A5010402660- Image Enhancement Techniques
- Biometric Identification and Security
- Advanced Image Fusion Techniques
- Advanced Image Processing Techniques
- Advanced Vision and Imaging
- 3D Surveying and Cultural Heritage
- Vehicle License Plate Recognition
- Optical Systems and Laser Technology
- 3D Shape Modeling and Analysis
- Image and Signal Denoising Methods
- Computer Graphics and Visualization Techniques
- Advanced Neural Network Applications
- Remote Sensing and LiDAR Applications
- Robotics and Sensor-Based Localization
- Video Surveillance and Tracking Methods
- Advanced Measurement and Detection Methods
- Infrared Target Detection Methodologies
- Image Processing Techniques and Applications
- Medical Image Segmentation Techniques
- Advanced Algorithms and Applications
- Gait Recognition and Analysis
- Single-cell and spatial transcriptomics
- Fire Detection and Safety Systems
- Image and Object Detection Techniques
- Face recognition and analysis
Shenyang Ligong University
2021-2025
Shenyang Institute of Automation
2017-2022
Chinese Academy of Sciences
2009-2022
Liaoning Technical University
2011-2020
University of Nottingham
2019-2020
University at Buffalo, State University of New York
2020
Shenyang University of Technology
2011-2013
Changchun University of Science and Technology
2011
Institute of Software
2009
University of Chinese Academy of Sciences
2009
This paper presents WiPose, the first 3D human pose construction framework using commercial WiFi devices. From pervasive signals, WiPose can reconstruct skeletons composed of joints on both limbs and torso body. By overcoming technical challenges faced by traditional camera-based perception solutions, such as lighting occlusion, proposed sensing technique demonstrates potential to enable a new generation applications health care, assisted living, gaming, virtual reality. is based novel deep...
Underwater images suffer from color casts and low illumination due to the scattering absorption of light as it propagates in water. These problems can interfere with underwater vision tasks, such recognition detection. We propose an adaptive learning attention network for image enhancement based on supervised learning, named LANet, solve these degradation issues. First, a multiscale fusion module is proposed combine different spatial information. Second, we design novel parallel module(PAM)...
As a new research focus in biometrics, palm vein recognition has attracted people's attention because of high security, liveness-detection, user acceptability and convenience. Palm exhibits as it uses the network blood vessels underneath skin for recognition. is interior biological information body, patterns are much harder intruders to copy compared other biometric features. mostly invisible human eyes; they commonly captured under near-infrared light. Under its natural state, veins...
Point cloud analysis is integral to numerous applications, including mapping and autonomous driving. However, the unstructured disordered nature of point clouds presents significant challenges for feature extraction. While both local non-local features are essential effective 3D analysis, existing methods often fail seamlessly integrate these complementary features. To address this limitation, we propose Local-Non-Local Complementary Learning Network (LNLCL-Net), a novel framework that...
<title>Abstract</title> The stability of open-pit mine slopes is a complex nonlinear system. Stress variation significant influencing factor in the occurrence landslide disasters and also key research focus early warning risk assessment.However, traditional methods are confronted with challenges, including low prediction accuracy poor robustness when dealing time series data. In order to address aforementioned issues, present paper proposes an intelligent model based on Variational Mode...
PDF HTML阅读 XML下载 导出引用 引用提醒 基于C4.5决策树的流量分类方法 DOI: 作者: 作者单位: 作者简介: 通讯作者: 中图分类号: 基金项目: Supported by the National Basic Research Program of China under Grant No.2007CB307100 (国家重点基础研究发展计划(973)) Internet Traffic Classification Using C4.5 Decision Tree Author: Affiliation: Fund Project: 摘要 | 图/表 访问统计 参考文献 相似文献 引证文献 资源附件 文章评论...
The ROI (region of interest) extraction is the key step in palmprint or palm vein recognition, which very important for subsequent feature and recognition. In this paper, method recognition mainly studied. Firstly, preprocessing operation carried out by using binary morphological denoising technology, then regions are located extracted based on maximum inscribed circle centroid methods. Finally, algorithms tested PUT database CASIA database, experimental results show that methods paper have...
Since light is scattered and absorbed by water, underwater images have inherent degradation (e.g., hazing, color shift), consequently impeding the development of remotely operated vehicles (ROVs). Toward this end, we propose a novel method, referred to as <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${B}$ </tex-math></inline-formula> est notation="LaTeX">${o}\text{f}$ Bo th World notation="LaTeX">${s}$...
Person re-identification (Re-ID) networks are often affected by factors such as pose variations, changes in viewpoint, and occlusion, leading to the extraction of features that encompass a considerable amount irrelevant information. However, most research has struggled address challenge simultaneously endowing with both attentive diversified To concurrently extract yet diverse pedestrian features, we amalgamated strengths convolutional neural network (CNN) attention self-attention. By...
The stability of open-pit mine slopes is a complex nonlinear system. Stress variation significant influencing factor in the occurrence landslide disasters and also key research focus early warning risk assessment. However, traditional methods are confronted with challenges, including low prediction accuracy poor robustness when dealing time series data. In order to address aforementioned issues, present paper proposes an intelligent model based on Variational Mode Decomposition (VMD) Dung...
With the growing demand for information security, finger-vein recognition has become widespread. However, robustness of process becomes a major problem. When identifying unseen categories with traditional systems, few issues remain, such as interference and low efficiency. This paper proposes Deep Generalized Label Finger-Vein (DGLFV) model to extract feature maps achieve high-accuracy recognition. The largest rectangular region is extracted through image semantic segmentation advanced...
Palm vein recognition is motivated by the advantages of high security and liveness detection, but its popularity prevented cost palm capture devices. This study proposes a low-cost practical system. First, authors' system captures near-infrared (NIR) image with complementary metal–oxide–semiconductor camera in lieu an NIR charge-coupled device camera. The goal to reduce devices greatly. Second, this adopts thenar area on as region interest (ROI) for further recognition. get rich vessel avoid...
Palm vein recognition is a high-security biometric. Outside the NIR capture box and contactless palm are more popular but challenging. The users feel comfortable outside face optical blurring brought by visible light. Contactless gestures solve hygienic problem image rotation, position translation, scale transformation which makes classification difficult especially in large-scale databases. To address these problems, we develop wavelet denoising ResNet, consists of two models: (WD) model...