检索结果-内蒙古大学图书馆

Integration of seismic and image data processing for rockfall monitoring and early warning along transportation networks

引用

NATURAL HAZARDS 2016年第1-Sup期83卷 S133-S153页

作者： Partsinevelos, Panagiotis Kritikakis, George Economou, Nikos Agioutantis, Zach Tripolitsiotis, Achilleas Mertikas, Stelios Vafidis, Antonis Tech Univ Crete Sch Mineral Resources Engn Geodesy & Geomat Engn Lab Univ Campus Khania Crete Greece Tech Univ Crete Sch Mineral Resources Engn Appl Geophys Lab Univ Campus Khania Crete Greece Univ Kentucky Dept Min Engn Lexington KY USA Space Geomat Ltd Ksanthoudidou 10A Khania Crete Greece

The occurrence of rockfall incidents on the transportation network may cause injuries, and even casualties, as well as severe damage to infrastructure such as dwellings, railways, road corridors, etc. Passive protective measures (i.e., rockfall barriers, wire nets, etc.) are mainly deployed by operators of ground transport networks to minimize the impact of detrimental effects on these networks. In conjunction with these passive measures, active rockfall monitoring should ideally include the magnitude of each rockfall, its initial and final position, and the triggering mechanism that might have caused its detachment from the slope. In this work, the operational principle of a low-cost rockfall monitoring and alerting system is being presented. The system integrates measurements from a multi-channel seismograph and commercial cameras as the primary equipment for event detection. A series of algorithms analyze these measurements independently in order to reduce alarms originated by surrounding noise and sources other than rockfall events. The detection methodology employs two different sets of algorithms: Time-frequency analyses of the rockfall event's seismic signature are performed using moving window pattern recognition algorithms, whereas image processing techniques are utilized to deliver object detection and localization. Training and validation of the proposed approach was performed through field tests that involved manually induced rockfall events and recording of sources (i.e., passing car, walking people) that may cause a false alarm. These validation tests revealed that the seismic monitoring algorithms produce a 4.17 % false alarm rate with an accuracy of 93 %. Finally, the results of a 34-day operational monitoring period are presented and the ability of the imaging system to identify and exclude false alarms is discussed. The entire processing cycle is 10-15 s. Thus, it can be considered as a near real-time system for early warning of rockfall events.

关键词： Rockfall monitoring Seismic signature Multi-temporal imagery datasets STA/LTA

来源：评论

学校读者我要写书评

暂无评论

2016 IEEE International conference on Consumer Electronics-China, ICCE-China 2016

2016 IEEE International Conference on Consumer Electronics-C...

引用

2016 IEEE International conference on Consumer Electronics-China, ICCE-China 2016

ISBN: (纸本)9781509061938

The proceedings contain 49 papers. The topics discussed include: joint non-uniform detection and low-complexity decoding for multi-level cell NAND flash memory;joint time switching and power allocation in large-scale MISO OFDM systems with wireless powered relay;hierarchical features learning with convolutional neural networks based on aircraft recognition on images from remote sensing image;optimizing the smoothness of production lines with considerations of structural and dynamic complexities for electronics manufacturing;compact CPW-fed asymmetric UWB antenna with two symmetrical stubs;joint resource allocation with energy harvesting base stations in two adjacent cells;the design and implementation of super base station side l1c system in TD-LTE pattern;low complexity iterative frequency domain decision feedback equalization for faster-than- Nyquist signaling;temporal order information for complex action recognition;application of mobile Bluetooth based on human physiological parameters wireless sensor;design and implementation of low-cost SM4 for consumer electronic product;wavefront parallel processing based on Posix threads;and fast cu-splitting decisions based on data mining.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis, classification, and estimation of pattern for land of aurangabad region using high-resolution satellite image

引用

Advances in Intelligent Systems and Computing 2016年 380卷 413-427页

作者： Vibhute, Amol D. Dhumal, Rajesh K. Nagne, Ajay D. Rajendra, Yogesh D. Kale, K.V. Mehrotra, S.C. Department of Computer Science & IT Dr. B. A. M. University AurangabadMaharashtra431004 India

ISBN: (纸本)9788132225225

Land use land cover (LULC) information extraction is a crucial exercise for agricultural land. The present study highlights the advantages of remote sensing, GIS, and GPS techniques for LULC mapping from high-resolution remote sensing data. High spatial resolution (5.8 m) satellite imagery of IRS-P6 Resourcesat-ii LISS-IV having three spectral bands was utilized for LULC classification and for data processing ENVI 4.4 tool and Arc GIS10 software were used. Eight training samples for LULC classes have been selected from the image. Supervised classification using maximum likelihood (ML), Mahalanobis distance (MD), and minimum distance to means (MDM) were applied. The performances of above classifiers were evaluated in terms of the classification accuracy with respect to the collected real-time ground truth information. The evaluation result shows that the overall accuracies of LULC classifications are approximately 84.40, 77.98, and 74.31% with Kappa coefficients 0.82, 0.74, and 0.70 for the ML, MD, and MDM, respectively. It is noticed that ML has a better accuracy than the MD and MDM classifiers and it is a more effective method for complex and noisy remote sensing data because of its unified approach for estimation of parameters. © Springer India 2016.

关键词： Satellite imagery

来源：评论

学校读者我要写书评

暂无评论

TWO LEVELS FUSION DECISION FOR MULTISPECTRAL image pattern recognition

TWO LEVELS FUSION DECISION FOR MULTISPECTRAL IMAGE PATTERN R...

引用

ISPRS Annals of the Photogrammetry, remote sensing and Spatial Information Sciences

作者： Elmannai, H. Loghmari, M. A. Naceur, M. S. Carthage Univ Ecole Super Commun Tunis Ariana 2083 Tunisia Univ Tunis El Manar UTM Ecole Natl Ingn Tunis Tunis 1002 Tunisia Lab Teledetect & Syst Informat Reference Spatiale Tunis Le Belvedere 1002 Tunisia

Major goal of multispectral data analysis is land cover classification and related applications. The dimension drawback leads to a small ratio of the remote sensing training data compared to the number of features. Therefore robust methods should be associated to overcome the dimensionality curse. The presented work proposed a pattern recognition approach. Source separation, feature extraction and decisional fusion are the main stages to establish an automatic pattern recognizer. The first stage is pre-processing and is based on non linear source separation. The mixing process is considered non linear with gaussians distributions. The second stage performs feature extraction for Gabor, Wavelet and Curvelet transform. Feature information presentation provides an efficient information description for machine vision projects. The third stage is a decisional fusion performed in two steps. The first step assign the best feature to each source/pattern using the accuracy matrix obtained from the learning data set. The second step is a source majority vote. Classification is performed by Support Vector Machine. Experimentation results show that the proposed fusion method enhances the classification accuracy and provide powerful tool for pattern recognition.

关键词： Source separation Support Vector Machine Feature extraction Decisional fusion pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Using video magnification approach directly to extract heart-beat

Using video magnification approach directly to extract heart...

引用

International conference on Applied System Innovation (ICASI)

作者： Jui-Lin Lai Shin-Chia Tsai Rong-Sheng Lin Shin-Yi Huang Department of Electronic Engineering National United University Miao-Li City Taiwan R.O.C.

ISBN: (纸本)9781467398893

In the paper, the non-invasive body bio-information sensor with Video color Magnification (VM) image processing approach to extract the value of heart-beat is proposed. Implementing the video color magnification algorithm to execute the very small variation of the color in the cached video images is magnified. Measurement result shows that the value of heart-beat is calculated the times of the alternately variation between the high and low than the average value for the intension of the processed images during a constant time. The accuracy of measured data is reach 98% compared with the consumer equipment. The proposed bio-sensor system can be integrated the wireless and internet to connect the detection platform for the health diagnosis and health-care with remote-sensing applications will save medical resource given human with the better life quality.

关键词： Decision support systems Graphics Programming Measurement uncertainty Computers pattern recognition Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Periodic pattern Enhancement: A Stochastic Resonance Approach 5

Periodic Pattern Enhancement: A Stochastic Resonance Approac...

引用

IEEE International conference on Signal processing, Communications and Computing ICSPCC 2015

作者： Wang, Zelong Xie, Meihua Zhu, Jubo Natl Univ Def Technol Dept Math & Syst Sci Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781479989201

This paper investigates two basic problems about the periodic pattern in pattern recognition and artificial intelligence: weak periodic pattern and the noise. We make use of stochastic resonance (SR) theory to enhance periodic pattern by transferring the noise energy to the pattern energy, which not only removes the noise but also improves the periodic pattern intensity. We firstly analyze the basic principle of the energy transfer by SR theoretically;and then, we design the optimized SR nonlinear system to enhance the periodic pattern;finally, we apply the proposed method to two popular periodic patterns, i.e., the texture pattern of the optical remote sensing image and the spatial pattern of the fingerprint image. The experiments have a good performance and the proposed method can be extended to wider applications of periodic pattern enhancement.

关键词： SR nonlinear system energy transfer optical remote sensing fingerprint image radar cross section

来源：评论

学校读者我要写书评

暂无评论

Comparative study of feature dimension reduction algorithm for high-resolution remote sensing image classification 5

Comparative study of feature dimension reduction algorithm f...

引用

IEEE International conference on Signal processing, Communications and Computing ICSPCC 2015

作者： Li Shijin Li Huimin Hohai Univ Coll Comp & Informat Nanjing 210098 Jiangsu Peoples R China Hohai Univ Coll Comp & Informat Nanjing 210098 Jiangsu Peoples R China

ISBN: (纸本)9781479989201

The high-resolution remote sensing image classification is an important research topic in pattern recognition, and its computational complexity grows exponentially with the increase of the dimension. Hence, it is necessary to perform feature dimension reduction. This paper presents a comparative study on state-of-the-art feature selection and feature transformation methods for the task of high-resolution remote sensing image classification. We conduct a group of experiments on mRMR, PCA and KPCA for their applicability. Comparison results show that nonlinear dimension reduction method based on feature transformation is more suitable for the task at hand. What's more, appropriate kernel function and kernel parameters are also essential. It is vital to reduce the dimension, which can alleviate the computational cost greatly and improve accuracy.

关键词： remote sensing image classification feature dimension reduction feature selection feature transformation

来源：评论

学校读者我要写书评

暂无评论

Combining Low Level Features and Visual Attributes for VHR remote sensing image Classification 9

Combining Low Level Features and Visual Attributes for VHR R...

引用

9th International Symposium on Multispectral image processing and pattern recognition (MIPPR) - remote sensing image processing, Geographic Information Systems, and Other Applications

作者： Zhao, Fumin Sun, Hao Liu, Shuai Zhou, Shilin Natl Univ Def Technol Sch Elect Sci & Engn Changsha 410073 Hunan Peoples R China

ISBN: (纸本)9781510600560

Semantic classification of very high resolution (VHR) remote sensing images is of great importance for land use or land cover investigation. A large number of approaches exploiting different kinds of low level feature have been proposed in the literature. Engineers are often frustrated by their conclusions and a systematic assessment of various low level features for VHR remote sensing image classification is needed. In this work, we firstly perform an extensive evaluation of eight features including HOG, dense SIFT, SSIM, GIST, Geo color, LBP, Texton and Tiny images for classification of three public available datasets. Secondly, we propose to transfer ground level scene attributes to remote sensing images. Thirdly, we combine both low-level features and mid-level visual attributes to further improve the classification performance. Experimental results demonstrate that i) Dene SIFT and HOG features are more robust than other features for VHR scene image description. ii) Visual attribute competes with a combination of low level features. iii) Multiple feature combination achieves the best performance under different settings.

关键词： attribute feature RS image SVM semantic accuracy classification VHR

来源：评论

学校读者我要写书评

暂无评论

Road Segmentation using Multipass Single-Pol Synthetic Aperture Radar imagery

Road Segmentation using Multipass Single-Pol Synthetic Apert...

引用

IEEE conference on Computer Vision and pattern recognition (CVPR)

作者： Koch, Mark W. Moya, Mary M. Chow, Jim G. Goold, Jeremy Malinas, Rebecca Sandia Natl Labs POB 5800 Albuquerque NM 87185 USA

ISBN: (纸本)9781467367592

Synthetic aperture radar (SAR) is a remote sensing technology that can truly operate 24/7. It's an all-weather system that can operate at any time except in the most extreme conditions. By making multiple passes over a wide area, a SAR can provide surveillance over a long time period. For high level processing it is convenient to segment and classify the SAR images into objects that identify various terrains and man-made structures that we call "static features." In this paper we concentrate on automatic road segmentation. This not only serves as a surrogate for finding other static features, but road detection in of itself is important for aligning SAR images with other data sources. In this paper we introduce a novel SAR image product that captures how different regions decorrelate at different rates. We also show how a modified Kolmogorov-Smirnov test can be used to model the static features even when the independent observation assumption is violated.

关键词： image edge detection image resolution image segmentation Optimization Roads Speckle Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Histo-Binary Combined Corner Enhancement (HBCCE) improved algorithm for image processing corner detection

Histo-Binary Combined Corner Enhancement (HBCCE) improved al...

引用

2015 International conference on image processing, Computer Vision, and pattern recognition, IPCV 2015, at WORLDCOMP 2015

作者： El Harraj, Abdeslam Raissouni, Naoufal RSAID Lab.: Remote Sensing/Sign.-Image Proc. and Appl. Math./Info./Decis. Making National School for Applied Sciences of Tetuan Univeristy of Abdelmalek Essaadi BP. 2222. M'Hannech II Tetuan93030 Morocco

ISBN: (纸本)1601324049

A novel algorithm, Histo-Binary Combined Corner Enhancement (HBCCE), for enhancing corner detection is discussed. The main goal is to enhance the repeatability for the corner by corner sharpening using a preprocessing filtering strategy. We are particularly interested in corner points because they are defined locally, usually in very small neighborhoods. The quality of the corners and the efficiency of the detection methods are both very important aspects that can greatly impact the accuracy, robustness and real-time performance of the corresponding corner-based vision system. There are many variant of corner detectors, but, no precise corner detector exists. The most used corner detectors our days are, Harris corner detector [1], Sh-Tomasi detector [2], SUSAN detector [3], CSS detector [4], FAST detector [5] and AGAST detector [6]. In the present paper, we propose a new strategy to enhance the corner detectors by adding a preprocessing stack prior to any detection step, as mentioned previously the final goal is to sharpen the corners so they can be easily detected. Our approach is based on an efficient combination of filters. We verify the performance of the proposed method by measuring the repeatability rate under various JPEG compressions, rotation, scale, blur and illumination changes using a standard dataset [7]. © International conference on image processing, Computer Vision, and pattern recognition, IPCV *** right reserved.

关键词： image enhancement

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：