field, which is simple and convenient, but requires a great deal of manpower and material resources to obtain ground control points. Although newer cross-calibration methods do not require ground control points, calibration accuracy still depends on a periodically updated reference image. Accordingly, this study proposes a geometric self-calibration method based on the positioning consistency constraint of conjugate image points to provide rapid and accurate calibration of the YaoGan-13 satellite. The proposed method can accurately calibrate geometric parameters without requiring ground control points or high-precision reference images. To verify the absolute positioning accuracy obtained using the proposed self-calibration method, YaoGan-13 Stripmap images of multiple regions were collected and evaluated. The results indicate that high-accuracy absolute positioning can be achieved with a plane accuracy of 3.83 m or better for Stripmap data, without regarding elevation error. Compared to the conventional calibration method using high-accuracy control data, the difference between the two methods is only about 2.53 m, less than the 3-m resolution of the image, verifying the effectiveness of the proposed self-calibration method.