Haiguang Li
Haiguang Li has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Haoting Liu
University of Science and Technology
6 shared publications - Qing Li
University of Science and Technology Beijing
6 shared publications - Mengmeng Wang
Beijing Engineering Research Center of Industrial Spectrum Imaging, School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, China
3 shared publications - Xiaofei Lu
Jiuquan Satellite Launch Center, Jiuquan 732750, China
3 shared publications Fujie Tang
Uint, 63610, Korla, China
2 shared publications- Hui Zhao
Jiuquan Satellite Launch Center, China
2 shared publications
Latest Publications
- Open Access
- 8 November 2025
- Published by MDPI AG in Electronics
- Vol. 14 (22) , 4371
Target Localization of a Quadrotor UAV with Multi-Level Coordinate System Transformation Based on Monocular Camera Position Compensation
In recent years, unmanned aerial vehicle (UAV) technology has been increasingly widely used in natural disaster rescue. To enable fast and accurate localization of rescue targets in disaster environments, this paper proposes a multi-level coordinate system transformation method for quadrotor UAVs based on monocular camera position compensation. First, the preprocessed image object is transformed from pixel coordinates to camera coordinates. Second, to address the issue that coupling errors between the camera and UAV coordinate systems degrade the accuracy of coordinate conversion and target positioning, a Static–Dynamic Compensation Model (SDCM) for UAV camera position error is established. This model leverages a UAV attitude-based compensation mechanism to enable accurate conversion of camera coordinates to UAV coordinates and north-east-down (NED) coordinates. Finally, according to the Earth model, a multi-level continuous conversion chain from the target coordinates to the Earth-centered–Earth-fixed (ECEF) coordinates and the world-geodetic-system 1984 (WGS84) coordinates is constructed. Extensive experimental results show that the accuracy of the overall positioning method is improved by approximately 23.8% after completing our camera position compensation, which effectively enhances the positioning performance under the basic method of coordinate transformation, and provides technical support for the rapid rescue in the post-disaster phase.
- 8 November 2025
- Published by MDPI AG in Electronics
- Vol. 14 (22) , 4371
Open AccessTarget Localization of a Quadrotor UAV with Multi-Level Coordinate System Transformation Based on Monocular Camera Position Compensation
In recent years, unmanned aerial vehicle (UAV) technology has been increasingly widely used in natural disaster rescue. To enable fast and accurate localization of rescue targets in disaster environments, this paper proposes a multi-level coordinate system transformation method for quadrotor UAVs based on monocular camera position compensation. First, the preprocessed image object is transformed from pixel coordinates to camera coordinates. Second, to address the issue that coupling errors between the camera and UAV coordinate systems degrade the accuracy of coordinate conversion and target positioning, a Static–Dynamic Compensation Model (SDCM) for UAV camera position error is established. This model leverages a UAV attitude-based compensation mechanism to enable accurate conversion of camera coordinates to UAV coordinates and north-east-down (NED) coordinates. Finally, according to the Earth model, a multi-level continuous conversion chain from the target coordinates to the Earth-centered–Earth-fixed (ECEF) coordinates and the world-geodetic-system 1984 (WGS84) coordinates is constructed. Extensive experimental results show that the accuracy of the overall positioning method is improved by approximately 23.8% after completing our camera position compensation, which effectively enhances the positioning performance under the basic method of coordinate transformation, and provides technical support for the rapid rescue in the post-disaster phase.
- Open Access
Interactive Maintenance of Space Station Devices Using Scene Semantic Segmentation
A novel interactive maintenance method for space station in-orbit devices using scene semantic segmentation technology is proposed. First, a wearable and handheld system is designed to capture images from the astronaut in the space station’s front view scene and play these images on a handheld terminal in real-time. Second, the proposed system quantitatively evaluates the environmental lighting condition in the scene by calculating image quality evaluation parameters. If the lighting condition is not proper, a prompt message will be given to the astronaut to remind him or her to adjust the environment illumination. Third, our system adopts an improved DeepLabV3+ network for semantic segmentation of these astronauts’ forward view scene images. Regarding the improved network, the original backbone network is replaced with a lightweight convolutional neural network, i.e., the MobileNetV2, with a smaller model scale and computational complexity. The convolutional block attention module (CBAM) is introduced to improve the network’s feature perception ability. The atrous spatial pyramid pooling (ASPP) module is also considered to enable an accurate calculation of encoding multi-scale information. Extensive simulation experiment results indicate that the accuracy, precision, and average intersection over the union of the proposed algorithm can be better than 95.0%, 96.0%, and 89.0%, respectively. And the ground application experiments have also shown that our proposed technique can effectively shorten the working time of the system user.
Open AccessInteractive Maintenance of Space Station Devices Using Scene Semantic Segmentation
A novel interactive maintenance method for space station in-orbit devices using scene semantic segmentation technology is proposed. First, a wearable and handheld system is designed to capture images from the astronaut in the space station’s front view scene and play these images on a handheld terminal in real-time. Second, the proposed system quantitatively evaluates the environmental lighting condition in the scene by calculating image quality evaluation parameters. If the lighting condition is not proper, a prompt message will be given to the astronaut to remind him or her to adjust the environment illumination. Third, our system adopts an improved DeepLabV3+ network for semantic segmentation of these astronauts’ forward view scene images. Regarding the improved network, the original backbone network is replaced with a lightweight convolutional neural network, i.e., the MobileNetV2, with a smaller model scale and computational complexity. The convolutional block attention module (CBAM) is introduced to improve the network’s feature perception ability. The atrous spatial pyramid pooling (ASPP) module is also considered to enable an accurate calculation of encoding multi-scale information. Extensive simulation experiment results indicate that the accuracy, precision, and average intersection over the union of the proposed algorithm can be better than 95.0%, 96.0%, and 89.0%, respectively. And the ground application experiments have also shown that our proposed technique can effectively shorten the working time of the system user.
- Open Access
Small Scale Multi-Object Segmentation in Mid-Infrared Image Using the Image Timing Features–Gaussian Mixture Model and Convolutional-UNet
The application of intelligent video monitoring for natural resource protection and management has become increasingly common in recent years. To enhance safety monitoring during the grazing prohibition and rest period of grassland, this paper proposes a multi-object segmentation algorithm based on mid-infrared images for all-weather surveillance. The approach integrates the Image Timing Features–Gaussian Mixture Model (ITF-GMM) and Convolutional-UNet (Con-UNet) to improve the accuracy of target detection. First, a robust background modelling, i.e., the ITF-GMM, is proposed. Unlike the basic Gaussian Mixture Model (GMM), the proposed model dynamically adjusts the learning rate according to the content difference between adjacent frames and optimizes the number of Gaussian distributions through time series histogram analysis of pixels. Second, a segmentation framework based on Con-UNet is developed to improve the feature extraction ability of UNet. In this model, the maximum pooling layer is replaced with a convolutional layer, addressing the challenge of limited training data and improving the network’s ability to preserve spatial features. Finally, an integrated computation strategy is designed to combine the outputs of ITF-GMM and Con-UNet at the pixel level, and morphological operations are performed to refine the segmentation results and suppress noises, ensuring clearer object boundaries. The experimental results show the effectiveness of proposed approach, achieving a precision of 96.92%, an accuracy of 99.87%, an intersection over union (IOU) of 94.81%, and a recall of 97.75%. Furthermore, the proposed algorithm meets real-time processing requirements, confirming its capability to enhance small-target detection in complex outdoor environments and supporting the automation of grassland monitoring and enforcement.
Open AccessSmall Scale Multi-Object Segmentation in Mid-Infrared Image Using the Image Timing Features–Gaussian Mixture Model and Convolutional-UNet
The application of intelligent video monitoring for natural resource protection and management has become increasingly common in recent years. To enhance safety monitoring during the grazing prohibition and rest period of grassland, this paper proposes a multi-object segmentation algorithm based on mid-infrared images for all-weather surveillance. The approach integrates the Image Timing Features–Gaussian Mixture Model (ITF-GMM) and Convolutional-UNet (Con-UNet) to improve the accuracy of target detection. First, a robust background modelling, i.e., the ITF-GMM, is proposed. Unlike the basic Gaussian Mixture Model (GMM), the proposed model dynamically adjusts the learning rate according to the content difference between adjacent frames and optimizes the number of Gaussian distributions through time series histogram analysis of pixels. Second, a segmentation framework based on Con-UNet is developed to improve the feature extraction ability of UNet. In this model, the maximum pooling layer is replaced with a convolutional layer, addressing the challenge of limited training data and improving the network’s ability to preserve spatial features. Finally, an integrated computation strategy is designed to combine the outputs of ITF-GMM and Con-UNet at the pixel level, and morphological operations are performed to refine the segmentation results and suppress noises, ensuring clearer object boundaries. The experimental results show the effectiveness of proposed approach, achieving a precision of 96.92%, an accuracy of 99.87%, an intersection over union (IOU) of 94.81%, and a recall of 97.75%. Furthermore, the proposed algorithm meets real-time processing requirements, confirming its capability to enhance small-target detection in complex outdoor environments and supporting the automation of grassland monitoring and enforcement.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-15
Batch Processing for Enhanced InISAR Imaging of Space Targets
High-precision 3D reconstruction of satellites is critical for automatic target recognition (ATR). This paper introduces a batch processing-based method to enhance the performance of interferometric inverse synthetic aperture radar (InISAR) imaging. By utilizing the phase information within the inverse synthetic aperture radar (ISAR) image sequence, the main error components of height estimation are accurately estimated via the ordinary least squares (OLS) method. Additionally, an arc interval determination strategy for optimizing the batch processing performance is proposed. To ensure accurate phase unwrapping in challenging imaging scenarios, a phase unwrapping method based on the minimum standard deviation criterion is also proposed. Simulation experiments validate the effectiveness and superiority of the proposed algorithms. Compared with the traditional two-ISAR-image InISAR imaging method, the batch processing approach improves the precision of height estimation by approximately 50% with an arc length of approximately 15°.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-15
Batch Processing for Enhanced InISAR Imaging of Space Targets
High-precision 3D reconstruction of satellites is critical for automatic target recognition (ATR). This paper introduces a batch processing-based method to enhance the performance of interferometric inverse synthetic aperture radar (InISAR) imaging. By utilizing the phase information within the inverse synthetic aperture radar (ISAR) image sequence, the main error components of height estimation are accurately estimated via the ordinary least squares (OLS) method. Additionally, an arc interval determination strategy for optimizing the batch processing performance is proposed. To ensure accurate phase unwrapping in challenging imaging scenarios, a phase unwrapping method based on the minimum standard deviation criterion is also proposed. Simulation experiments validate the effectiveness and superiority of the proposed algorithms. Compared with the traditional two-ISAR-image InISAR imaging method, the batch processing approach improves the precision of height estimation by approximately 50% with an arc length of approximately 15°.
- 29 September 2024
- Published by Springer Nature
- p. 613-620
Research on Intelligent Applications of Metaverse Battlefield for Human-Computer Interaction
- 29 September 2024
- Published by Springer Nature
- p. 613-620
Research on Intelligent Applications of Metaverse Battlefield for Human-Computer Interaction
- Open Access
- 17 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 364-366
Development of a Picosecond Ultraviolet Light Source for Transient Radiation Time Response Testing of High-speed Cameras
We demonstrate a picosecond ultraviolet light source for transient radiation time response testing of high-speed cameras. The ultraviolet picosecond (ps) laser light with high output power was generated by the sum frequency of 1064 nm fundamental frequency light beam and 532 nm laser beam. A high quality La2CaB10O19 (LCB) nonlinear optical crystal cut along phase-matched directions with type I was applied. When the input power of homemade 1064 nm laser incident on LCB crystal was 74.8 W, the highest optical conversation efficiency was achieved at 31.95%. The highest laser power of 24.2 W operating at 355 nm was generated with 75.8 W 1064 nm ps pump laser beam (pulse width: 10 ps, repetition rate: 1 MHz), and the corresponding transfer efficiency was 31.93%.
- 17 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 364-366
Open AccessDevelopment of a Picosecond Ultraviolet Light Source for Transient Radiation Time Response Testing of High-speed Cameras
We demonstrate a picosecond ultraviolet light source for transient radiation time response testing of high-speed cameras. The ultraviolet picosecond (ps) laser light with high output power was generated by the sum frequency of 1064 nm fundamental frequency light beam and 532 nm laser beam. A high quality La2CaB10O19 (LCB) nonlinear optical crystal cut along phase-matched directions with type I was applied. When the input power of homemade 1064 nm laser incident on LCB crystal was 74.8 W, the highest optical conversation efficiency was achieved at 31.95%. The highest laser power of 24.2 W operating at 355 nm was generated with 75.8 W 1064 nm ps pump laser beam (pulse width: 10 ps, repetition rate: 1 MHz), and the corresponding transfer efficiency was 31.93%.
- Open Access
- 17 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 303-308
Light Radiation Source Segmentation in Sky Using Mean Adjustment OTSU
An image segmentation algorithm is proposed in this paper for the detection of light radiant source in sky. First, a mean adjustment-OTSU algorithm, i.e., MA-OTSU, is designed, which optimizes threshold selection using global grayscale mean to decrease the weight of pixel values close to the average grayscale. Second, pixel values greater than the threshold are preserved for histogram equalization, continuing with the MA-OTSU algorithm for segmentation until the threshold reaches zero. Third, the effectiveness of proposed algorithm is validated using two different scenes, considering factors such as ambient light and background complexity. Experimental results indicate that, compared to the classic OTSU method, the method proposed in this paper can produce higher quality segmentation results with fewer iterations.
- 17 May 2024
- Published by Association for Computing Machinery (ACM)
- p. 303-308
Open AccessLight Radiation Source Segmentation in Sky Using Mean Adjustment OTSU
An image segmentation algorithm is proposed in this paper for the detection of light radiant source in sky. First, a mean adjustment-OTSU algorithm, i.e., MA-OTSU, is designed, which optimizes threshold selection using global grayscale mean to decrease the weight of pixel values close to the average grayscale. Second, pixel values greater than the threshold are preserved for histogram equalization, continuing with the MA-OTSU algorithm for segmentation until the threshold reaches zero. Third, the effectiveness of proposed algorithm is validated using two different scenes, considering factors such as ambient light and background complexity. Experimental results indicate that, compared to the classic OTSU method, the method proposed in this paper can produce higher quality segmentation results with fewer iterations.
- Open Access
- 24 November 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (23) , 5484
Estimating the Observation Area of a Stripmap SAR via an ISAR Image Sequence
The stripmap mode is a basic and important mode for spaceborne synthetic aperture radars (SARs). Estimating the time-varying area observed by spaceborne SARs operating in stripmap mode is a practical but challenging field of research. In this article, we propose a novel method that parameterizes the time-varying area observed by the spaceborne SAR operating in the boresight stripmap mode into a fixed antenna attitude. Based on the principle of minimizing the dihedral angle between the plane containing the ideal estimated scatterers and the plane containing the actual parabolic antenna edge of a spaceborne SAR, an objective function is established for estimating the area observed by a spaceborne SAR operating in the boresight stripmap mode. Then, simulation experiments are designed to validate the feasibility and the robustness of the proposed method. The experimental simulation results show that the proposed method is feasible, and even under low signal-to-noise ratio (SNR) conditions of 10 dB, the proposed method still has good robustness.
- 24 November 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (23) , 5484
Open AccessEstimating the Observation Area of a Stripmap SAR via an ISAR Image Sequence
The stripmap mode is a basic and important mode for spaceborne synthetic aperture radars (SARs). Estimating the time-varying area observed by spaceborne SARs operating in stripmap mode is a practical but challenging field of research. In this article, we propose a novel method that parameterizes the time-varying area observed by the spaceborne SAR operating in the boresight stripmap mode into a fixed antenna attitude. Based on the principle of minimizing the dihedral angle between the plane containing the ideal estimated scatterers and the plane containing the actual parabolic antenna edge of a spaceborne SAR, an objective function is established for estimating the area observed by a spaceborne SAR operating in the boresight stripmap mode. Then, simulation experiments are designed to validate the feasibility and the robustness of the proposed method. The experimental simulation results show that the proposed method is feasible, and even under low signal-to-noise ratio (SNR) conditions of 10 dB, the proposed method still has good robustness.
- 19 January 2013
- Published by Springer Nature in Applied Intelligence
- Vol. 39 (4) , 793-804
A real-time transportation prediction system
- 19 January 2013
- Published by Springer Nature in Applied Intelligence
- Vol. 39 (4) , 793-804
A real-time transportation prediction system