A5049255145- Advanced Image Fusion Techniques
- Image Enhancement Techniques
- Video Surveillance and Tracking Methods
- Advanced Neural Network Applications
- Advanced Welding Techniques Analysis
- Advanced Thermoelectric Materials and Devices
- Advanced Image Processing Techniques
- Advanced Image and Video Retrieval Techniques
- Remote-Sensing Image Classification
- Automated Road and Building Extraction
- Data Management and Algorithms
- E-commerce and Technology Innovations
- Remote Sensing and Land Use
- Phase-change materials and chalcogenides
- Infrared Target Detection Methodologies
- Digital Image Processing Techniques
- Electronic Packaging and Soldering Technologies
- Advanced SAR Imaging Techniques
- Underwater Vehicles and Communication Systems
- Visual Attention and Saliency Detection
- Thermal properties of materials
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Remote Sensing and LiDAR Applications
- Advanced Computing and Algorithms
- Thermal Radiation and Cooling Technologies
Xidian University
2004-2025
Shenyang 242 Hospital
2024
Shenyang Maternity and Child Health Hospital
2024
Sun Yat-sen University
2024
Wuhan University
2024
Beijing University of Posts and Telecommunications
2023
Yanshan University
2023
Huazhong University of Science and Technology
2005-2006
The ratio of non-high-density lipoprotein cholesterol (non-HDL-C) to HDL-C (NHHR) is a novel lipid parameter used assess the risk cardiovascular disease. Previous studies have demonstrated an association between NHHR and non-alcoholic fatty liver disease (NAFLD). Owing lack research exploring this relationship in specific populations, study aimed determine potential link NAFLD among American adults United States. Data were retrieved from National Health Nutrition Examination Survey (NHANES)...
Object detection in UAV images is an important and challenging task for many applications, which often needs highly efficient algorithms to meet the accuracy real-time requirements of applications. In this paper, we investigate mechanisms detecting dense small objects images. Specifically, 1) kernel K-means used obtain optimal anchors object detection; 2) a spatial information enhancement module (SIE) proposed improve by extracting location information; 3) Coord_C3 receptive field network...
Flexible thermoelectric devices (f-TEDs) facilitate direct energy conversion between heat and electricity, presenting significant potential in body harvesting personal thermal management. Conventional f-TEDs employing polyimide (PI) substrates encounter...
With the advantages of wide range, constant observation ability, and an active imaging mechanism, synthetic aperture radar (SAR) has been a preferrable choice for ship detection in complicated scenarios. However, existing algorithms, especially convolutional neural network (CNN), cannot achieve satisfactory accuracy generalization ability. Moreover, complex architectures limit their real-time performances on embedding or edge computing platforms. To handle these issues, this article proposes...
Ship detection is of great importance in territorial security and marine environmental protection. However, the accurate small ships a challenging task complex environments mainly due to having few features on remote sensing images. In this letter, we propose ship model based YOLOv5s. The major proposed include: (1) layer added with shallow feature map Head skip connections are employed Neck improve accuracy ships; (2) novel effective Hybrid Spatial Pyramid Pooling (HSPP) fuse local global...
As an atmospheric phenomenon, haze significantly reduces the visibility of outdoor and remote sensing images. imaging have different mechanisms, existing dehazing methods are hard to be applied for both images In this article, efficient method is proposed which can The has advantages based on image enhancement restoration methods. To address problem inaccurate calculation transmittance in methods, a Gaussian-weighted fusion introduced obtain refined transmittance. addition, solve color...
Visual object tracking is a fundamental video task in computer vision. Recently, the notably increasing power of perception algorithms allows unification single/multiobject and box/mask-based tracking. Among them, Segment Anything Model (SAM) attracts much attention. In this report, we propose HQTrack, framework for High Quality Tracking anything videos. HQTrack mainly consists multi-object segmenter (VMOS) mask refiner (MR). Given to be tracked initial frame video, VMOS propagates masks...
遥感影像由于雾霾的原因导致清晰度下降,增添了遥感影像目标检测和地物分割任务的困难。提出一种基于自适应SLIC的遥感影像去雾算法,主要包括:首先,针对有雾遥感影像出现局部区域高亮问题,使用改进的Retinex算法,对输入遥感影像进行对比度增强,保留图像细节,以减少伪影现象,扩展图像的对比度动态范围,准确估计遥感影像大气强度值;其次,提出了一种自适应SLIC算法,解决超像素数目参数设定的困难,对输入遥感影像进行超像素分割,避免局部对比度强烈区域对固定窗口的影响,从而获得更加精确的透射率估计;最后,基于暗通道先验原理和大气散射模型恢复出无雾遥感影像。使用所提算法和He等人、Zhu等人、Han等人和Nie等人的四种算法进行对比,分别在公开数据集Inria Aerial Image Dataset和RICE...
This article uses a fuzzy clustering method to conduct susceptibility assessment of landslide disasters in Nayong County, Guizhou Province, China. Fuzzy is an unsupervised classifier with objectivity and natural classification characteristics more line the actual distribution disasters. However, large number clusters obtained by this are unlabeled, so its disaster significance has yet be discovered. based on concept spatial pattern recognition, which treats as components. The approach...
Ultrasound imaging has been widely used in clinical examinations owing to the advantages of being portable, real-time, and radiation-free. Considering potential extensive deployment autonomous examination systems hospitals, robotic US attracted increased attention. However, due inter-patient variations, it is still challenging have an optimal path for each patient, particularly thoracic applications with limited acoustic windows, e.g., intercostal liver imaging. To address this problem, a...
The multimodal MRI data is often ultilized for breast cancer analysis, and by now still difficult inefficient to explored segmentation algorithms. In this paper, we propose a MP-Unet based on U-net convolutional neural network, which can effectively ensemble multiple inputs of modal obtain accuracy results at the end. MP-Unet, reused some good quality training. models are further integrated Bagging algorithm improve lesions. Experiments suggest that our proposed method has huge performance...
The segmentation of Synthetic aperture radar (SAR) images is vital and fundamental in SAR image processing, so evaluating results without ground truth (GT) an essential part algorithms comparison, parameters selection, optimization. In this study, we first extracted the heterogeneous features (HF) to adequately describe targets, which were by proposed intensity feature extractor (IFEE) based on edge-hold two fruitful methods. Then a novel effective unsupervised evaluation (UE) metric <italic...
ObjectWith social and economic development, more areas are evolving toward modern cities [1]. Road information is critical for urban planning, traffic navigation GIS data updates [2]. Traditional manual collection methods inefficient. The advancement of remote sensing technology allows the automatic extraction road from high resolution images [3]-[7].MethodThis paper proposes a model high-resolution based on multi-headed self-retaining mechanism U-Net (MSAU-Net) to achieve accurate roads in...