- Advanced Image Fusion Techniques
- Remote-Sensing Image Classification
- Image and Signal Denoising Methods
- Advanced Vision and Imaging
- Advanced Data Compression Techniques
- Image Processing Techniques and Applications
- Video Coding and Compression Technologies
- Image Enhancement Techniques
- Advanced Steganography and Watermarking Techniques
- Advanced Image and Video Retrieval Techniques
- Advanced Image Processing Techniques
- Remote Sensing and Land Use
- Video Analysis and Summarization
- Photoacoustic and Ultrasonic Imaging
- Visual Attention and Saliency Detection
- Image Retrieval and Classification Techniques
- Chaos-based Image/Signal Encryption
- Video Surveillance and Tracking Methods
- Advanced Measurement and Detection Methods
- Advanced Numerical Analysis Techniques
- Image and Video Stabilization
- Sparse and Compressive Sensing Techniques
- Digital Image Processing Techniques
- CCD and CMOS Imaging Sensors
- Medical Image Segmentation Techniques
Dalian University
2024-2025
Liaoning Normal University
2014-2024
Nanjing University
2008-2021
Dalian University of Technology
2019-2021
Nanjing University of Science and Technology
2006-2010
Previous video summarization studies focused on monocular videos, and the results would not be good if they were applied to multi-view videos directly, due problems such as redundancy in multiple views. In this paper, we present a method for summarizing videos. We construct spatio-temporal shot graph formulate problem labeling task. The is derived from hypergraph, which encodes correlations with different attributes among shots hyperedges. then partition identify clusters of event-centered...
The application of hyperspectral image (HSI) is more and extensive, but the lower spatial resolution seriously affects its effect. Using low-resolution (LR-HSI) high-resolution multispectral (MSI) fusion technology to achieve super-resolution reconstruction HSI has become a mainstream method. However, most existing methods do not make full use large-scale range remote sensing images, neglect preservation spatial-spectral information in process. Considering that spectral fused (HR-HSI) mainly...
The high spectral resolution of hyperspectral (HS) images provides the possibility omnidirectional feature identification objects. However, high-dimensional features and redundancy information properties make data processing application HS extremely challenging. Thus, effectively expressing correlating intrinsic correlations by establishing a statistical model is great significance. This article proposes nonsubsampled shearlet transform hidden Markov forest (NSST-HMF) model. new approach has...
The nonsubsampled Contourlet transform (NSCT) not only retains the characteristics of transform, but also has good characteristic shift-invariance, which plays a significant role in denoising, fusion, and segmentation texture-rich images. NSCT properties important property image processing, such as This paper proposes Gaussian-Cauchy mixture distribution-based hidden Markov tree model (GC-NSCT-HMT). specific form distribution is determined by kurtosis coefficients each subband. First, we...
Bad weather reduces the imaging quality of intelligent vision system, such as haze and fog. Thus, removal has received wide attention from researchers. Most algorithms often suffer color distortion edge loss when dealing with images containing large areas sky. In this paper, we propose an effective dehazing method. The iterative threshold segmentation is used to segment sky region out image, then brightness adjusted increase clarity. improved dark channel priori process rest regions....
Pan-sharpening is an important means to improve the spatial resolution of multispectral (MS) images. Although a large number pan-sharpening methods have been developed, improving MS while effectively maintaining its spectral information has not well solved so far, and it also taken as criterion measure whether sharpened product can meet practical needs. The back-projection (BP) method iteratively injects backwards into results in post-processing manner, which generally unsatisfied...
With the maturity and popularization of high-performance sensor technology, it is now possible to acquire huge amounts very high-resolution (VHR) remote sensing images. The change detection (CD) for VHR images currently receiving special attention earth observation applications, however, as a hot research field, needs be studied in depth improve accuracy fine changes. To this end, full-scale gated message passing framework (GaMPF) based on collaborative estimation image proposed paper. On...
Current remote sensing hardware technology is not yet able to acquire multiband images with both high spatial and spectral resolution. As an important tool compensate for the lack of information acquisition multispectral (MS) images, pan-sharpening has been continuously active research area in image processing. Although many methods have emerged, problem how obtain resolution while effectively maintaining MS well solved. Many aspects still need further research. In this article, we first...
This paper proposes a new hyperspectral image compressed sensing model (hyperspectral col-
Abstract In this paper, the generation method of medial axis in arbitrary quadrilateral surface is proposed. It can provide a solution for simplification complex fillet feature and mesh model. By using locus associated with moving Frenet frame, we realize simple fast algorithm generating axis. As engineering problem, B-rep 3D solid models clear boundary definition are mostly applied; information vertex, side model, which clearly stored model file, be used to simplify traditional axis, order...