检索结果-内蒙古大学图书馆

11th IEEE Annual International conference on Nano/Micro Engineered and Molecular systems, NEMS 2016

作者： Li, Xiuyuan Zhao, Yulong Hu, Tengjiang Zhang, Qi Li, Yingxue State Key Laboratory for Mechanical Manufacturing System Xi'An Jiaotong University China Collaborative Innovation Center of High-End Manufacturing Equipment Xi'An Jiaotong University China

ISBN: (纸本)9781509019472

A novel high- speed image super-resolution algorithm based on sparse representation for MEMS defect detection is proposed in this paper. Traditional super-resolution algorithms adopt a single dictionary to represent images, which cannot differentiate varieties of image blocks and leads to slow processing speed. Aiming at overcoming this shortage of traditional super-resolution algorithms, image blocks are divided into different categories by local features and each of these categories possesses the corresponding high and low resolution dictionary pairs. Experimental results of different MEMS defects show that the improved algorithm can obtain images of little lower quality with much less processing time, indicating that the proposed algorithm is more suitable for MEMS defect detection. © 2016 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Architecture for Dynamic Allocation of Computer Vision Tasks 16

Architecture for Dynamic Allocation of Computer Vision Tasks

引用

10th International conference on Distributed Smart Cameras (ICDSC)

作者： Weissenfeld, Axel Opitz, Andreas Pflugfelder, Roman Fernandez, Gustavo Austrian Inst Technol Donau City Str 1 A-1220 Vienna Austria

ISBN: (纸本)9781450347860

The use of reconfigurable computer vision architecture for image processing tasks is an important and challenging application in real time systems with limited resources. It is an emerging field as new computing architectures are developed, new algorithms are proposed and users define new emerging applications in surveillance. In this paper, a computer vision architecture capable of reconfiguring the processing chain of computer vision algorithms is summarised. The processing chain consists of multiple computer vision tasks, which can be distributed over various computing units. One key characteristic of the designed architecture is graceful degradation, which prevents the system from failure. This system characteristic is achieved by distributing computer vision tasks to other nodes and parametrizing each task depending on the specified quality-of-service. Experiments using an object detector applied to a public dataset are presented.

关键词： Passenger tracking reconfigurable vision processing architectures QoS Management

来源：评论

学校读者我要写书评

暂无评论

3D anomaly inspection system for sewer pipes using stereo vision and novel image processing 11

3D anomaly inspection system for sewer pipes using stereo vi...

引用

11th IEEE conference on Industrial Electronics and Applications, ICIEA 2016

作者： Huynh, Phat Ross, Robert Martchenko, Andrew Devlin, John Department of Engineering La Trobe University MelbourneVIC Australia

ISBN: (纸本)9781509026050

This paper describes and evaluates a novel 3D inspection system to detect anomalies in sewer pipes using stereo vision coupled with novel image processing algorithms. Currently, most commercial pipe inspection systems are designed with one or more Closed-circuit Television (CCTV) cameras. These systems are slow, costly and have limited accuracy (caused by human and environmental factors). More sophisticated systems (Laser-based, Infrared Thermography, Ultrasonic-based and Ground Penetrating Radar) suffer from: low resolution, high noise, high operational costs and an inability to detect water infiltration. The main objective of this research is to apply stereo vision and robust image processing to generate 3D images of anomalies in sewer pipes in order to achieve high efficiency and accuracy for pipe inspection. The results show that various types of defects are successfully detectable. In addition, the correspondence time can be reduced by up to 45% and the accuracy of disparity maps is maintained compared to traditional local correspondence algorithms. Each component of the proposed system was tested individually with real and simulated data sets. © 2016 IEEE.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Optical Signal processing of Video Surveillance for Recognizing and Measurement Location Railway Infrastructure Elements 14

Optical Signal Processing of Video Surveillance for Recogniz...

引用

14th International conference on Optical Technologies for Telecommunications

作者： Diyazitdinov, Rinat R. Vasin, Nikolay N. PSUTI Dept Commun Syst 23 Tolstoy St Samara 443010 Russia

ISBN: (纸本)9781510600485

processing of optical signals, which are received from CCD sensors of video cameras, allows to extend the functionality of video surveillance systems. Traditional video surveillance systems are used for saving, transmitting and preprocessing of the video content from the controlled objects. Video signal processing by analytics systems allows to get more information about object's location and movement, the flow of technological processes and to measure other parameters. For example, the signal processing of video surveillance systems, installed on carriage-laboratories, are used for getting information about certain parameters of the railways. Two algorithms for video processing, allowing recognition of pedestrian crossings of the railways, as well as location measurement of the so-called "Anchor Marks" used to control the mechanical stresses of continuous welded rail track are described in this article. The algorithms are based on the principle of determining the region of interest (ROI), and then the analysis of the fragments inside this ROI.

关键词： video surveillance systems optical signal processing diagnostic systems pedestrian crossing railway tracks railways Anchor Marks RANSAC Canny Gaussian impulse the image histogram the region of interest

来源：评论

学校读者我要写书评

暂无评论

Proceedings of Fifth International conference on Soft Computing for Problem Solving 1st ed. 2016

引用

丛书名： Advances in Intelligent systems and Computing

2016年

作者： Millie Pant Kusum Deep Jagdish Chand Bansal Atulya Nagar Kedar Nath Das

ISBN: (数字)9789811004513

ISBN: (纸本)9789811004506

The proceedings of SocProS 2015 will serve as an academic bonanza for scientists and researchers working in the field of Soft Computing. This book contains theoretical as well as practical aspects using fuzzy logic, neural networks, evolutionary algorithms, swarm intelligence algorithms, etc., with many applications under the umbrella of Soft Computing. The book will be beneficial for young as well as experienced researchers dealing across complex and intricate real world problems for which finding a solution by traditional methods is a difficult task. The different application areas covered in the proceedings are: image processing, Cryptanalysis, Industrial Optimization, Supply Chain Management, Newly Proposed Nature Inspired algorithms, Signal processing, Problems related to Medical and Health Care, Networking Optimization Problems, etc.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Smoggy Environment Recognition by Combining Infrared and Visible images 1

引用

4th International conference on Communications, Signal processing, and systems (CSPS)

作者： Wang, Lujia Tong, Ying Liu, Zeng Chen, Jin Zhou, Meili Liu, Hengxin Zhang, Ji Tianjin Normal Univ Coll Elect & Commun Engn Tianjin 300387 Peoples R China Tianjin 4 High Sch Tianjin 300000 Peoples R China

ISBN: (数字)9783662498316

ISBN: (纸本)9783662498316;9783662498293

Smoke recognition is one of the research directions in the field of digital image processing, but common algorithms are mostly based on the video sequence of images. A combination of infrared and visible images is presented in this paper, by extracting the analyte infrared image outer contour, and complete comparison of the extent of the visible outline of the image in the same area. Then according to the measured object within the outer contour of the two bands contain the number of pixels ratio, determine the impact of smoggy on the visible image. Experiments show that the algorithm needs to be analyzed only for the infrared and visible band single still image. You can draw judgment of smoggy environment, and it can provide the basis for a fire alarm.

关键词： Smoggy recognition Infrared image Visible image Edge extraction

来源：评论

学校读者我要写书评

暂无评论

Fast processing of microscopic images using object-based extended depth of field

引用

BMC BIOINFORMATICS 2016年第19期17卷 229-237页

作者： Intarapanich, Apichart Kaewkamnerd, Saowaluck Pannarut, Montri Shaw, Philip J. Tongsima, Sissades Natl Sci & Technol Dev Agcy Natl Elect & Comp Technol Ctr Thailand Sci Pk Pathum Thani Thailand Natl Sci & Technol Dev Agcy Natl Ctr Genet Engn & Biotechnol Thailand Sci Pk Pathum Thani Thailand

Background: Microscopic analysis requires that foreground objects of interest, e.g. cells, are in focus. In a typical microscopic specimen, the foreground objects may lie on different depths of field necessitating capture of multiple images taken at different focal planes. The extended depth of field (EDoF) technique is a computational method for merging images from different depths of field into a composite image with all foreground objects in focus. Composite images generated by EDoF can be applied in automated image processing and pattern recognition systems. However, current algorithms for EDoF are computationally intensive and impractical, especially for applications such as medical diagnosis where rapid sample turnaround is important. Since foreground objects typically constitute a minor part of an image, the EDoF technique could be made to work much faster if only foreground regions are processed to make the composite image. We propose a novel algorithm called object-based extended depths of field (OEDoF) to address this issue. Methods: The OEDoF algorithm consists of four major modules: 1) color conversion, 2) object region identification, 3) good contrast pixel identification and 4) detail merging. First, the algorithm employs color conversion to enhance contrast followed by identification of foreground pixels. A composite image is constructed using only these foreground pixels, which dramatically reduces the computational time. Results: We used 250 images obtained from 45 specimens of confirmed malaria infections to test our proposed algorithm. The resulting composite images with all in-focus objects were produced using the proposed OEDoF algorithm. We measured the performance of OEDoF in terms of image clarity (quality) and processing time. The features of interest selected by the OEDoF algorithm are comparable in quality with equivalent regions in images processed by the state-of-the-art complex wavelet EDoF algorithm;however, OEDoF required four times l

关键词： Malaria Color Space Composite image Foreground Object Foreground Pixel

来源：评论

学校读者我要写书评

暂无评论

Interpretable and globally optimal prediction for textual grounding using image concepts 17

Interpretable and globally optimal prediction for textual gr...

引用

Proceedings of the 31st International conference on Neural Information processing systems

作者： Raymond A. Yeh Jinjun Xiong Wen-mei W. Hwu Minh N. Do Alexander G. Schwing Department of Electrical Engineering University of Illinois at Urbana-Champaign IBM Thomas J. Watson Research Center

ISBN: (纸本)9781510860964

Textual grounding is an important but challenging task for human-computer interaction, robotics and knowledge mining. Existing algorithms generally formulate the task as selection from a set of bounding box proposals obtained from deep net based systems. In this work, we demonstrate that we can cast the problem of textual grounding into a unified framework that permits efficient search over all possible bounding boxes. Hence, the method is able to consider significantly more proposals and doesn't rely on a successful first stage hypothesizing bounding box proposals. Beyond, we demonstrate that the trained parameters of our model can be used as word-embeddings which capture spatial-image relationships and provide interpretability. Lastly, at the time of submission, our approach outperformed the current state-of-the-art methods on the Flickr 30k Entities and the ReferltGame dataset by 3.08% and 7.77% respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Flood Water Depth Estimation - A Survey

Flood Water Depth Estimation - A Survey

引用

7th IEEE International conference on Computational Intelligence and Computing Research (ICCIC)

作者： Nair, Bhavana B. Rao, Sethuraman Amrita Vishwa Vidyapeetham Amrita Ctr Wireless Networks & Applicat Amritapuri Kollam India

ISBN: (纸本)9781509006120

Global warming induced drastic climate changes have increased the frequency of natural disasters such as flooding, worldwide. Flooding is a constant threat to humanity and reliable systems for flood monitoring and analysis need to be developed. Flood hazard assessment needs to take into account physical characteristics such as flood depth, flow velocity and the duration of flooding. This paper provides the researchers with a detailed compilation of the methods that can be used for the estimation of flood water depth. A comparative study has been done between the water depth estimation techniques based on image processing and those which does not involve image processing. The comparison is based on various attributes such as implementation methods, advantages, accuracy and cost. image processing methods are classified based on various algorithms such as character recognition, feature extraction, region of interest (ROI), FIR filter etc. Similarly, non-image processing methods are classified based on hardware used such as sensors, level indicators, etc., and other signal based techniques. This study can be used to identify the best method for flood water depth estimation.

关键词： image processing flood water depth edge detection level indicators sensors

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of image Retrieval systems using Shape Feature Based on Wavelet Transform 2

Performance Evaluation of Image Retrieval Systems using Shap...

引用

2nd International conference on Cognitive Computing and Information processing (CCIP)

作者： Desai, Padmashree Pujari, Jagadeesh Kinnikar, Anita BVBCET Dept CSE Hubli India SDMCET Dept ISE Dharwad Karnataka India

ISBN: (纸本)9781509010257

Digital era has produced large volume of images which created many challenges in computer science field to store, retrieve and manage images efficiently and effectively. Many techniques and algorithms have been proposed by different researcher to implement Content Based image Retrieval (CBIR) systems. This paper discusses performance of different CBIR systems implemented using combined features colour, texture and shape as a prominent feature based on wavelet transform. Choice of the feature extraction technique used in image retrieval determines performance of CBIR systems. In this paper evaluation of performance of three CBIR systems based on wavelet decomposition using threshold, wavelet decomposition using morphology operators and wavelet decomposition using Local Binary Patterns (LBP) is done. Also the performance of these methods is compared with the existing methods SIMPLIcity and FIRM. Average precision is used to compare the performance of the implemented systems. Results indicate that performance of CBIR systems using wavelet decomposition give better results than simplicity and FIRM, also wavelet decomposition with Local Binary Patterns (LBP) exhibit better retrieval efficiency compared to wavelet decomposition using threshold and morphological operators. Theses CBIR systems have been tested on bench mark Wang's image database. Precision versus Recall graphs for each system shows the performance of respective systems.

关键词： CBIR LBP Precision Recall Wavelet Decomposition

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：