Blar i NTNU Open på forfatter "Zhu, Hu"
-
Bilateral Weighted Regression Ranking Model with Spatial-Temporal Correlation Filter for Visual Tracking
Zhu, Hu; Peng, Hao; Xu, Guoxia; Deng, Lizhen; Cheng, Yueying; Song, Aiguo (Peer reviewed; Journal article, 2021)Many discriminative correlation filter (DCF)-based methods have successfully leveraged the guidance for solving two problems (i.e., the boundary effect and temporal filtering degradation) as a model prior to visual tracking. ... -
Dual Calibration Mechanism based L2,p-Norm for Graph Matching
Yu, Yu-Feng; Xu, Guoxia; Huang, Ke-Kun; Zhu, Hu; Chen, Long; Wang, Hao (Peer reviewed; Journal article, 2020)Unbalanced geometric structure caused by variations with deformations, rotations and outliers is a critical issue that hinders correspondence establishment between image pairs in existing graph matching methods. To deal ... -
A Dual Stream Spectrum Deconvolution Neural Network
Deng, Lizhen; Xu, Guoxia; Dai, Yanyu; Zhu, Hu (Peer reviewed; Journal article, 2021)With the development of spectral detection and photoelectric imaging, multi-band spectrum is always degraded by the random noise and band overlap during the acquisition of spectrum devices. Owing to the fixed spectrum ... -
Entropy-Driven Morphological Top-Hat Transformation for Infrared Small Target Detection
Deng, Lizhen; Xu, Guoxia; Zhang, Jieke; Zhu, Hu (Peer reviewed; Journal article, 2022)Infrared small target detection is a key technique in an infrared system. In the past decade, many methods have concentrated on traditional top-hat transformation, which relies on the hand-crafted shape and value of ... -
Flexible Subspace Clustering: A Joint Feature Selection and K-Means Clustering Framework
Long, Zhong-Zhen; Xu, Guoxia; Du, Jiao; Zhu, Hu; Yan, Taiyu; Yu, Yu-Feng (Peer reviewed; Journal article, 2021)Regarding as an important computing paradigm, cloud computing is to address big and distributed databases and rather simple computation. In this paradigm, data mining is one of the most important and fundamental problems. ... -
A Generalized Low-Rank Double-Tensor Nuclear Norm Completion Framework for Infrared Small Target Detection
Deng, Lizhen; Xu, Dongyuan; Xu, Guoxia; Zhu, Hu (Peer reviewed; Journal article, 2022)Infrared small target detection is a research hotspot in computer vision technology that plays an important role in infrared early warning systems. Specifically, infrared images with strong background clutter and noise ... -
Infrared small target detection via adaptive M-estimator ring top-hat transformation
Deng, Lizhen; Zhang, Jieke; Xu, Guoxia; Zhu, Hu (Peer reviewed; Journal article, 2021)Top-Hat transformation is an essential technology in the field of infrared small target detection. Many modified Top-Hat transformation methods have been proposed based on the different structure of structural elements. ... -
Learning the Distribution-Based Temporal Knowledge With Low Rank Response Reasoning for UAV Visual Tracking
Xu, Guoxia; Wang, Hao; Zhao, Meng; Pedersen, Marius; Zhu, Hu (Peer reviewed; Journal article, 2022)In recent years, the constraint based correlation filter has shown good performance in unmanned aerial vehicle (UAV) tracking, which gains a lot popularity in many intelligence transportation applications. In this work, a ... -
Multimodal Fusion Method Based on Self-Attention Mechanism
Zhu, Hu; Wang, Ze; Shi, Yu; Hua, Yingying; Xu, Guoxia; Deng, Lizhen (Peer reviewed; Journal article, 2020)Multimodal fusion is one of the popular research directions of multimodal research, and it is also an emerging research field of artificial intelligence. Multimodal fusion is aimed at taking advantage of the complementarity ... -
PcGAN: A Noise Robust Conditional Generative Adversarial Network for One Shot Learning
Deng, Lizhen; He, Chunming; Xu, Guoxia; Zhu, Hu; Wang, Hao (Peer reviewed; Journal article, 2022)Traffic sign classification plays a vital role in autonomous vehicles for its powerful capability in information representation. However, the low-quality data of traffic signs captured by in-vehicle cameras often inevitably ... -
RoDeRain: Rotational Video Derain via Nonconvex and Nonsmooth Optimization
Deng, Lizhen; Xu, Guoxia; Zhu, Hu; Bao, Bing-Kun (Peer reviewed; Journal article, 2021)Video derain is an important issue in the field of digital image processing and computer vision. This paper divides rain streaks into two types: one is rain in natural scenes, and the other is rain in stochastic scenes. ... -
Tensor field Graph-Cut for Image Segmentation: A Non-convex Perspective
Zhu, Hu; Zhang, Jieke; Xu, Guoxia; Deng, Lizhen (Peer reviewed; Journal article, 2020)Image segmentation is a key component of image analysis, which refers to the process of partitioning the image into multiple segments. Graph cut is widely used in image segmentation by constructing a graph that the minimal ... -
TV2++: a novel spatial-temporal total variation for super resolution with exponential-type norm
Deng, Lizhen; Zhou, Zhetao; Xu, Guoxia; Zhu, Hu; Bao, Bing-Kun (Peer reviewed; Journal article, 2020)Recently, many super-resolution algorithms have been proposed to recover high-resolution images to improve visualization and help better analyze images. Among them, total variation regularization (TV) methods have been ... -
Video smoke removal based on low‐rank tensor completion via spatial‐temporal continuity constraint
Zhu, Hu; Xu, Guoxia; Liu, Lu; Deng, Lizhen (Journal article; Peer reviewed, 2021)Smoke has a very bad effect on the outdoor vision system. Not only are the videos with poor visual effects obtained, but also the quality and structure of the videos are reduced. In this paper, we propose a video smoke ... -
When Infrared Small Target Detection Meets Tensor Ring Decomposition: A Multiscale Morphological Framework
Deng, Lizhen; Song, Jie; Xu, Guoxia; Zhu, Hu (Peer reviewed; Journal article, 2022)Detecting the small targets from a heterogeneous background in an infrared image is a challenging problem, which has received extensive attention. In this article, we propose a method in terms of tensor ring (TR) decomposition ...