Qinghua Liu

Dr. Qinghua Liu

orcid

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
8 August 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XLXiuqin Li
Xiuqin Li
DLDong Li
Dong Li
HLHongqing Liu
Hongqing Liu
JWJun Wan
Jun Wan
ZCZhanye Chen
Zhanye Chen
QLQinghua Liu
Qinghua Liu
Thanks to the excellent feature representation capabilities of neural networks, target detection methods based on deep learning are now widely applied in synthetic aperture radar (SAR) ship detection. However, the multi-scale variation, small targets with complex background such as islands, sea clutter, and inland facilities in SAR images increase the difficulty for SAR ship detection. To increase the detection performance, in this paper, a novel deep learning network for SAR ship detection, termed as attention-guided balanced feature pyramid network (A-BFPN), is proposed to better exploit semantic and multilevel complementary features, which consists of the following two main steps. First, in order to reduce interferences from complex backgrounds, the enhanced refinement module (ERM) is developed to enable BFPN to learn the dependency features from the channel and space dimensions, respectively, which enhances the representation of ship objects. Second, the channel attention-guided fusion network (CAFN) model is designed to obtain optimized multi-scale features and reduce serious aliasing effects in hybrid feature maps. Finally, we illustrate the effectiveness of the proposed method, adopting the existing SAR Ship Detection Dataset (SSDD) and Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0). Experimental results show that the proposed method is superior to the existing algorithms, especially for multi-scale small ship targets under complex background.

6 January 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JWJun Wan
Jun Wan
XTXiaoheng Tan
Xiaoheng Tan
ZCZhanye Chen
Zhanye Chen
DLDong Li
Dong Li
QLQinghua Liu
Qinghua Liu
LZLinrang Zhang
Linrang Zhang
Ground moving targets will typically be defocused because of the range migration (RM) and Doppler frequency migration (DFM) caused by the unknown relative motions between the platform of synthetic aperture radar (SAR) and the ground moving targets. The received signal of the ground moving target easily exhibits the Doppler ambiguity, and the Doppler ambiguity leads to the refocusing difficulty of ground moving targets. To address these problems, a SAR refocusing method of ground moving targets with Doppler ambiguity based on modified second-order keystone transform (MSOKT) and keystone transform (KT) is presented in this paper. Firstly, the second-order phase is separated by the time reversing process. Secondly, MSOKT is performed to compensate the range curvature migration and DFM, and then the coefficient of the second-order phase is estimated. Finally, a well-refocused result of the moving target is achieved after KT and the estimated Doppler ambiguity number are used to eliminate residual range walk migration. The proposed method can accurately remove RM and DFM and effectively focus the moving targets without residual correction errors. Moreover, the effects of Doppler ambiguity (including Doppler center blur and spectrum split) and blind speed sidelobe are further avoided. On the basis of the analysis of cross-term for the multiple target case, the identification strategy of spurious peak of cross-term is proposed. Additionally, the developed method can be sped up by nonuniform fast Fourier transform without the interpolation operation. The effectiveness of the proposed method is verified by both airborne and spaceborne real data processing results.

31 August 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
HWHui Wang
Hui Wang
SOShan Ouyang
Shan Ouyang
QLQinghua Liu
Qinghua Liu
KLKefei Liao
Kefei Liao
LZLijun Zhou
Lijun Zhou
Correctly estimating the relative permittivity of buried targets is crucial for accurately determining the target type, geometric size, and reconstruction of shallow surface geological structures. In order to effectively identify the dielectric properties of buried targets, on the basis of extracting the feature information of B-SCAN images, we propose an inversion method based on a deep neural network (DNN) to estimate the relative permittivity of targets. We first take the physical mechanism of ground-penetrating radar (GPR), working in the reflection measurement mode as the constrain condition, and then design a convolutional neural network (CNN) to extract the feature hyperbola of the underground target, which is used to calculate the buried depth of the target and the relative permittivity of the background medium. We further build a regression network and train the network model with the labeled sample set to estimate the relative permittivity of the target. Tests were carried out on the GPR simulation dataset and the field dataset of underground rainwater pipelines, respectively. The results show that the inversion method has high accuracy in estimating the relative permittivity of the target.

13 October 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
SLShuang Liu
Shuang Liu
DLDong Li
Dong Li
RJRenJie Jiang
RenJie Jiang
QLQinghua Liu
Qinghua Liu
JWJun Wan
Jun Wan
HLHehao Liu
Hehao Liu
Ship detection in synthetic aperture radar (SAR) images has attracted extensive attention due to its promising applications. While numerous methods for ship detection have been proposed, detecting ships in complex scenarios remains challenging. The main factors contributing to the lower detection accuracy are SAR image characteristics, such as blurred outlines, and similar scattering intensities between actual ship targets and background environment, induced by the special imaging mechanism. To alleviate these issues, we propose a Mixed-scale Self-distillation Network (MSNet) for accurate ship detection in SAR images. Firstly, the zoom strategy is used to obtain more ship target information, and differentiated information between ship targets and background environments at different scales is aggregated through the designed search module. Then, the consistency self-distillation module is proposed to match feature attention maps at different scales, which forces the model to capture the potential semantic attributes of ship targets through a self-distillation fashion. After that, the refinement module is developed to further enhance the discriminative semantics among different hierarchical features under mixed scales. Furthermore, to alleviate the uncertainty arising from indistinguishable background interference in SAR images, we introduce an uncertainty perception loss to facilitate the model to make accurate judgments in candidate regions. Extensive experiments are performed on the SAR ship detection dataset from the Gaofen-3, RadarSat-2, Sentinel-1, and TerraSAR satellites. The experimental results consistently demonstrate the superiority of our method over the existing state-of-the-art methods. Besides, detailed model analysis experiments further validate the effectiveness of our proposed method in SAR image ship detection tasks. The code will be available at: https://github.com/shuangliumax/MSNet/

2 December 2023 in Signal Processing
Verified
Journal Article
Closed access
XKXiaohua Kang
Xiaohua Kang
JWJun Wan
Jun Wan
DLDong Li
Dong Li
QLQinghua Liu
Qinghua Liu
HLHongqing Liu
Hongqing Liu
ZCZhanye Chen
Zhanye Chen

17 January 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MWMingze Wu
Mingze Wu
QLQinghua Liu
Qinghua Liu
SOShan Ouyang
Shan Ouyang
Ground penetrating radar (GPR) image inversion is of great significance for interpreting GPR data. In practical applications, the complexity and nonuniformity of underground structures bring noise and clutter interference, making GPR inversion problems more challenging. To address these issues, this study proposes a two-stage GPR image inversion network called MHInvNet based on multi-scale dilated convolution (MSDC) and hybrid attention gate (HAG). This method first denoises the B-scan through the first network MHInvNet1, then combines the denoised B-scan from MHInvNet1 with the undenoised B-scan as input to the second network MHInvNet2 for inversion to reconstruct the distribution of the permittivity of underground targets. To further enhance network performance, the MSDC and HAG modules are simultaneously introduced to both networks. Experimental results from simulated and actual measurement data show that MHInvNet can accurately invert the position, shape, size, and permittivity of underground targets. A comparison with existing methods demonstrates the superior inversion performance of MHInvNet.