Xiayang Xiao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiayang Xiao has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Haipeng Wang
Fudan University
7 shared publications - Penghao Xiao
Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai, China
3 shared publications Zhuoxuan Li
Fudan University, Shanghai, China
2 shared publications- Binze Hu
Fudan University, Shanghai, China
1 shared publication Chunjie Zhang
Key Laboratory for Information Science of Electromagnetic Waves (MoE), Fudan University, Shanghai, China
1 shared publication- Chunzhuo Fan
Beijing Remote Sensing Information Institute, Beijing, China
1 shared publication
Latest Publications
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 74 (7) , 7038-7052
PGRA: Physics-Guided Rotation Adaptive Attention for Few-Shot SAR Target Recognition
Synthetic Aperture Radar target recognition under few-shot conditions presents significant challenges due to azimuth sensitivity, insufficient utilization of physical priors, and limited generalization capability. To address these issues, this study proposes a novel Physics Guided Rotation Adaptive Attention mechanism that integrates electromagnetic scattering priors with rotation-equivariant attention modeling. The proposed PGRA consists of three key components: 1) Channel Interdependency Dynamic Encoder that purifies and recalibrates feature channels, 2) Multi-angle Rotation-Equivariant Encoder that constructs dual feature branches for image-driven and ASC-based physical representation using a rotational convolutional layer, and 3) Gated Physics-Semantic Modulator that aligns and fuses features across modalities through cross-attention and adaptive gating. By explicitly encoding rotation-aware responses and embedding physically interpretable structures, PGRA enhances both robustness and semantic discriminability in low-sample regimes. Experimental results on the MSTAR and SAR-UAV datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods, achieving up to 10.69% accuracy improvement under the OFA-3 few-shot setting while maintaining strong generalization under cross-view conditions. The source code used in this study is publicly available at: https://github.com/waluef/PGRA.
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 74 (7) , 7038-7052
PGRA: Physics-Guided Rotation Adaptive Attention for Few-Shot SAR Target Recognition
Synthetic Aperture Radar target recognition under few-shot conditions presents significant challenges due to azimuth sensitivity, insufficient utilization of physical priors, and limited generalization capability. To address these issues, this study proposes a novel Physics Guided Rotation Adaptive Attention mechanism that integrates electromagnetic scattering priors with rotation-equivariant attention modeling. The proposed PGRA consists of three key components: 1) Channel Interdependency Dynamic Encoder that purifies and recalibrates feature channels, 2) Multi-angle Rotation-Equivariant Encoder that constructs dual feature branches for image-driven and ASC-based physical representation using a rotational convolutional layer, and 3) Gated Physics-Semantic Modulator that aligns and fuses features across modalities through cross-attention and adaptive gating. By explicitly encoding rotation-aware responses and embedding physically interpretable structures, PGRA enhances both robustness and semantic discriminability in low-sample regimes. Experimental results on the MSTAR and SAR-UAV datasets demonstrate that our approach significantly outperforms existing state-of-the-art methods, achieving up to 10.69% accuracy improvement under the OFA-3 few-shot setting while maintaining strong generalization under cross-view conditions. The source code used in this study is publicly available at: https://github.com/waluef/PGRA.
- 21 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. PP (00189251) , 1-16
Reciprocal Point Learning Network with Large Electromagnetic Kernel for SAR Open-Set Recognition
The limitations of existing Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) methods lie in their confinement by the closed-environment assumption, hindering their effective and robust handling of unknown target categories in open environments. Open Set Recognition (OSR), a pivotal facet for algorithmic practicality, intends to categorize known classes while denoting unknown ones as “unknown.” The chief challenge in OSR is to mitigate risks associated with numerous unknown samples within the open space. To enhance open-set SAR classification, a method called scattering kernel with reciprocal learning network is proposed. Initially, a feature representing paradigm is constructed on the base of reciprocal point learning (RPL), establishing a bounded space for potential unknown classes. This approach indirectly introduces unknown information into a learner confined to known classes, thereby acquiring more concise and discriminative representations. Subsequently, considering the variability in the imaging of targets at different angles and the discreteness of components in SAR images, a proposal is made to design large-sized convolutional kernels based on attribute scattering center (ASC) models. This enhances the ability to extract intrinsic non-linear features and specific scattering characteristics in SAR images, thereby improving the discriminative features of the model and mitigating the impact of imaging variations on classification performance. Experiments conducted on the public datasets substantiate the superior performance of this approach called ASC-RPL over mainstream methods.
- 21 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. PP (00189251) , 1-16
Reciprocal Point Learning Network with Large Electromagnetic Kernel for SAR Open-Set Recognition
The limitations of existing Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) methods lie in their confinement by the closed-environment assumption, hindering their effective and robust handling of unknown target categories in open environments. Open Set Recognition (OSR), a pivotal facet for algorithmic practicality, intends to categorize known classes while denoting unknown ones as “unknown.” The chief challenge in OSR is to mitigate risks associated with numerous unknown samples within the open space. To enhance open-set SAR classification, a method called scattering kernel with reciprocal learning network is proposed. Initially, a feature representing paradigm is constructed on the base of reciprocal point learning (RPL), establishing a bounded space for potential unknown classes. This approach indirectly introduces unknown information into a learner confined to known classes, thereby acquiring more concise and discriminative representations. Subsequently, considering the variability in the imaging of targets at different angles and the discreteness of components in SAR images, a proposal is made to design large-sized convolutional kernels based on attribute scattering center (ASC) models. This enhances the ability to extract intrinsic non-linear features and specific scattering characteristics in SAR images, thereby improving the discriminative features of the model and mitigating the impact of imaging variations on classification performance. Experiments conducted on the public datasets substantiate the superior performance of this approach called ASC-RPL over mainstream methods.
- 14 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Scattering Guided Image Despeckling: A Score-Based Diffusion Approach in Frequency Domain
When it comes to deep-learning-based methods for despeckling synthetic aperture radar (SAR) images, maintaining spatial structure, ensuring process stability, and achieving fast inference are still major challenges. To address these issues, a novel method named scattering guided image despeckling (SGID), which is based on the wavelet—transform—conditioned diffusion model for SAR despeckling, has been proposed. First, the core component of this approach is the adaptive scattering extraction module (ASEM), which is designed to preserve the spatial structure of images effectively. It achieves the preservation of spatial structure by leveraging SAR imaging principles to adaptively extract scattering points, thereby retaining critical spatial information. Second, considering that speckle noise in SAR images is mainly concentrated in the high-frequency region, this study has designed a high-frequency despeckling module (HFDM). This module adopts a direction-aware adaptive weight allocation strategy, aiming to precisely regulate the weight allocation of high-frequency components in all the directions during the processing, so as to maximize the coherence and consistency of the high-frequency detail structures in the images. Finally, the entire processing workflow is conducted in the frequency domain, which contributes significantly to the improvement of inference speed. Experimental results demonstrate that the proposed method achieves state-of-the-art (SOTA) performance in both spatial structure preservation and despeckling quality. Besides, its inference speed is 0.19 s, which is 67 times faster than that of comparable diffusion-model-based methods. The code for this study will be publicly available at https://github.com/SihaoDong/SGID.
- 14 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 22 (1545598X) , 1-5
Scattering Guided Image Despeckling: A Score-Based Diffusion Approach in Frequency Domain
When it comes to deep-learning-based methods for despeckling synthetic aperture radar (SAR) images, maintaining spatial structure, ensuring process stability, and achieving fast inference are still major challenges. To address these issues, a novel method named scattering guided image despeckling (SGID), which is based on the wavelet—transform—conditioned diffusion model for SAR despeckling, has been proposed. First, the core component of this approach is the adaptive scattering extraction module (ASEM), which is designed to preserve the spatial structure of images effectively. It achieves the preservation of spatial structure by leveraging SAR imaging principles to adaptively extract scattering points, thereby retaining critical spatial information. Second, considering that speckle noise in SAR images is mainly concentrated in the high-frequency region, this study has designed a high-frequency despeckling module (HFDM). This module adopts a direction-aware adaptive weight allocation strategy, aiming to precisely regulate the weight allocation of high-frequency components in all the directions during the processing, so as to maximize the coherence and consistency of the high-frequency detail structures in the images. Finally, the entire processing workflow is conducted in the frequency domain, which contributes significantly to the improvement of inference speed. Experimental results demonstrate that the proposed method achieves state-of-the-art (SOTA) performance in both spatial structure preservation and despeckling quality. Besides, its inference speed is 0.19 s, which is 67 times faster than that of comparable diffusion-model-based methods. The code for this study will be publicly available at https://github.com/SihaoDong/SGID.
- Open Access
- 25 December 2024
- 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) , 3071-3086
OSAD: Open-Set Aircraft Detection in SAR Images
Current mainstream SAR image object detection methods still lack robustness when dealing with unknown objects in open environments. Open-set detection aims to enable detectors trained on a closed set to detect all known objects and identify unknown objects in open-set environments. The key challenges are how to improve the generalization to potential unknown objects and reduce the empirical classification risk of known categories under strong supervision. To address these challenges, a novel open-set aircraft detector for SAR images is proposed, named Open-Set Aircraft Detection (OSAD), which is equipped with three dedicated components: global context modeling (GCM), location quality-driven pseudo labeling generation (LPG), and prototype contrastive learning (PCL). GCM effectively enhances the network's representation of objects by attention maps which are formed by capturing of long sequential positional relationships. LPG leverages clues about object positions and shapes to optimize localization quality, avoiding overfitting to known category information and enhancing generalization to potential unknown objects. PCL employs prototype-based contrastive encoding loss to promote instance-level intra-class compactness and inter-class variance, aiming to minimize the overlap between known and unknown distributions and reduce the empirical classification risk of known categories. Extensive experiments have demonstrated that the proposed method can effectively detect unknown objects and exhibit competitive performance without compromising closed-set performance. The highest absolute gain which ranges from 0 to 18.36% can be achieved on the average precision of unknown objects.
- 25 December 2024
- 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) , 3071-3086
Open AccessOSAD: Open-Set Aircraft Detection in SAR Images
Current mainstream SAR image object detection methods still lack robustness when dealing with unknown objects in open environments. Open-set detection aims to enable detectors trained on a closed set to detect all known objects and identify unknown objects in open-set environments. The key challenges are how to improve the generalization to potential unknown objects and reduce the empirical classification risk of known categories under strong supervision. To address these challenges, a novel open-set aircraft detector for SAR images is proposed, named Open-Set Aircraft Detection (OSAD), which is equipped with three dedicated components: global context modeling (GCM), location quality-driven pseudo labeling generation (LPG), and prototype contrastive learning (PCL). GCM effectively enhances the network's representation of objects by attention maps which are formed by capturing of long sequential positional relationships. LPG leverages clues about object positions and shapes to optimize localization quality, avoiding overfitting to known category information and enhancing generalization to potential unknown objects. PCL employs prototype-based contrastive encoding loss to promote instance-level intra-class compactness and inter-class variance, aiming to minimize the overlap between known and unknown distributions and reduce the empirical classification risk of known categories. Extensive experiments have demonstrated that the proposed method can effectively detect unknown objects and exhibit competitive performance without compromising closed-set performance. The highest absolute gain which ranges from 0 to 18.36% can be achieved on the average precision of unknown objects.
- Open Access
- 30 August 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) , 15862-15884
Neural Networks Integer Computation: Quantizing Convolutional Neural Networks of Inference and Training for Object Detection in Embedded Systems
Deep neural networks (DNNs) have evolved to be the state-of-the-art technique for machine learning tasks. However, their high computational demands make them difficult to deploy on embedded devices with limited hardware resources and strict power budgets. Most embedded systems perform better with 8-bit data processing, prompting extensive research into 8-bit network quantization to enable faster inference. This paper aims to propose a unified 8-bit inference and training framework to support object detection tasks, striving to balance accuracy and speed for conventional convolutional neural networks (CNNs). Initially, this paper establishes a unified full int8 post-training quantization (PTQ) method using KL_divergence to evaluate the range of parameter distributions and thresholds before and after quantization. This method effectively addresses the quantization issues commonly found in networks with linear activations. For networks with nonlinear activations, this paper introduces a hybrid precision post-training quantization (H-PTQ) method that utilizes hybrid precision to perform forward inference, thereby mitigating quantization errors caused by nonlinear activation functions. Furthermore, quantization-aware training (QAT) typically employs the straight-through estimator (STE) for backward propagation of gradients through the quantization function. However, since STE is an approximate computation, this paper proposes an alternative called $\alpha$ -quantization-aware training ( $\alpha$ -QAT). This method replaces the quantized weights in the loss function with affine combinations of the quantized and full-precision weights, enabling more precise forward and backward propagation to fine-tune the errors introduced by quantization. Finally, this paper conducted evaluations of quantized networks on ARM platforms and performed experiments across multiple datasets. The results indicate that the proposed PTQ, H-PTQ, and $\alpha$ -QAT methods achieved maximum accelerations of 4x, 2.3x, and 3.9x, respectively. Additionally, these methods significantly reduced memory overhead by up to 57.11%, 43.16%, and 91.94%, and achieved model compression rates of up to 51.52%, 48.48%, and 49.70%.
- 30 August 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) , 15862-15884
Open AccessNeural Networks Integer Computation: Quantizing Convolutional Neural Networks of Inference and Training for Object Detection in Embedded Systems
Deep neural networks (DNNs) have evolved to be the state-of-the-art technique for machine learning tasks. However, their high computational demands make them difficult to deploy on embedded devices with limited hardware resources and strict power budgets. Most embedded systems perform better with 8-bit data processing, prompting extensive research into 8-bit network quantization to enable faster inference. This paper aims to propose a unified 8-bit inference and training framework to support object detection tasks, striving to balance accuracy and speed for conventional convolutional neural networks (CNNs). Initially, this paper establishes a unified full int8 post-training quantization (PTQ) method using KL_divergence to evaluate the range of parameter distributions and thresholds before and after quantization. This method effectively addresses the quantization issues commonly found in networks with linear activations. For networks with nonlinear activations, this paper introduces a hybrid precision post-training quantization (H-PTQ) method that utilizes hybrid precision to perform forward inference, thereby mitigating quantization errors caused by nonlinear activation functions. Furthermore, quantization-aware training (QAT) typically employs the straight-through estimator (STE) for backward propagation of gradients through the quantization function. However, since STE is an approximate computation, this paper proposes an alternative called $\alpha$ -quantization-aware training ( $\alpha$ -QAT). This method replaces the quantized weights in the loss function with affine combinations of the quantized and full-precision weights, enabling more precise forward and backward propagation to fine-tune the errors introduced by quantization. Finally, this paper conducted evaluations of quantized networks on ARM platforms and performed experiments across multiple datasets. The results indicate that the proposed PTQ, H-PTQ, and $\alpha$ -QAT methods achieved maximum accelerations of 4x, 2.3x, and 3.9x, respectively. Additionally, these methods significantly reduced memory overhead by up to 57.11%, 43.16%, and 91.94%, and achieved model compression rates of up to 51.52%, 48.48%, and 49.70%.
- 15 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (2) , 1722-1739
Aircraft Detection and Classification Based on Joint Probability Detector Integrated With Scattering Attention
Synthetic aperture radar (SAR) image intelligence interpretation is always a challenging task due to its special imaging mechanism. This paper focuses on the aircraft detection and recognition in large-scale SAR images. The objects in large-size SAR images are usually sparsely distributed and tend to be highly concentrated in certain areas. Therefore, the detection and classification in SAR images are affected easily by imaging environment, leading to ineffective and instability. It suffers from time-consuming, high false-alarm rate, and low recognition rate. To alleviate these problems, a joint probability detector (JPD) integrated with scattering attention (SA) is designed for aircraft detection and classification. Based on the fact that all aircraft are parked in the airport area, an airport detection method with mixed strategy (ADMS) is proposed to obtain the valid region (airport), narrowing downing the scope of detection area, increasing the detection efficiency as well as suppressing a lot of false alarms outside the airport. Considering that it's easy to generate false alarms within the airport on account of clutter scattering interference, a two-stage detector is introduced to improve the accuracy by replacing a stronger region proposal network (RPN) and optimizing a lower bound to a joint probabilistic objective over two stages. Furthermore, the classification encoder module incorporates scattering attention into convolution neural network to leverage the distribution relation among strong scattered points to enhance the classification performance. Finally, extensive experiments on the ZKXT and GaoFen-3 datasets verify the effectiveness and superiority of the proposed approach, and surpass runner up by 5.3% with mF1 indicator. On a large GaoFen3 image (16550× 11945 pixels), the proposed method improves the detection speed by 187.52%, without sacrificing the accuracy. More importantly, the proposed method has been applied to the SAR image interpretation and achieved the expected effect in the actual application.
- 15 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Aerospace and Electronic Systems
- Vol. 60 (2) , 1722-1739
Aircraft Detection and Classification Based on Joint Probability Detector Integrated With Scattering Attention
Synthetic aperture radar (SAR) image intelligence interpretation is always a challenging task due to its special imaging mechanism. This paper focuses on the aircraft detection and recognition in large-scale SAR images. The objects in large-size SAR images are usually sparsely distributed and tend to be highly concentrated in certain areas. Therefore, the detection and classification in SAR images are affected easily by imaging environment, leading to ineffective and instability. It suffers from time-consuming, high false-alarm rate, and low recognition rate. To alleviate these problems, a joint probability detector (JPD) integrated with scattering attention (SA) is designed for aircraft detection and classification. Based on the fact that all aircraft are parked in the airport area, an airport detection method with mixed strategy (ADMS) is proposed to obtain the valid region (airport), narrowing downing the scope of detection area, increasing the detection efficiency as well as suppressing a lot of false alarms outside the airport. Considering that it's easy to generate false alarms within the airport on account of clutter scattering interference, a two-stage detector is introduced to improve the accuracy by replacing a stronger region proposal network (RPN) and optimizing a lower bound to a joint probabilistic objective over two stages. Furthermore, the classification encoder module incorporates scattering attention into convolution neural network to leverage the distribution relation among strong scattered points to enhance the classification performance. Finally, extensive experiments on the ZKXT and GaoFen-3 datasets verify the effectiveness and superiority of the proposed approach, and surpass runner up by 5.3% with mF1 indicator. On a large GaoFen3 image (16550× 11945 pixels), the proposed method improves the detection speed by 187.52%, without sacrificing the accuracy. More importantly, the proposed method has been applied to the SAR image interpretation and achieved the expected effect in the actual application.
- Open Access
- 17 May 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (10) , 2609
Distillation Sparsity Training Algorithm for Accelerating Convolutional Neural Networks in Embedded Systems
The rapid development of neural networks has come at the cost of increased computational complexity. Neural networks are both computationally intensive and memory intensive; as such, the minimal energy and computing power of satellites pose a challenge for automatic target recognition (ATR). Knowledge distillation (KD) can distill knowledge from a cumbersome teacher network to a lightweight student network, transferring the essential information learned by the teacher network. Thus, the concept of KD can be used to improve the accuracy of student networks. Even when learning from a teacher network, there is still redundancy in the student network. Traditional networks fix the structure before training, such that training does not improve the situation. This paper proposes a distillation sparsity training (DST) algorithm based on KD and network pruning to address the above limitations. We first improve the accuracy of the student network through KD, and then through network pruning, allowing the student network to learn which connections are essential. DST allows the teacher network to teach the pruned student network directly. The proposed algorithm was tested on the CIFAR-100, MSTAR, and FUSAR-Ship data sets, with a 50% sparsity setting. First, a new loss function for the teacher-pruned student was proposed, and the pruned student network showed a performance close to that of the teacher network. Second, a new sparsity model (uniformity half-pruning UHP) was designed to solve the problem that unstructured pruning does not facilitate the implementation of general-purpose hardware acceleration and storage. Compared with traditional unstructured pruning, UHP can double the speed of neural networks.
- 17 May 2023
- Published by MDPI AG in Remote Sensing
- Vol. 15 (10) , 2609
Open AccessDistillation Sparsity Training Algorithm for Accelerating Convolutional Neural Networks in Embedded Systems
The rapid development of neural networks has come at the cost of increased computational complexity. Neural networks are both computationally intensive and memory intensive; as such, the minimal energy and computing power of satellites pose a challenge for automatic target recognition (ATR). Knowledge distillation (KD) can distill knowledge from a cumbersome teacher network to a lightweight student network, transferring the essential information learned by the teacher network. Thus, the concept of KD can be used to improve the accuracy of student networks. Even when learning from a teacher network, there is still redundancy in the student network. Traditional networks fix the structure before training, such that training does not improve the situation. This paper proposes a distillation sparsity training (DST) algorithm based on KD and network pruning to address the above limitations. We first improve the accuracy of the student network through KD, and then through network pruning, allowing the student network to learn which connections are essential. DST allows the teacher network to teach the pruned student network directly. The proposed algorithm was tested on the CIFAR-100, MSTAR, and FUSAR-Ship data sets, with a 50% sparsity setting. First, a new loss function for the teacher-pruned student was proposed, and the pruned student network showed a performance close to that of the teacher network. Second, a new sparsity model (uniformity half-pruning UHP) was designed to solve the problem that unstructured pruning does not facilitate the implementation of general-purpose hardware acceleration and storage. Compared with traditional unstructured pruning, UHP can double the speed of neural networks.
- Open Access
- 30 November 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (23) , 6077
Aircraft Detection in SAR Images Based on Peak Feature Fusion and Adaptive Deformable Network
Due to the unique imaging mechanism of synthetic aperture radar (SAR), targets in SAR images often shows complex scattering characteristics, including unclear contours, incomplete scattering spots, attitude sensitivity, etc. Automatic aircraft detection is still a great challenge in SAR images. To cope with these problems, a novel approach called adaptive deformable network (ADN) combined with peak feature fusion (PFF) is proposed for aircraft detection. The PFF is designed for taking full advantage of the strong scattering features of aircraft, which consists of peak feature extraction and fusion. To fully exploit the strong scattering features of the aircraft in SAR images, peak features are extracted via the Harris detector and the eight-domain pixel detection of local maxima. Then, the saliency of aircraft under multiple imaging conditions is enhanced by multi-channel blending. All the PFF-preprocessed images are fed into the ADN for training and testing. The core components of ADN contain an adaptive spatial feature fusion (ASFF) module and a deformable convolution module (DCM). ASFF is utilized to reconcile the inconsistency across different feature scales, raising the characterization capabilities of the feature pyramid and improving the detection performance of multi-scale aircraft further. DCM is introduced to determine the 2-D offsets of feature maps adaptively, improving the geometric modeling abilities of aircraft in various shapes. The well-designed ADN is established by combining the two modules to alleviate the problems of the multi-scale targets and attitude sensitivity. Extensive experiments are conducted on the GaoFen-3 (GF3) dataset to demonstrate the effectiveness of the PFF-ADN with an average precision of 89.34%, as well as an F1-score of 91.11%. Compared with other mainstream algorithms, the proposed approach achieves state-of-the-art performance.
- 30 November 2022
- Published by MDPI AG in Remote Sensing
- Vol. 14 (23) , 6077
Open AccessAircraft Detection in SAR Images Based on Peak Feature Fusion and Adaptive Deformable Network
Due to the unique imaging mechanism of synthetic aperture radar (SAR), targets in SAR images often shows complex scattering characteristics, including unclear contours, incomplete scattering spots, attitude sensitivity, etc. Automatic aircraft detection is still a great challenge in SAR images. To cope with these problems, a novel approach called adaptive deformable network (ADN) combined with peak feature fusion (PFF) is proposed for aircraft detection. The PFF is designed for taking full advantage of the strong scattering features of aircraft, which consists of peak feature extraction and fusion. To fully exploit the strong scattering features of the aircraft in SAR images, peak features are extracted via the Harris detector and the eight-domain pixel detection of local maxima. Then, the saliency of aircraft under multiple imaging conditions is enhanced by multi-channel blending. All the PFF-preprocessed images are fed into the ADN for training and testing. The core components of ADN contain an adaptive spatial feature fusion (ASFF) module and a deformable convolution module (DCM). ASFF is utilized to reconcile the inconsistency across different feature scales, raising the characterization capabilities of the feature pyramid and improving the detection performance of multi-scale aircraft further. DCM is introduced to determine the 2-D offsets of feature maps adaptively, improving the geometric modeling abilities of aircraft in various shapes. The well-designed ADN is established by combining the two modules to alleviate the problems of the multi-scale targets and attitude sensitivity. Extensive experiments are conducted on the GaoFen-3 (GF3) dataset to demonstrate the effectiveness of the PFF-ADN with an average precision of 89.34%, as well as an F1-score of 91.11%. Compared with other mainstream algorithms, the proposed approach achieves state-of-the-art performance.
- Open Access
- 29 October 2018
- Published by Wiley in Journal of Sensors
- Vol. 2018, 1-11
Detecting and Measuring Internal Anomalies in Tree Trunks Using Radar Data for Layer Identification
Radar detection has proven to be an effective, nondestructive test for the determination of the quality of wood-based materials, especially in the wooden structures of ancient buildings and trees. However, the results are usually inaccurate, and it is difficult to interpret internal anomalies due to the moisture content of wood, individual differences, and other factors. In this paper, a new measurement method is proposed based on the use of ground-penetrating radar (GPR) for abnormality localization and imaging. Firstly, the time delay of the reflected signal in the inner trees is analyzed with matched filter and Hilbert detections. Secondly, the two approaches are compared with the use of a forward model, and the Hilbert algorithm is found to be more accurate. Thirdly, a laser scanner is used to collect contour data and determine the location and characteristics of internal tree anomalies. Lastly, the proposed method is tested on ancient willows at the Summer Palace. The results show that the error in the depth and area estimates of the anomalies was within 10% and 5%, respectively. Consequently, the GPR method for locating the anomalies in trees is feasible, and a laser scanner combined with contour data can present the size of the abnormal regions within the trees.
- 29 October 2018
- Published by Wiley in Journal of Sensors
- Vol. 2018, 1-11
Open AccessDetecting and Measuring Internal Anomalies in Tree Trunks Using Radar Data for Layer Identification
Radar detection has proven to be an effective, nondestructive test for the determination of the quality of wood-based materials, especially in the wooden structures of ancient buildings and trees. However, the results are usually inaccurate, and it is difficult to interpret internal anomalies due to the moisture content of wood, individual differences, and other factors. In this paper, a new measurement method is proposed based on the use of ground-penetrating radar (GPR) for abnormality localization and imaging. Firstly, the time delay of the reflected signal in the inner trees is analyzed with matched filter and Hilbert detections. Secondly, the two approaches are compared with the use of a forward model, and the Hilbert algorithm is found to be more accurate. Thirdly, a laser scanner is used to collect contour data and determine the location and characteristics of internal tree anomalies. Lastly, the proposed method is tested on ancient willows at the Summer Palace. The results show that the error in the depth and area estimates of the anomalies was within 10% and 5%, respectively. Consequently, the GPR method for locating the anomalies in trees is feasible, and a laser scanner combined with contour data can present the size of the abnormal regions within the trees.