A5031563962- Infrared Target Detection Methodologies
- Advanced Image Fusion Techniques
- Remote-Sensing Image Classification
- Advanced Measurement and Detection Methods
- Image Enhancement Techniques
- Remote Sensing and Land Use
- Optical Systems and Laser Technology
- Advanced Image Processing Techniques
- Calibration and Measurement Techniques
- Video Surveillance and Tracking Methods
- Image Processing Techniques and Applications
- Image and Signal Denoising Methods
- Advanced Vision and Imaging
- Advanced Image and Video Retrieval Techniques
- Advanced Chemical Sensor Technologies
- Thermography and Photoacoustic Techniques
- Organic Light-Emitting Diodes Research
- Organic Electronics and Photovoltaics
- Martial Arts: Techniques, Psychology, and Education
- Robotics and Sensor-Based Localization
- Photoacoustic and Ultrasonic Imaging
- Image Retrieval and Classification Techniques
- Fiber-reinforced polymer composites
- Infrared Thermography in Medicine
- Iterative Learning Control Systems
Xidian University
2016-2025
Xinjiang University
2025
Nanjing University of Finance and Economics
2024
China University of Mining and Technology
2024
Beijing Normal University
2024
Obstetrics and Gynecology Hospital of Fudan University
2020-2023
Powerchina Huadong Engineering Corporation (China)
2022
Qilu University of Technology
2021
Shandong Academy of Sciences
2021
Xi'an University of Technology
2012
Recently, autoencoder-based hyperspectral anomaly detection methods have demonstrated excellent performance on images (HSIs). The autoencoder (AE) can simultaneously reconstruct both the targets and background, but lack of prior information limits ability to detect anomalies. This study proposes a novel method based guided AE reduce feature representation for targets. First, multi-layer network with skip connections is proposed fully extract abundant latent features from HSIs enhance...
Autoencoders (AEs) are central to hyperspectral anomaly detection, given their impressive efficacy. However, the current methodologies often neglect global pixel similarity of image (HsI), thereby limiting reconstruction accuracy. This study introduces an innovative pixel-associated AE approach that leverages associations augment detection. First, a dictionary construction methodology was introduced based on superpixel distance estimation construct distinct dictionaries for background and...
The aim of infrared and visible image fusion is to obtain an integrated that contains obvious object information high spatial resolution background information. more conductive for a human or machine understand mine the contained in image. To attain this purpose, algorithm based on multi-level Gaussian curvature filtering (MLGCF) decomposition proposed. First, MLGCF presented employed decompose input source images into three different layers: small-scale, large-scale, base layers. Then,...
Over the last two decades, anomaly detection (AD) has been known to play a critical role in hyperspectral image analysis, which provides new way distinguish targets from background without prior knowledge. Recently, representation-based methods were proposed and soon became significant type of on AD. In this paper, novel AD algorithm based convolutional neural network (CNN) low-rank representation (LRR) is proposed. First, CNN model built trained (HSI) datasets accurately obtain resulting...
Hyperspectral anomaly detection is a challenging task due to the inaccurate evaluation of background statistics and contamination pixels. In this paper, we propose an effective hyperspectral algorithm based on local joint subspace process support vector machine (SVM). The method mainly consists three steps. At first, in process, combine Mahalanobis distance spectral angular projection by sliding change dual windows. With spatial-spectral information jointly utilized score also obtained....
Anomaly detection (AD) in hyperspectral target is of particular interest because no prior knowledge ground object spectra required. However, it difficult to utilize the salient features image (HSI) and mitigate effects noise AD, which greatly limits performance. Here, we report a strategy implement AD by visual attention model background subtraction with adaptive weight. Through band selection method, most discriminating bands are selected as input images for subsequent processing. Then,...
Infrared and visible image fusion technique is a popular topic in analysis because it can integrate complementary information obtain reliable accurate description of scenes. Multiscale transform theory as signal representation method widely used fusion. In this paper, novel infrared proposed based on spectral graph wavelet (SGWT) bilateral filter. The main novelty study that SGWT for On the one hand, source images are decomposed by its domain. approach not only effectively preserves details...
The advent of hyperspectral cameras has popularized the study video trackers. Although images can better distinguish targets compared to their RGB counterparts, occlusion and rotation target affect effectiveness target. For instance, obscures target, reducing tracking accuracy even causing failure. In this regard, paper proposes a novel tracker where double Siamese network (D-Siam) forms basis framework. Moreover, AlexNet serves as backbone D-Siam. current also adopts...
Existing deep learning-based hyperspectral anomaly detection methods typically perform by reconstructing a clean background. However, for the networks, there are many parameters that need to be adjusted. To reduce of network and improve performance detection, light CNN based on residual learning background estimation was proposed. Different from traditional methods, proposed method could directly learn features rather than features. First, during training stage, non-central convolution...
Abstract Covalent organic frameworks (COFs) are widely studied for hydrogen peroxide (H₂O₂) photosynthesis, with 3D COFs standing out their porous structures and chemical stability. However, the difficult preparation of low efficiency in separating photo‐generated electrons holes (e − h + ) limits efficient production H 2 O . In this study, two kinds [6+3] (XJU‐1, XJU‐2) significant charge separation, achieving record‐breaking H₂O₂ photocatalysis rates 34 777 11 922 µmol g⁻¹ h⁻¹,...
The aim of multi-focus image fusion technology is to integrate different partially focused images into one all-focused image. To realize this goal, a new method based on guided filter proposed and an efficient salient feature extraction presented in paper. Furthermore, primarily the main objective present work. Based extraction, first used acquire smoothing containing most sharpness regions. obtain initial map, we compose mixed focus measure by combining variance intensities energy gradient...
Fusion of infrared and visible images is a significant research area in image analysis computer vision. The purpose fusion to combine the complementary information source into fused image. Thus, it vital efficiently represent important choose rational rules. To achieve this aim, an method using multiscale directional nonlocal means (MDNLM) filter proposed paper. MDNLM combines feature preserving edge by with capacity capturing bank, which can effectively intrinsic geometric structure images....