Huaiyue Ding

Huaiyue Ding

Auto-generated profile, based on publicly available information

Huaiyue Ding

College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 April 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
DXDeliang Xiang
Deliang Xiang
XPXiaoyu Pan
Xiaoyu Pan
HDHuaiyue Ding
Huaiyue Ding
JCJianda Cheng
Jianda Cheng
XSXiaokun Sun
Xiaokun Sun
When the geometric distortion of the synthetic aperture radar (SAR) images to be registered is large, the spatial correspondence between the feature points of the two images will change significantly. Hence, the registration of SAR images with large geometric distortion is challenging. To solve this problem, a two-stage registration method of SAR images with large distortion based on superpixel segmentation is proposed in this article. First, the two SAR images are coarsely registered by geographic coordinate referencing. After coarse registration, superpixel segmentation is performed on the two SAR images, respectively. Next, in the superpixel neighborhood of the reference image, we slide the corresponding superpixel template of the sensed image, finding its position with the highest similarity in the reference image. Compared with the traditional fixed-size template, the superpixel template can segment the distorted region more effectively. Meanwhile, with the help of the adaptive threshold detector proposed in this article, the regions with varying degrees of distortion can be distinguished based on their similarity. Furthermore, the geometry mapping relationship is calculated for the regions with different distortion degrees in the images, respectively, and the corresponding feature points in different images are accurately matched to complete the fine registration. Finally, the registration results of regions with different degrees of distortion are fused to obtain the final SAR image registration results. Experimental results based on Sentinel-1 data show that the registration accuracy of the proposed method can reach within 1 pixel.

21 March 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
DXDeliang Xiang
Deliang Xiang
HDHuaiyue Ding
Huaiyue Ding
XSXiaokun Sun
Xiaokun Sun
JCJianda Cheng
Jianda Cheng
Canbin HuCanbin Hu
Canbin Hu
YSYi Su
Yi Su
Polarimetric synthetic aperture radar (PolSAR) is an active microwave imaging system. Due to the coherence characteristic of PolSAR imaging, inherent coherent speckle noise exists in PolSAR images. The registration of PolSAR images is severely affected by speckle noise. Therefore, we first propose a joint filter that combines Refined-Lee filtering and polarimetric whitening filtering (PWF). The filter first applies Refined-Lee filtering to PolSAR images, which greatly reduces the speckle noise while maintaining high-resolution detailed information of the texture, and then uses PWF to normalize and whiten the polarimetric matrix to further limit the interference of speckle noise. After that, the binary robust invariant scalable keypoints (BRISK) algorithm is used to extract high-quality keypoints from the denoised PolSAR image. Then a novel Siamese Multiscale Attention Network (SMAN) is designed, which uses attention modules to construct feature descriptors with different scales. To fully utilize polarimetric information, we adopt the polarimetric covariance matrix and three polarimetric features as inputs to the network and the Second Order Similarity (SOS) as the loss function to train the network. In the keypoint matching stage, we present to use the symmetric displacement distance to further constrain the keypoint pairs obtained by the initial matching, which improves the accuracy of matching keypoint pairs. Experimental results show that our proposed method can effectively reduce the interference of speckle noise and overcome non-linear differences, geometric distortions, and differences in polarimetric scattering information to achieve accurate PolSAR image registration.

12 January 2026 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
DGDongdong Guan
Dongdong Guan
RFRui Feng
Rui Feng
YXYuzhen Xie
Yuzhen Xie
HDHuaiyue Ding
Huaiyue Ding
YCYang Cui
Yang Cui
DXDeliang Xiang
Deliang Xiang
As is well known, obtaining high-quality measured SAR vehicle data is difficult. As a result, deep learning-based data generation is frequently utilized for SAR target augmentation because of its affordability and simplicity of use. However, existing methods do not adequately consider the target scattering information during data generation, resulting in generated target SAR data that does not conform to the physical scattering laws of SAR imaging. In this paper, we propose a SAR target data generation method based on target scattering features and Cycle-Consistent Generative Adversarial Networks (CycleGAN). First, a physical model-based method called Orthogonal Matching Pursuit (OMP) is adopted to extract the Attribute Scattering Centers (ASC) of SAR vehicle targets. Then, a multidimensional SAR target feature representation is constructed. Based on the scattering difference between the generated and real SAR target images, we introduce a loss function and further develop a generative model based on the CycleGAN. Therefore, the scattering mechanisms of SAR targets can be well learned, making the generated SAR data conform to the target scattering features. We conduct SAR target generation experiments under standard operating conditions (SOC) and extended operating conditions (EOC) on our self-acquired dataset as well as SAMPLE and MSTAR datasets. The SAR vehicle target data generated under SOC shows a more accurate scattering feature distribution to the real target data than other state-of-the-art methods. In addition, we generate SAR target data under EOC that conforms to SAR imaging patterns by modulating ASC feature parameters. Finally, the target recognition performance based on our proposed generated SAR vehicle data under SOC is validated, where the recognition rate increased by 4% after the addition of our generated target data. The code for the proposed method is publicly available at https://github.com/freel3/ Transformation _Mstar2SAMPLE.

19 November 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
JCJianda Cheng
Jianda Cheng
DGDongdong Guan
Dongdong Guan
DXDeliang Xiang
Deliang Xiang
JTJiaxin Tang
Jiaxin Tang
HDHuaiyue Ding
Huaiyue Ding
BLBangjie Li
Bangjie Li
Although remote sensing image registration has been developing at a high speed for decades, polarimetric synthetic aperture radar (PolSAR) image registration is still a challenging task because of the presence of polarimetric scattering differences, geometric distortions, and speckle noise. Due to the lack of PolSAR image training data, the generalization performance of deep learning-based registration methods is poor and cannot fundamentally solve the problem of PolSAR image registration. In this paper, we propose a novel PolSAR image registration framework that integrates feature selection, feature descriptor extraction, and template matching. Firstly, we use structural similarity to select polarimetric features that are similar in structural information, thus using structural information to overcome polarimetric scattering differences. On this basis, a feature descriptor named oriented gradient of polarimetric feature (OGPF) is proposed to overcome the polarimetric scattering information difference by extracting geometric structure information using oriented gradient channels (OGCs) and 3-D Gaussian convolution. Finally, we propose to use polarimetric whitening filter (PWF) and non-maximum sup- pression (NMS) to extract keypoints with significant structural information to reduce the interference of speckle noise on keypoint selection, and further propose a template downsampling strategy to reduce the complexity of template matching. The proposed method is evaluated using six pairs of PolSAR images with different scenes, and the results show that its registration performance outperforms the state-of-the-art methods.

20 February 2025 in IEEE Access
Verified
Journal Article
Open access
ZGZichen Gao
Zichen Gao
QLQinmei Liu
Qinmei Liu
YZYibin Zhou
Yibin Zhou
QLQing Liu
Qing Liu
ZMZu Ma
Zu Ma
HZHengduan Zhang
Hengduan Zhang
Detection and control of potential breeding sites (PBS) for Aedes albopictus are considered among the most effective methods for managing mosquito-borne diseases. Due to the high adaptability and rapid reproduction of mosquitoes, PBS are widely distributed. Traditional manual investigation methods are inefficient and would increase the risk of exposure. Unmanned Aerial Vehicle (UAV) remote sensing technology, with its speed and broad coverage, can capture large-scale images quickly. However, current PBS detection methods primarily focus on the detection of large, regular containers. To address the issue for detecting diverse PBS in complex environments, we propose a method called MultiDCCSP-YOLO. This approach integrates several modules to improve the PBS detection accuracy from UAV remote sensing images with challenging backgrounds. We introduce the Multi-DC Block and use it to build the CSPDCStage module. This module captures multi-scale features while reducing computational demands without compromising the detection accuracy. The FasterELAN module minimizes overfitting risks and enhances the detection of PBS targets with limited-sample classes. Additionally, we incorporate the Adaptive Threshold Focal Loss (ATFL) function to emphasize small, hard-to-detect targets, thereby improving multi-scale PBS detection performance. The MultiDCCSP-YOLO method enables efficient and accurate PBS detection in complex environments, facilitating large-scale monitoring efforts.

12 January 2026 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
DGDongdong Guan
Dongdong Guan
NLNengcai Li
Nengcai Li
YXYuzhen Xie
Yuzhen Xie
HDHuaiyue Ding
Huaiyue Ding
DXDeliang Xiang
Deliang Xiang
Polarimetric target decomposition is fundamental for interpreting scattering mechanisms in polarimetric synthetic aperture radar (PolSAR) imagery. However, existing model-based methods often overestimate volume scattering, exhibit coupling between surface and double-bounce components, and yield unstable results on high-resolution airborne data, particularly for man-made vehicle targets, hindering accurate characterization. This letter proposes a novel four-component decomposition method designed for high-resolution airborne PolSAR imagery. Building upon the classical modeling of volume and helix scattering, two physically extended components are incorporated: an extended surface scattering model and an extended double-bounce scattering model. The former employs a rotated dipole to describe surface polarization anisotropy beyond ideal single-bounce assumptions, while the latter incorporates a rotated quarter-wave mechanism to characterize amplitude–phase inconsistencies neglected in conventional dihedral models. Experiments on a high-resolution Ku-band vehicle dataset demonstrate that the proposed method effectively suppresses volume overestimation, alleviates surface–double-bounce coupling, and enhances component stability while preserving edge and structural fidelity. The model achieves improved adaptability to complex targets without increasing component dimensionality, while maintaining strong physical interpretability, offering a new pathway for refined vehicle scattering analysis in airborne PolSAR data.