Ming Xu

Dr. Ming Xu

Ocean University of China, Qingdao, Shandong, China

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

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

Representative Publications

View All Publications
6 October 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
MXMing Xu
Ming Xu
HLHongping Li
Hongping Li
YYYuying Yun
Yuying Yun
FYFan Yang
Fan Yang
CLCuishu Li
Cuishu Li
Oceanic eddies are ubiquitous phenomena carrying large amounts of energy, thus of great importance for marine ecology and sea-air exchange. As an all-weather, high-resolution sensor, Synthetic Aperture Radar could provide valuable observations for oceanic eddies. However, there are few well-established methods for eddy detection on SAR images except for manual seeking, which is laborious and time-consuming. In combination with deep learning, this study is among the earliest in the literature that attempts end-to-end eddy detection on SAR images. Due to obscure pictures and indistinct eddy boundaries, ordinary deep learning models are not adaptable to the objective. Therefore, an customized model, SANet—stacked attention network, is designed to recognize the unique eddy pattern presented on radar images automatically. SANet is a two-unit stacking architecture, with each an hourglass structure for bottom-up, top-down reference and the overall stacking network for iterative extractions of eddy textures contained in shallow layers of each unit. Besides, SANet has included the inner-hourglass attention gates and the outer-hourglass GCblock for the extracted features to be more concentrated on the interested areas. Using SANet, we have identified 87.75% of eddies in the constructed dataset collected from ESA-2 and ENVISAT SAR products. The result is much better than the no-stacking counterpart U-net, as well as state-of-the-art deep learning models DeepLabV3+ and SegFomer, thus verifying the superiority of the proposed method. The generalization ability of the algorithm has also been tested. The code and the constructed SAR dataset have been made public for broader use.

30 March 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
MXMing Xu
Ming Xu
HLHongping Li
Hongping Li
HCHaihua Chen
Haihua Chen
Xiaobin YinXiaobin Yin
Xiaobin Yin
The Earth Exploration Satellite Service (EESS) for passive sensing has a primary frequency allocation in the 1400–1427 MHz band. All emissions unauthorized in this band are called RFI (Radio Frequency Interference). The SMOS (Soil Moisture and Ocean Salinity) mission is greatly perturbed by RFI impeding ocean salinity retrieval, especially in coastal areas such as the SCS (South China Sea), where the observed data has been discarded massively. At present, there is no way to eliminate the RFI impact on the retrieved salinity, other than by detecting and shutting down the emissions from the sources. However, it may be effective in a scientific sense if RFI can be quantified and applied to the salinity retrieval process. Therefore, this study proposes an RFI measuring method that can investigate contamination in both prominent and moderate respects, aroused either by on-site emissions or nearby continents. Based on the proposed method, two levels of hierarchical RFI maps of the SCS region, including the separated one and the merged one, are presented and discussed, indicating more severe contamination in northern and western SCS. Moreover, to verify the generalization of the method on open oceans far from continents, an area in the middle central Pacific is selected and tested. The result shows few or no RFI in this unattended region, which is consistent with the authors’ knowledge. This study presents the concept of the “RFI map” to describe the contamination, which will hopefully help researchers comprehend the RFI state intuitively and assist in ocean salinity retrieval statistically.

23 December 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
SHSUN Haochen
SUN Haochen
HLHongping Li
Hongping Li
MXMing Xu
Ming Xu
TXTianyu Xia
Tianyu Xia
HYHao Yu
Hao Yu
As a ubiquitous mesoscale phenomenon, ocean eddies significantly impact ocean energy and mass exchange. Detecting these eddies accurately and efficiently has become a research focus in ocean remote sensing. Many traditional detection methods, rooted in physical principles, often encounter challenges in practical applications due to their complex parameter settings, while effective, deep learning models can be limited by the high computational demands of their extensive parameters. Therefore, this paper proposes a new approach to eddy detection based on the altimeter data, the Ghost Attention Deeplab Network (GAD-Net), which is a lightweight and efficient semantic segmentation model designed to address these issues. The encoder of GAD-Net consists of a lightweight ECA+GhostNet and an Atrous Spatial Pyramid Pooling (ASPP) module. And the decoder integrates an Efficient Attention Network (EAN) module and an Efficient Ghost Feature Integration (EGFI) module. Experimental results show that GAD-Net outperforms other models in evaluation indices, with a lighter model size and lower computational complexity. It also outperforms other segmentation models in actual detection results in different sea areas. Furthermore, GAD-Net achieves detection results comparable to the Py-Eddy-Tracker (PET) method with a smaller eddy radius and a faster detection speed. The model and the constructed eddy dataset are publicly available.

22 February 2005
Verified
Conference Paper
Closed access
MXMing Xu
Ming Xu
RZRong-Chun Zhao
Rong-Chun Zhao
MPM. Petrou
M. Petrou
This work presents a new framework for integrating supplementary information (sparse stereo data or reference image) and shape from shading modules, in order to solve the ambiguity of the shading patterns and to get a complete 3D structural solution. The framework is composed of several functional modules and processes three kinds of surfaces: curved surface, planar surface and self-shadowed region, separately. In determination of curved surface orientations, four basic styles of surface patches such as dome, cup, horizontal saddle and vertical saddle could be selected to approximate the current local surface patch according to its directional curvature features which are derived from the supplementary information. It is demonstrated that the ancillary information compensates the inadequacies of the shape from shading approach and produces a reconstructed surface, which is an improvement over that surface produced by shape from shading alone.

11 February 2026 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
MXMing Xu
Ming Xu
RHRuhui Huang
Ruhui Huang
KYKunde Yang
Kunde Yang
Eddy trajectory prediction is crucial for understanding ocean dynamics and has practical implications in various fields. While existing sequential modeling approaches potentially introduce redundancy, this study reformulates oceanic eddy trajectory as a Markov Decision Process (MDP), assuming that the next position of an eddy can be predicted based solely on its current state, rather than on extended historical sequences. Under this framework, a simple Multi-Layer Perceptron (MLP) model, optimized by minimizing the difference between predicted and actual eddy propagation velocities, achieves prediction accuracy comparable to that of more complex sequential modeling approaches. This not only validates the Markovian assumption, but also provides a computationally efficient alternative for eddy forecasting. Furthermore, we identify a critical issue in existing prediction evaluations on employing retrospective state variables as model inputs for intermediate forecast days. The problem is addressed by reusing the initial-day state variables throughout the entire forecast period, thereby establishing a more reliable benchmark for future research.