检索结果-内蒙古大学图书馆

Motion Multi-object Detection Method under Complex Environment

Motion Multi-object Detection Method under Complex Environme...

International Conference on Industrial Informatics, Computing Technology, Intelligent Technology, Industrial Information Integration (ICIICII)

作者： Zi-Xiao Pan Mei Wang School of Automation Wuhan University of Technology Wuhan China Yantai Vocational College Laboratory of Image Processing &Pattem Recognition Yantai China

ISBN: (纸本)9781509035762

An optimization object detection method based on color image symmetrical frame-difference is proposed in order to solve the problem of motion multi-object detection difficult under complex environment. In this paper, firstly the color images distance is defined to calculate the frame-difference between two adjacent images. Then the before and after symmetrical image-distance of three adjacent images in difference frame interval step can be completed respectively. Secondly, an optimization binary method is designed to extract more object pixels. And the before and after object binary results of the adjacent images with the same middle (key frame) image are given respectively. At last, motion multi-object of the key frame image is achieved by the fusion result of logical AND between the before and after object binary results depending on three-frame-adjacent images with the same key frame. Actual color images from traffic surveillance system are used to test, the experimental result shows that the optimization object detection algorithm based on symmetrical frame difference in the proper step can extract motion multi-objects in different movement speed under complex environment and its accuracy and effectiveness of the proposed algorithm are verified.

关键词： Object detection Color image edge detection Optimization Surveillance Traffic control Motorcycles

来源：评论

学校读者我要写书评

暂无评论

A simple but effective denoising algorithm in projection domain of CBCT 8th

A simple but effective denoising algorithm in projection dom...

引用

8th International Conference on image and Graphics, ICIG 2015

作者： Chang, Shaojie Zhang, Yanbo Bai, Ti Chen, Xi Xu, Qiong Mou, Xuanqin Institute of Image Processing and Pattern Recognition Xi’an Jiaotong University Xi’anShaanxi710049 China

ISBN: (纸本)9783319219776

There are growing concerns on the potential side effect of radiation, which could be decreased by lowering the tube current. However, this manner will lead to a degraded image since X-ray imaging is a quantum accumulation process. Great efforts have been devoted to alleviate this problem. In this paper, a simple Wiener filter was employed to denoise projection data in detector domain. And then an enhancement filter was exploited to strengthen small structures. As a consequence, this combination leaded to a reconstruction with good trade-off between noise and resolution. For the purpose of comparison, block-matching and 3D/4D denoising algorithm (BM3D/BM4D) were also adopted to denoise the projections. Experimental results demonstrated that the proposed algorithm could deliver a reconstruction with comparable quality as BM4D algorithm while better than that of BM3D denoising algorithm. Note that the propose algorithm has a much higher computation efficiency than BM3D/BM4D, and hence provides an insight into the clinical utility where real time is of high importance. © Springer International Publishing Switzerland 2015.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Patch-based Object Tracking via Locality-constrained Linear Coding

Patch-based Object Tracking via Locality-constrained Linear ...

引用

第35届中国控制会议

作者： Kunqi Gu Mingna Liu Tao Zhou Fanghui Liu Xiangjian He Jie Yang Yu Qiao Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai Institute of Spaceflight Control Technology Infrared Detection Technology Research and Development Center China Aerospace Science and Technology Corporation School of Computing and Communications University of Technology The Key Laboratory of Ministry of Education for System Control and Information Processing

ISBN: (纸本)9781509009107

In this paper,the Locality-constrained Linear Coding(LLC) algorithm is incorporated into the object tracking ***,we extract local patches within a candidate and then utilize the LLC algorithm to encode these *** on these codes,we exploit pyramid max pooling strategy to generate a richer feature *** feature histogram which integrates holistic and part-based features can be more discriminative and ***,an occlusion handling strategy is utilized to make our tracker more ***,an efficient graph-based manifold ranking algorithm is exploited to capture the relevance between target templates and *** tracking,target templates are taken as labeled nodes while target candidates are taken as unlabeled nodes,and the goal of tracking is to search for the candidate that is the most relevant to existing labeled nodes by manifold ranking *** on challenging video sequences have demonstrated the superior accuracy and robustness of the proposed method in comparison to other state-of-the-art baselines.

关键词： object tracking LLC pyramid max-pooling local appearance model manifold ranking

来源：评论

学校读者我要写书评

暂无评论

Low dose CT image denoising using a generative adversarial network with wasserstein distance and perceptual loss

arXiv

引用

arXiv 2017年

作者： Yang, Qingsong Yan, Pingkun Zhang, Yanbo Yu, Hengyong Shi, Yongyi Mou, Xuanqin Kalra, Mannudeep K. Zhang, Yi Sun, Ling Wang, Ge Department of Biomedical Engineering Rensselaer Polytechnic Institute TroyNY12180 United States Department of Electrical and Computer Engineering University of Massachusetts Lowell LowellMA01854 United States Institute of Image Processing and Pattern Recognition Xian Jiaotong University Xian Shaanxi710049 China Department of Radiology Massachusetts General Hospital Harvard Medical School BostonMA United States College of Computer Science Sichuan Universiyt Chengdu610065 China Department of Radiology West China Hospital Sichuan University Chengdu610041 China

The continuous development and extensive use of CT in medical practice has raised a public concern over the associated radiation dose to the patient. Reducing the radiation dose may lead to increased noise and artifacts, which can adversely affect the radiologists judgement and confidence. Hence, advanced image reconstruction from low-dose CT data is needed to improve the diagnostic performance, which is a challenging problem due to its ill-posed nature. Over the past years, various low-dose CT methods have produced impressive results. However, most of the algorithms developed for this application, including the recently popularized deep learning techniques, aim for minimizing the mean-squared-error (MSE) between a denoised CT image and the ground truth under generic penalties. Although the peak signal-to-noise ratio (PSNR) is improved, MSE-or weighted-MSE-based methods can compromise the visibility of important structural details after aggressive denoising. This paper introduces a new CT image denoising method based on the generative adversarial network (GAN) with Wasserstein distance and perceptual similarity. The Wasserstein distance is a key concept of the optimal transport theory, and promises to improve the performance of GAN. The perceptual loss suppresses noise by comparing the perceptual features of a denoised output against those of the ground truth in an established feature space, while the GAN focuses more on migrating the data noise distribution from strong to weak statistically. Therefore, our proposed method transfers our knowledge of visual perception to the image denoising task and is capable of not only reducing the image noise level but also trying to keep the critical information at the same time. Promising results have been obtained in our experiments with clinical CT images. Copyright © 2017, The Authors. All rights reserved.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

Reeb graphs through local binary patterns 10

Reeb graphs through local binary patterns

引用

10th IAPR-TC-15 International Workshop on Graph-Based Representations in pattern recognition, GbRPR 2015

作者： Janusch, Ines Kropatsch, Walter G. Pattern Recognition and Image Processing Group Institute of Computer Graphics and Algorithms Vienna University of Technology Vienna Austria

ISBN: (纸本)9783319182230

This paper presents an approach to derive critical points of a shape, the basis of a Reeb graph, using a combination of a medial axis skeleton and features along this skeleton. A Reeb graph captures the topology of a shape. The nodes in the graph represent critical points (positions of change in the topology), while edges represent topological persistence. We present an approach to compute such critical points using Local Binary patterns. For one pixel the Local Binary pattern feature vector is derived comparing this pixel to its neighbouring pixels in an environment of a certain radius. We start with an initial segmentation and a medial axis representation. Along this axis critical points are computed using Local Binary patterns with the radius, defining the neighbouring pixels, set a bit larger than the radius according to the medial axis transformation. Critical points obtained in this way form the node set in a Reeb graph, edges are given through the connectivity of the skeleton. This approach aims at improving the representation of flawed segmented data. In the same way segmentation artefacts, as for example single pixels representing noise, may be corrected based on this analysis. © Springer International Publishing Switzerland 2015.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Robust weighted least squares for guided depth upsampling

Robust weighted least squares for guided depth upsampling

引用

IEEE International Conference on image processing

作者： Wei Liu Xiaogang Chen Jie Yang Qiang Wu Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University Shanghai China College of Communication and Art Design University of Shanghai for Science and Technology China School of Computing and Communications University of Technology Sydney Australia

ISBN: (纸本)9781467399623

In this paper, we propose a new guided depth upsampling method denoted as Robust Weighted Least Squares (RWLS). Our work is inspired by the connection between the Weighted Least Squares (WLS) and the Auto Regressive (AR) model. By adopting a new robust penalty function to model the smoothness of the proposed model, we show that the proposed method performs much better in preserving sharp depth discontinuities than previous work. Through both mathematical analysis and experimental results, we show that our method has promising performance on handling the inconsistency between the guidance image and the depth map in both preserving sharp depth discontinuities and suppressing the texture copy artifacts.

关键词： Robustness Interpolation Color image resolution Mathematical model Noise measurement image color analysis

来源：评论

学校读者我要写书评

暂无评论

An improved algorithm of search for compressive sensing image recovery based on lp norm

An improved algorithm of search for compressive sensing imag...

引用

Chinese Automation Congress, CAC 2015

作者： Yuan, Jiang Pei, Shen Ping, Zhao Yang, Daiji Zhen, Chen Jiangxi Province Key Laboratory of Image Processing and Pattern Recognition Nanchang330063 China College of Information Engineering Nanchang Hangkong University 330063 China

Compressed sensing theory by developing a signal sparse features, under the condition of far less than the Nyquist sampling rate, the correct signal is acquired with random sampling the discrete samples, and then thro... 详细信息

ISBN: (纸本)9781467371896

关键词： image reconstruction

来源：评论

学校读者我要写书评

暂无评论

image-based characterization of the pulp flows

引用

pattern recognition and image Analysis 2016年第3期26卷 630-637页

作者： Sorokin, M. Strokina, N. Eerola, T. Lensu, L. Karttunen, K. Kalviainen, H. Machine Vision and Pattern Recognition Laboratory School of Engineering Science Lappeenranta University of Technology PO Box 20 LappeenrantaFI-53851 Finland Computer Vision Group Department of Signal Processing Tampere University of Technology PO Box 527 TampereFI-33101 Finland Cemis-Oulu Unit of Measurement Technology Kajaani University Consortium University of Oulu PO Box 127 KajaaniFI-87400 Finland School of Information Technology Monash University Malaysia Jalan Lagoon Selatan Bandar Sunway Selangor Darul Ehsan46150 Malaysia

Material flow characterization is important in the process industries and its further automation. In this study, close-to-laminar pulp suspension flows are analyzed based on double-exposure images captured in laboratory conditions. The correlation-based methods including autocorrelation and the particle image pattern technique were studied. During the experiments, synthetic and real test data with manual ground truth were used. The particle image pattern matching method showed better performance achieving the accuracy of 90.0% for the real data set with linear motion of the suspension and 79.2% for the data set with flow distortions. © 2016, Pleiades Publishing, Ltd.

关键词： pattern matching

来源：评论

学校读者我要写书评

暂无评论

Small target detection using an optimization-based filter 40

Small target detection using an optimization-based filter

引用

40th IEEE International Conference on Acoustics, Speech, and Signal processing, ICASSP 2015

作者： Xie, Kai Fu, Keren Zhou, Tao Yang, Jie Wu, Qiang He, Xiangjian Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China School of Computing and Communications University of Technology Sydney Australia

ISBN: (纸本)9781467369978

Small target detection is a critical problem in the Infrared Search And Track (IRST) system. Although it has been studied for years, there are some challenges remained, e.g. cloud edges and horizontal lines are likely to cause false alarms. This paper proposes a novel method using an optimization-based filter to detect infrared small target in heavy clutter. First, we design a certain pixel area as active area. Second, a weighted quadratic cost function is performed in the active area. Finally, a filter based on statistics of active area is derived from the cost function. Our method could preserve heterogeneous area, meanwhile, remove target region. Experimental results show our method achieves satisfied performance in heavy clutter. © 2015 IEEE.

关键词： active area area statistics heavy clutter optimization-based filter small target detection

来源：评论

学校读者我要写书评

暂无评论

Impulse noise removal in two-dimensional electrophoresis images based on dome recognition 8

Impulse noise removal in two-dimensional electrophoresis ima...

引用

8th International Conference on BioMedical Engineering and Informatics, BMEI 2015

作者： Ou, Qiaofeng Zhang, Huisheng Li, Lixin Xiong, Bangshu School of Electronic Information Northwestern Polytechnical University Xi'an710072 Hong Kong Key Laboratory of Image Processing and Pattern Recognition of Jiangxi Province Nanchang Hangkong University Nanchang330063 China

ISBN: (纸本)9781509000227

Two-dimensional gel electrophoresis (2DE) images are often corrupted by impulse noise in broad sense (including various artifacts, such as fingerprints, hairs, gel cracks, strips, water stains, dust and so on). In this paper, we propose a novel adaptive directional filter (ADF) to remove impulse noise completely and accurately. Firstly, we detect the impulse noise based on the observation that the directional derivative distributions around the protein spot centers and noise pixels are very different. Then, according to the bell-shaped three-dimensional appearance of protein spots, the greatest and smallest gradient directions were used to restore the noised pixels. Lastly, the pixels adjacent to the modified pixels are iteratively detected and restored until no impulse noise is detected. Experimental results on the synthetic and real 2DE images show that the proposed method performs much better than the previous approaches. © 2015 IEEE.

关键词： Pixels

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：