检索结果-内蒙古大学图书馆

2nd international conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2018

作者： Hu, Junpeng Cao, Xinrong Chen, Xinwei Li, Zuoyong Zhang, Fuquan College of Mathematics and Computer Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

ISBN: (纸本)9783030045845

image dehazing is an important research topic in the field of image processing and computer vision. image dehazing aims to remove haze in images and make image scenes clearer. image dehazing based on dark channel prior is a currently popular type of methods. However, image dehazing results obtained by existing methods based on dark channel prior usually have color distortion and low brightness causing partial image details invisible. To alleviate this issue, we presented a modified method based on dark channel prior. First, the proposed method estimates the value of atmospheric light by using a quadtree algorithm, and uses the dark channel prior to pixelwisely estimate and optimize medium transmission. Second, the proposed method uses a classic atmospheric scattering model to generate an initial image dehazing result, and transforms the result from RGB (Red, Green, and Blue) color space to HSV (Hue, Saturation, and Value) color space. Finally, the proposed method conducts the CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm on the V component of the initial result, and maps the result into the RGB space to obtain final image dehazing result. Experimental results showed that the proposed method effectively alleviated color distortion and made image scenes clearer in image dehazing results. © Springer Nature Switzerland AG 2019.

关键词： Demulsification

来源：评论

学校读者我要写书评

暂无评论

Localization of Human 3D Joints Based on Binocular vision 4th

Localization of Human 3D Joints Based on Binocular Vision

引用

4th international conference on Cognitive Systems and Information processing (ICCSIP)

作者： Xu, Zheng Li, Jinping Yin, Jianqin Wu, Yanchun Jinan Univ Shandong Prov Key Lab Network Based Intelligent C Sch Informat Sci & Engn Jinan 250022 Shandong Peoples R China Jinan Univ Shandong Coll Jinan 250022 Shandong Peoples R China Jinan Univ Univ Key Lab Informat Proc & Cognit Comp 13 Five Jinan 250022 Shandong Peoples R China Beijing Univ Posts & Telecommun Sch Automat Beijing 100876 Peoples R China

ISBN: (纸本)9789811379864;9789811379857

With the development of image/video based 3D pose estimation techniques, service robots, human-computer interaction, and 3D somatosensory games have been developed rapidly. However, 3D pose estimation is still one of the most challenging tasks in computer vision. On the one hand, diversity of poses, occlusion and self-occlusion, change in illumination, and complex background increase the complexity of human pose estimation. On the other hand, many application scenarios require high real-time performance for 3D pose estimation. Therefore, we present a 3D pose estimation method based on binocular vision in this paper. For each frame of the binocular videos, the human body is detected firstly;Then Stacked-Hourglass network is used to detect the human joints, and the pixel coordinates of the key joints of all the human bodies in the binocular images are obtained. Finally, with the calibrated camera internal parameters and external parameters, the 3D coordinates of the major joints in the world coordinate system are estimated. This method does not rely on 3D data sets for training. It only requires binocular cameras to perform 3D pose estimation. The experimental results show that the method can locate key joints precisely and the real-time performance is achieved in complex background.

关键词： Pose estimation 3D joints localization Binocular vision

来源：评论

学校读者我要写书评

暂无评论

An improved occlusion detection with constraints approach for video processing 1

引用

14th EAI international conference on Industrial Networks and Intelligent Systems, INISCOM 2018

作者： Vu, Tuan-Anh Phan, Hung Ngoc Huynh, Tu Kha Ha, Synh Viet-Uyen School of Computer Science and Engineering International University Vietnam National University Ho Chi Minh city Viet Nam

ISBN: (数字)9783030058739

ISBN: (纸本)9783030058722

The accurate understanding of occlusion region is critical for trustworthy estimation of optical flow to prevent the negative influence of occluded pixels on disocclusion regions. However, occlusion is the result of motion. In contrast, estimating accurate optical flow is necessary to locate reliable occlusions. Hence, one of the key challenges that required further exploration and research is the accuracy at the boundaries of the moving objects. This paper presents the work in process approach that can detect occlusion regions by using some constraints such as pixel-wise coherence, segment-wise confidence and edge-motion coherence. Comparing to the previous methods, our method achieves the same efficiency by solving only one Partial Differential Equation (PDE) problem. The proposed method is faster and provides better coverage rates for occlusion regions than variation techniques in various numbers of benchmark datasets. With these improved results, we can apply and extend our approach to a wider range of applications in computer vision, such as: motion estimation, object detection and tracking, robot navigation, 3D reconstruction, image registration. © 2019, ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

image Segmentation Based on Local Chan-Vese Model Combined with Fractional Order Derivative 15th

Image Segmentation Based on Local Chan-Vese Model Combined w...

引用

15th international conference on Intelligent Computing, ICIC 2019

作者： Zou, Le Song, Liang-Tu Wang, Xiao-Feng Chen, Yan-Ping Tang, Chao Zhang, Chen Hefei Institute of Intelligent Machines Hefei Institutes of Physical Science Chinese Academy of Sciences P.O. Box 1130 HefeiAnhui230031 China University of Science and Technology of China HefeiAnhui230027 China Anhui Provincial Engineering Laboratory of Big Data Technology Application for Urban Infrastructure Department of Computer Science and Technology Hefei University Hefei230601 China

ISBN: (纸本)9783030267629

image segmentation plays a significant role in computer vision and image processing. In this paper, we proposed a novel Local Chan–Vese (LCV) image segmentation model. The new model combined classical LCV model with fractional order magnitude image. We used absolute value instead of square root operation to approximate the magnitude of fractional order gradient, and constructed the eight directions fractional differential masks. We can get a novel fractional order difference image and drive a new local image fitting term. We also presented a new distance regularized term. The new distance regularization term was defined by a potential function. We used the spectral residual method for getting the saliency map of the given image. The initial level set function was driven based on saliency map to accelerate the convergence speed. The experiments were given to show the effectiveness of the new image segmentation model. © 2019, Springer Nature Switzerland AG.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Moving target detection under turbulence degraded visible and infrared image sequences 1

引用

2nd international conference on computer vision and image processing, cvip 2017

作者： Veenu, Chaudhary Ajay, Kumar Anurekha, Sharma Department of Electronic Science Kurukshetra University KurukshetraHaryana136119 India Instrumentation Research and Development Establishment DehradunUttarakhand248008 India

ISBN: (数字)9789811078958

ISBN: (纸本)9789811078941

The presence of atmospheric turbulence over horizontal imaging paths introduces time-varying perturbations and blur in the scene that severely degrade the performance of moving object detection and tracking systems of vision applications. This paper proposed a simple and efficient algorithm for moving target detection under turbulent media, based on adaptive background subtraction approach with different types of background models followed by adaptive global thresholding to detect foreground. This proposed method is implemented in MATLAB and tested on turbulence degraded video sequences. Further, this proposed method is also compared with state-of-the-art method published in the literature. The result shows that the detection performance by proposed algorithm is better. Further, the proposed method can be easily implemented in FPGA-based hardware. © 2018, Springer Nature Singapore Pte Ltd.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Implementation and Optimization of image Acquisition with Smartphones in computer vision 32

Implementation and Optimization of Image Acquisition with Sm...

引用

32nd international conference on Information Networking (ICOIN)

作者： Xiu, Lingyan Ma, Bojiao Zhu, Konglin Zhang, Lin Beijing Univ Posts & Telecommun Sch Informat & Commun Engn Beijing 100876 Peoples R China

ISBN: (纸本)9781538622902

With many emerging function modules, such as image acquisition, front-end local processing, wireless transmission and so on, the smartphone becomes a major front-end hardware in the mobile-cloud computer vision system. However, due to the limitations of local resources and camera performance, there are many problems in image acquisition with smartphones. For example, the images are not as clear as those captured by professional camera equipment. And the performance of image acquisition is much more sensitive to background procedures and environment. These shortcomings have brought great challenges in terms of accuracy and delay in computer vision. In this paper, the Resolution Adaptive Algorithm (RAA) is proposed to select the optimal resolution for image acquisition in different situations. Furthermore, in order to improve the efficiency of local resources and reduce the processing delay, a low-quality image filtered method is presented to delete the invalid images. In our experiment, the average delay between image acquisition and display is about 100ms, which meets the requirement of detection in real time.

关键词： smartphone image acquisition image resolution accuracy delay

来源：评论

学校读者我要写书评

暂无评论

image processing techniques in vision-based robot navigation

Image processing techniques in vision-based robot navigation

引用

international conference on Control, Artificial Intelligence, Robotics and Optimization (ICCAIRO)

作者： Munguia, Rodrigo Bolea, Yolanda Grau, Antoni Univ Guadalajara Dept Comp Sci CUCEI Guadalajara Jalisco Mexico Tech Univ Catalonia UPC Automat Control Dept Barcelona Spain

ISBN: (纸本)9781538695760

Motivated by the problems of vision-based mobile robot map building and localization, we present a comparative study of statistical methods for matching image features in a wide base line between learning and recognition phases. A general methodology called feature-class method for the problem of fast matching image features in a wide base line is described in the context of mobile robots. The objective of this work is to discuss and to show the performance of such methods in an example of visual SLAM, with experiments done with real data.

关键词： computer vision robot navigation image processing

来源：评论

学校读者我要写书评

暂无评论

Deep convolutional neural network for person re-identification: A comprehensive review 2nd

Deep convolutional neural network for person re-identificati...

引用

2nd international conference on computer vision and image processing, cvip 2017

作者： Chahar, Harendra Nain, Neeta Department of Computer Science and Engineering Malaviya National Institute of Technology Jaipur India

ISBN: (纸本)9789811078941

In video surveillance, person re-identification (re-id) is a popular technique to automatically finding whether a person has been already seen in a group of cameras. In the recent years, availability of large-scale datasets, the deep learning-based approaches have made significant improvement in the accuracy over the years as compared to hand-crafted approaches. In this paper, we have distinguished the person re-id approaches into two categories, i.e., image-based and video-based approaches;deep learning approaches are reviewed in both categories. This paper contains the brief survey of deep learning approaches on both image and video person re-id datasets. We have also presented the current ongoing works, issues, and future directions in large-scale datasets. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

vision-based surface roughness evaluation system for end milling

引用

international JOURNAL OF computer INTEGRATED MANUFACTURING 2018年第8期31卷 727-738页

作者： Cuka, Besmir Cho, Minho Kim, Dong-Won Chonbuk Natl Univ Ind & Informat Syst Engn Jeonju South Korea Korea Marine Equipment Res Inst Gunsan Si Jeollabuk Do South Korea

This paper presents a vision-based surface roughness evaluation system for end-milled metals, addressing digital reconstruction and calibration of inspected surfaces, and quantitative and qualitative evaluation of surface texture. Specimens with different levels of surface roughness are machined, and a comparison between stylus-based and vision-based measurements is performed while using standard roughness parameters. The vison-based results vary among 9% and 11% compared to the stylus-based ones, which is a minor error to trade-off for faster measurements. Furthermore, surface texture evaluation is performed by detecting the generated cusp lines and tool marks on the machined surface. The tool marks' distribution is analysed in order to determine whether the machining is performed under optimal cutting conditions. Results show that under optimal cutting conditions, the detected tool marks are normally distributed along the feed direction and the distance between two consecutive tool marks does not vary significantly. Based on the proposed methods software is implemented that enables the three-dimensional reconstruction, calibration and evaluation of the inspected surface.

关键词： Surface roughness computer vision image processing end milling

来源：评论

学校读者我要写书评

暂无评论

Human activity recognition by fusion of RGB, depth, and skeletal data 2nd

Human activity recognition by fusion of RGB, depth, and skel...

引用

2nd international conference on computer vision and image processing, cvip 2017

作者： Khaire, Pushpajit Imran, Javed Kumar, Praveen Department of Computer Science and Engineering Visvesvaraya National Institute of Technology Nagpur India Department of Computer Science and Engineering Indian Institute of Technology Roorkee India

ISBN: (纸本)9789811078941

A significant increase in research of human activity recognition can be seen in recent years due to availability of low-cost RGB-D sensors and advancement of deep learning algorithms. In this paper, we augmented our previous work on human activity recognition (Imran et al., IEEE international conference on advances in computing, communications, and informatics (ICACCI), 2016) [1] by incorporating skeletal data for fusion. Three main approaches are used to fuse skeletal data with RGB, depth data, and the results are compared with each other. A challenging UTD-MHAD activity recognition dataset with intraclass variations, comprising of twenty-seven activities, is used for testing and experimentation. Proposed fusion results in accuracy of 95.38% (nearly 4% improvement over previous work), and it also justifies the fact that recognition improves with an increase in number of evidences in support. © 2018, Springer Nature Singapore Pte Ltd.

关键词： Musculoskeletal system

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：