Conglong Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Conglong Guo has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Tian Lan
Beijing Institute of Technology
4 shared publications - Xiaopeng Yang
Beijing Institute of Technology
3 shared publications - Dong Li
School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
2 shared publications - Junbo Gong
Beijing Institute of Technology
2 shared publications - Peng Yin
School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China
2 shared publications - Haoran Sun
Department of Electronic Engineering, Tsinghua University, Beijing, China
1 shared publication
Latest Publications
- 25 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
A State-Space-Model-Based Hyperbola Detection Method for Arbitrarily Long GPR B-Scan
The hyperbola detection in the ground-penetrating radar data is of real significance for subsurface object localization. However, present detection methods in GPR cannot process B-scan data with arbitrary length. In this letter, a hyperbola detection method based on state space model (SSM) for arbitrarily long GPR B-scan is proposed. The proposed method consists of three parts: a time dimension encoder based on ResNet block, a state space model module and a time dimension decoder based on the transposed convolution. Firstly, the time dimension encoder extracts high-dimensional time dimension signal features from each scan channel of B-scan data. Then, the state space model module extracts bidirectional correlation features along the survey line from the feature maps obtained in the first part, thereby obtaining feature maps containing hyperbolic target features. Finally, the time dimension decoder decodes the features obtained in the second part and outputs the probability map representing the target hyperbolic vertex region. Based on the probability map, the hyperbola detection and localization result can be obtained. The effectiveness of proposed method is verified by both simulation and field experiments GPR B-scan data. In addition, the experimental results show that the proposed method can achieve the AP with 96.9%. The code is available in https://github.com/yimaxwell/state-space-model-for-GPR-detection.git.
- 25 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
A State-Space-Model-Based Hyperbola Detection Method for Arbitrarily Long GPR B-Scan
The hyperbola detection in the ground-penetrating radar data is of real significance for subsurface object localization. However, present detection methods in GPR cannot process B-scan data with arbitrary length. In this letter, a hyperbola detection method based on state space model (SSM) for arbitrarily long GPR B-scan is proposed. The proposed method consists of three parts: a time dimension encoder based on ResNet block, a state space model module and a time dimension decoder based on the transposed convolution. Firstly, the time dimension encoder extracts high-dimensional time dimension signal features from each scan channel of B-scan data. Then, the state space model module extracts bidirectional correlation features along the survey line from the feature maps obtained in the first part, thereby obtaining feature maps containing hyperbolic target features. Finally, the time dimension decoder decodes the features obtained in the second part and outputs the probability map representing the target hyperbolic vertex region. Based on the probability map, the hyperbola detection and localization result can be obtained. The effectiveness of proposed method is verified by both simulation and field experiments GPR B-scan data. In addition, the experimental results show that the proposed method can achieve the AP with 96.9%. The code is available in https://github.com/yimaxwell/state-space-model-for-GPR-detection.git.
- Open Access
- 17 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 3917-3926
Subspace Projection Attention Network for GPR Heterogeneous Clutter Removal
Clutter removal in ground-penetrating radar (GPR) based on deep learning has been studied in recent years. However, existing methods are primarily designed for homogeneous background conditions and utilize only local spatial information via the convolution operation. In order to solve these issues, a subspace projection attention network is proposed for GPR heterogeneous clutter removal in this paper. Firstly, a heterogeneous concrete dataset based on a numerical model with randomly placed aggregates is constructed, which incorporates the complex electromagnetic propagation process accurately to improve the effectiveness for heterogeneous clutter removal. In addition, the Clutter Basis learning neural Network (CBNet) is designed by integrating the subspace projection attention (SPA) module into the skip connection paths of U-Net architecture. By learning the subspace basis vectors adaptively, the SPA exploits both local and global spatial information to extract target features precisely. At the same time, the feature maps are projected to the target subspace to remove heterogeneous clutter features. Finally, the performance and effectiveness of proposed method is validated by simulations and experiments.
- 17 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 17 (19391404) , 3917-3926
Open AccessSubspace Projection Attention Network for GPR Heterogeneous Clutter Removal
Clutter removal in ground-penetrating radar (GPR) based on deep learning has been studied in recent years. However, existing methods are primarily designed for homogeneous background conditions and utilize only local spatial information via the convolution operation. In order to solve these issues, a subspace projection attention network is proposed for GPR heterogeneous clutter removal in this paper. Firstly, a heterogeneous concrete dataset based on a numerical model with randomly placed aggregates is constructed, which incorporates the complex electromagnetic propagation process accurately to improve the effectiveness for heterogeneous clutter removal. In addition, the Clutter Basis learning neural Network (CBNet) is designed by integrating the subspace projection attention (SPA) module into the skip connection paths of U-Net architecture. By learning the subspace basis vectors adaptively, the SPA exploits both local and global spatial information to extract target features precisely. At the same time, the feature maps are projected to the target subspace to remove heterogeneous clutter features. Finally, the performance and effectiveness of proposed method is validated by simulations and experiments.
- 9 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-14
Layered Media Parameter Inversion Method Based on Deconvolution Autoencoder and Self-Attention Mechanism Using GPR Data
Layered medium parameter inversion is a crucial technique in ground-penetrating radar (GPR) data processing and has wide application in civil engineering and geological exploration. In response to the issues of high computational complexity and low accuracy associated with existing methods, a novel layered medium parameter inversion approach is proposed, comprising the deconvolution autoencoder and the parameter inversion network. First, the deconvolution autoencoder is introduced to solve the pulse response of layered medium systems in an unsupervised manner, which enhances the computational efficiency of deconvolution and decouples the data acquisition system from the supervised model. Subsequently, a parameter inversion network, including a self-attention module and a residual multilayer perceptron (MLP), is proposed to address the challenge posed by the excessively sparse pulse responses. The self-attention module calculates the autocorrelation of the pulse sequence, providing temporal delay information between pulses and reducing the sparsity of the pulse response to facilitate feature extraction. Meanwhile, the residual MLP, known for its low information loss and adaptability to different output dimensions, is employed for model-based and pixel-based inversions in situations with and without prior knowledge of the layer number, respectively. Finally, simulated and measured datasets are constructed to comprehensively train and evaluate the proposed method. The results demonstrate that the proposed method exhibits better performance of inversion accuracy, computational efficiency, robustness, generalization capability, and noise resistance. In addition, it remains applicable even when prior knowledge of the layer number is unknown.
- 9 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-14
Layered Media Parameter Inversion Method Based on Deconvolution Autoencoder and Self-Attention Mechanism Using GPR Data
Layered medium parameter inversion is a crucial technique in ground-penetrating radar (GPR) data processing and has wide application in civil engineering and geological exploration. In response to the issues of high computational complexity and low accuracy associated with existing methods, a novel layered medium parameter inversion approach is proposed, comprising the deconvolution autoencoder and the parameter inversion network. First, the deconvolution autoencoder is introduced to solve the pulse response of layered medium systems in an unsupervised manner, which enhances the computational efficiency of deconvolution and decouples the data acquisition system from the supervised model. Subsequently, a parameter inversion network, including a self-attention module and a residual multilayer perceptron (MLP), is proposed to address the challenge posed by the excessively sparse pulse responses. The self-attention module calculates the autocorrelation of the pulse sequence, providing temporal delay information between pulses and reducing the sparsity of the pulse response to facilitate feature extraction. Meanwhile, the residual MLP, known for its low information loss and adaptability to different output dimensions, is employed for model-based and pixel-based inversions in situations with and without prior knowledge of the layer number, respectively. Finally, simulated and measured datasets are constructed to comprehensively train and evaluate the proposed method. The results demonstrate that the proposed method exhibits better performance of inversion accuracy, computational efficiency, robustness, generalization capability, and noise resistance. In addition, it remains applicable even when prior knowledge of the layer number is unknown.
- 29 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 23 (2) , 873-877
Radius Inversion of Buried Elongated Metallic Cylinders Based on Electromagnetic Resonance Using Broadband Dual-Polarization Radar
In this letter, a radius inversion method of buried elongated metallic cylinders is proposed based on electromagnetic (EM) resonance using broadband dual-polarization radar, which could be used in applications related to EM inverse scattering and non-destructive tests. Firstly, by utilizing the angular complementarity of dual-polarization receiving signals, the influence on resonance properties due to the difference of cylinder's orientation and polarization direction is removed. Then, the simplified natural resonance frequencies are defined and used to extract the resonance properties from the broadband EM response. Finally, the radius is accurately inverted by establishing a least-squares relationship between the radius and the simplified natural resonance wavelengths. The effectiveness of the proposed method is validated by numerical simulations and laboratory experiments.
- 29 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Antennas and Wireless Propagation Letters
- Vol. 23 (2) , 873-877
Radius Inversion of Buried Elongated Metallic Cylinders Based on Electromagnetic Resonance Using Broadband Dual-Polarization Radar
In this letter, a radius inversion method of buried elongated metallic cylinders is proposed based on electromagnetic (EM) resonance using broadband dual-polarization radar, which could be used in applications related to EM inverse scattering and non-destructive tests. Firstly, by utilizing the angular complementarity of dual-polarization receiving signals, the influence on resonance properties due to the difference of cylinder's orientation and polarization direction is removed. Then, the simplified natural resonance frequencies are defined and used to extract the resonance properties from the broadband EM response. Finally, the radius is accurately inverted by establishing a least-squares relationship between the radius and the simplified natural resonance wavelengths. The effectiveness of the proposed method is validated by numerical simulations and laboratory experiments.