检索结果-内蒙古大学图书馆

Robust video stabilisation algorithm using feature point selection and delta optical flow

IET computer vision 2009年第4期3卷 176-188页

作者： Cai, J. Walker, R. Queensland Univ Technol Sch Engn Syst ARCAA Brisbane Qld 4001 Australia

In this study, the authors propose a novel video stabilisation algorithm for mobile platforms with moving objects in the scene. The quality of videos obtained from mobile platforms, such as unmanned airborne vehicles, suffers from jitter caused by several factors. In order to remove this undesired jitter, the accurate estimation of global motion is essential. However, it is difficult to estimate global motions accurately from mobile platforms because of increased estimation errors and noises. Additionally, large moving objects in the video scenes contribute to the estimation errors. Currently, only very few motion estimation algorithms have been developed for video scenes collected from mobile platforms, and this study shows that these algorithms fail when there are large moving objects in the scene. In this study, a theoretical proof is provided which demonstrates that the use of delta optical flow can improve the robustness of video stabilisation in the presence of large moving objects in the scene. The authors also propose to use sorted arrays of local motions and the selection of feature points to separate outliers from inliers. The proposed algorithm is tested over six video sequences, collected from one fixed platform, four mobile platforms and one synthetic video, of which three contain large moving objects. Experiments show that our proposed algorithm performs well to all these video sequences.

关键词： computer vision and image processing techniques feature point selection Video signal processing global motion estimation feature extraction delta optical flow Optical, image and video signal processing image sequences robust video stabilisation algorithm video signal processing video sequences motion estimation

来源：评论

学校读者我要写书评

暂无评论

Compression artifact reduction of low bit-rate videos via deep neural networks using self-similarity prior

引用

IET image processing 2023年第2期17卷 480-491页

作者： Liu, Dongsheng Yu, Runyi Chen, Wei-Gang Zhejiang Gongshang Univ Sch Comp & Informat Engn Hangzhou 0011 Peoples R China Eastern Mediterranean Univ Dept Elect & Elect Engn Gazimagusa Turkey

This paper presents a hybrid scheme that integratedly uses self-similarity prior and deep convolutional neural network (CNN) fusion for compression artifact reduction in low bit-rate video applications. Based on the temporal correlation hypothesis, the self-similarity prior is extended to the temporal domain by using as references not only the current decoded frame but also its neighbouring frames. Furthermore, being cognizant of that the bicubic downsampling process can typically improve the perceptual quality of a video coded at low bit-rate, for each small patch in the current frame, we search for similar patches in down-scaled versions of these references, and then form several self-similarity prior based predictions by tiling these similar patches at corresponding positions. To further exploit information flow across scales, a deep CNN model is constructed that contains two sub-networks to estimate the final output. One sub-network takes the self-similarity prior based predictions along with the decoded frame itself;and the other takes the down-scaled versions of these frames as network input. Experimental results demonstrate that the proposed method can remarkably improve, both subjectively and objectively, quality of compressed video sequences of low bit-rates.

关键词： low bit-rate video applications video signal processing neighbouring frames image and video coding Neural nets video coding deep neural networks Optical, image and video signal processing computer vision and image processing techniques convolutional neural nets current decoded frame self-similarity prior based predictions deep learning (artificial intelligence) deep CNN model data compression image sequences Video signal processing temporal domain low bit-rate videos image resolution network input compressed video sequences temporal correlation hypothesis compression artifact reduction

来源：评论

学校读者我要写书评

暂无评论

An efficient local stereo matching method based on an adaptive exponentially weighted moving average filter in SLIC space

引用

IET image processing 2021年第8期15卷 1722-1732页

作者： Yang, Shan Lei, Xinyue Liu, Zhenfeng Sui, Guorong Univ Shanghai Sci & Technol Sch Opt & Comp Engn 516 JunGong Rd Shanghai 200093 Peoples R China

Rapidly obtaining accurate dense disparity maps has been the focus of stereo matching research. At present, approaches that achieve superior disparity maps require a large amount of computation, which is not suitable for practical applications. To address this issue, this paper proposes an efficient local matching method based on an adaptive exponentially weighted moving average filter and simple linear iterative clustering segmentation algorithm. First, an effective matching cost is introduced to adaptively integrate absolute intensity difference with Census transform, which is robust against texture free and luminance variate. Following this, during the cost aggregation, the exponentially weighted moving average filter and the SLIC segmentation are combined to handle the problems of computing consumption and adaptive expansion of the cost aggregation window. Finally, the dense disparity map is obtained by a winner-takes-all approach and disparity refinement. To demonstrate its efficiency and validity, the method is quantitatively tested and compared to existing approaches on the Middlebury benchmark. The results show that it has a non-occlusion accuracy of 90.66% and an average runtime of 7.01 s on the 2014 Middlebury dataset. Compared with existing competitive methods, the proposed method achieves superior matching results with a lower time cost.

关键词： Optical, image and video signal processing image recognition Filtering methods in signal processing computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

High energy flash X-ray image restoration using region extrema and kernel optimization

引用

IET image processing 2021年第12期15卷 2970-2985页

作者： Wang, Xiaolin Li, Qingwu Xu, Jinxin Hohai Univ Coll Internet Things Engn Changzhou Jiangsu Peoples R China Key Lab Changzhou Sensor Networks & Environm Sens Changzhou Jiangsu Peoples R China 724 Res Inst CSIC Nanjing Jiangsu Peoples R China

The quality of high energy flash X-ray images is crucial to the high-precision diagnosis of object density. High energy flash X-ray radiography is susceptible to the system blur, which usually causes the poor quality of static images. In response to this, a novel restoration algorithm using region extrema and kernel optimization (REKO) is presented. Based on the observation that the region extrema distribution of blurred high energy flash X-ray images deviates from opposite ends of image grey domain, the sparseness-inducing prior for regularizing image region extrema is applied to construct the restoration model. Considering the sparse characteristics of blur kernels, the sparseness-inducing regularization is incorporated to constrain blur kernels in the restoration model. The non-convex and non-linear objective function is gradually minimized through energy alternating minimization and dually linear approximation. Furthermore, a continuity enforced kernel optimization algorithm is proposed to estimate more accurate blur kernels. The discontinuous kernel elements are suppressed by extracting the main structure of blur kernels and constructing kernel continuity function in cross windows. Experimental results demonstrate that our algorithm can more accurately estimate blur kernels and achieve restoration results with sharper edges on high energy flash X-ray images.

关键词： Numerical approximation and analysis Sonic and ultrasonic radiation (medical uses) Optical, image and video signal processing Sonic and ultrasonic radiation (biomedical imaging/measurement) Optimisation techniques Interpolation and function approximation (numerical analysis) computer vision and image processing techniques Optimisation techniques Interpolation and function approximation (numerical analysis) Patient diagnostic methods and instrumentation Biology and medical computing

来源：评论

学校读者我要写书评

暂无评论

Mixed Poisson Gaussian noise reduction in fluorescence microscopy images using modified structure of wavelet transform

引用

IET image processing 2021年第7期15卷 1383-1398页

作者： Rasal, Tushar Veerakumar, Thangaraj Subudhi, Badri Narayan Esakkirajan, Sankaralingam Natl Inst Technol Goa Dept Elect & Commun Engn Ponda 403401 Goa India Indian Inst Technol Jammu Dept Elect Engn Nagrota 181221 Jammu & Kashmir India PSG Coll Technol Dept Instrumentat & Control Syst Engn Coimbatore 641004 Tamil Nadu India

Fluorescence microscopy is an important investigation tool of discoveries in the field of biological sciences where the imaging phenomena are limited by the noise. This paper introduces the integration of biorthogonal wavelet filters along with mixed Poisson-Gaussian unbiased risk estimate (MPGURE) based subband adaptive thresholding function for the restoration of low photon count microscopy images. The proposed algorithm consists of four steps. In the first step, variance stabilization transform along with a multi-scale Wiener filtering approach is used to filter out the noise and blurring effect. In the second step, deconvolved images are further decomposed by the biorthogonal wavelet filters. The modified wavelet subband structure is used for the identification of noisy and noise-free subbands. In the next stage, different noisy coefficients are thresholded using the MPGURE-based thresholding operation. The different thresholded images are combined along with different optimum coefficients. Finally, inverse variance stabilization transformation is applied to obtain the final restored output. Performance of the proposed algorithm is tested on 14 different benchmark image data sets with performance evaluation measures like signal-to-noise ratio, peak signal-to-noise ratio, mean structural similarity index measur, and correlation coefficient. Simulation results of the proposed algorithm claim better results than other state-of-the-art techniques.

关键词： Optical, image and video signal processing Filtering methods in signal processing Interpolation and function approximation (numerical analysis) computer vision and image processing techniques Integral transforms Other topics in statistics Interpolation and function approximation (numerical analysis) Integral transforms Other topics in statistics Patient diagnostic methods and instrumentation Biology and medical computing

来源：评论

学校读者我要写书评

暂无评论

Selective focus saliency model driven by object class-awareness

引用

IET image processing 2021年第6期15卷 1332-1344页

作者： Zhao, Danpei Yuan, Bo Shi, Zhenwei Jiang, Zhiguo Beihang Univ Sch Astronaut Image Proc Ctr Beijing 100191 Peoples R China Beihang Univ Beijing Key Lab Digital Media Beijing Peoples R China Beihang Univ Key Lab Spacecraft Design Optimizat & Dynam Simul Minist Educ Beijing Peoples R China

Current many salient object detection (SOD) models only focus on highlighting visual conspicuous region but fail to make saliency detection for specific targets. In this paper, a selective focus saliency model driven by object class-awareness (SF-OCA) to run saliency detection is proposed. The framework consists of a visual saliency detection flow, a segmentation-classification flow, and a class-awareness selection module. It combines bottom-up visual perception with a top-down task-driven manner, which is capable of detecting specific category salient targets and eliminating the interference from other saliency areas, providing a new idea for saliency detection. Experimental results show that the method achieves comparable performance with state-of-the-art models on four public saliency datasets. In addition, a new dataset was also built to test the proposed framework for the selective focus saliency detection. Compared with other SOD methods, the method not only highlights visual saliency regions but can choose more important or more noteworthy targets in a class-awareness manner. The method also shows better robustness under a variety of conditions including multi-targets, small targets and complex background.

关键词： image recognition computer vision and image processing techniques

来源：评论

学校读者我要写书评

暂无评论

Technique to correct yellowing and foxing in antique books

引用

IET image processing 2007年第2期1卷 123-133页

作者： Stanco, F. Tenze, L. Ramponi, G. Univ Catania Dipartimento Matemat & Informat I-95125 Catania Italy Univ Trieste Dipartimento Eletrotecn Elettron & Informat I-34127 Trieste Italy

New algorithms for the automatic restoration of antique documents affected by foxing and by yellowing deterioration processes are proposed in the paper. The physical restoration of such objects is both expensive and hard to carry out by nonspecialised library personnel. The proposed algorithms ensure fast and less expensive results, and can be used also by nonqualified operators. Moreover, these techniques improve the performance of optical character recognition operators.

关键词： nonqualified operators computer vision and image processing techniques automatic restoration deterioration processes Optical, image and video signal processing optical character recognition image restoration foxing Document processing techniques yellowing humanities document image processing Humanities computing antique documents antique books

来源：评论

学校读者我要写书评

暂无评论

Contour evolution scheme for variational image segmentation and smoothing

引用

IET image processing 2007年第3期1卷 287-294页

作者： Mahmoodi, S. Sharif, B. S. Newcastle Univ Sch Psychol Psychol Div Newcastle Upon Tyne NE2 4HH Tyne & Wear England Newcastle Univ Sch Elect Elect & Comp Engn Newcastle Upon Tyne NE1 7RU Tyne & Wear England

An algorithm, based on the Mumford-Shah (M-S) functional, for image contour segmentation and object smoothing in the presence of noise is proposed. However, in the proposed algorithm, contour length minimisation is not required and it is demonstrated that the M-S functional without contour length minimisation becomes an edge detector. Optimisation of this nonlinear functional is based on the method of calculus of variations, which is implemented by using the level set method. Fourier and Legendre's series are also employed to improve the segmentation performance of the proposed algorithm. The segmentation results clearly demonstrate the effectiveness of the proposed approach for images with low signal-to-noise ratios.

关键词： edge detection Fourier series image recognition variational image segmentation contour evolution scheme signal-to-noise ratio computer vision and image processing techniques minimisation optimisation Optimisation techniques contour length minimisation edge detector image smoothing Mumford-Shah functional image segmentation Legendre series

来源：评论

学校读者我要写书评

暂无评论

Blur identification with assumption validation for sensor-based video reconstruction and its implementation on field programmable gate array

引用

IET computerS AND DIGITAL techniques 2011年第4期5卷 271-286页

作者： Angelopoulou, M. E. Bouganis, C-S. Cheung, P. Y. K. Univ London Imperial Coll Sci Technol & Med Dept Elect & Elect Engn London SW7 2BT England

Restoration methods, such as super-resolution (SR), largely depend on the accuracy of the point spread function (PSF). PSF estimation is an ill-posed problem, and a linear and uniform motion is often assumed. In real-life systems, this may deviate significantly from the actual motion, impairing subsequent restoration. To address the above, this work proposes a dynamically configurable imaging system that combines algorithmic video enhancement, field programmable gate array (FPGA)-based video processing and adaptive image sensor technology. Specifically, a joint blur identification and validation (BIV) scheme is proposed, which validates the initial linear and uniform motion assumption. For the cases that significantly deviate from that assumption, the real-time reconfiguration property of an adaptive image sensor is utilised, and the sensor is locally reconfigured to larger pixels that produce higher frame-rate samples with reduced blur. Results demonstrate that once the sensor reconfiguration gives rise to a valid motion assumption, highly accurate PSFs are estimated, resulting in improved SR reconstruction quality. To enable real-time reconstruction, an FPGA-based BIV architecture is proposed. The system's throughput is significantly higher than 25 fps, for frame sizes up to 1024 x 1024, and its performance is robust to noise for signal-to-noise ratio (SNR) as low as 20 dB.

关键词： adaptive image sensor technology algorithmic video enhancement Video signal processing Logic and switching circuits point spread function imaging techniques autocorrelation-based blur identification framework Logic circuits image reconstruction sensor-based video reconstruction method field programmable gate arrays passive cameras Optical, image and video signal processing high-throughput hardware architecture computer vision and image processing techniques image enhancement field programmable gate array image motion analysis joint blur identification and validation scheme image sensors improved SR reconstruction quality image sensors system throughput signal-to-noise ratio

来源：评论

学校读者我要写书评

暂无评论

Double-weighted patch-based label fusion for MR brain image segmentation

引用

IET image processing 2021年第1期15卷 218-227页

作者： Yan, Meng Jin, Huazhong Zhao, Zhiqiang Xia, Dahai Pan, Ning Hubei Univ Technol Sch Comp 28 Nanli Rd Wuhan 430068 Hubei Peoples R China Hubei Key Lab Med Informat Anal Tumor Diag & Trea Wuhan Peoples R China Jiujiang Univ Sch Informat Sci & Technol Jiujiang Peoples R China South Cent Univ Nationalities Coll Biomed Engn Wuhan Peoples R China

In recent decades, a large number of label fusion methods have been introduced and applied to magnetic resonance brain image segmentation. This paper proposes a double-weighted label fusion method to improve the segmentation accuracy of magnetic resonance brain tissues. In weighted label fusion methods, different weights are utilised for different neighbouring pixels around the central test pixel. The weight of one specific neighbouring pixel is determined by the structural similarity between the patch of the atlas that centred in the neighbouring pixel and the patch of the image to be segmented that centred in the central test pixel, which is referred to as a patch-based label fusion scheme. This paper presents a double-weighted label fusion method to improve the segmentation accuracy of magnetic resonance brain tissues. The proposed label fusion method adds another new type of weights to the neighbouring pixels around the central test pixel and this new type of weights are calculated based on the atlas information itself. Segmentation experiments of different brain tissues show that our method can improve the segmentation performance.

关键词： Optical, image and video signal processing Biomedical magnetic resonance imaging and spectroscopy computer vision and image processing techniques Other topics in statistics Other topics in statistics Medical magnetic resonance imaging and spectroscopy Patient diagnostic methods and instrumentation Biology and medical computing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：