检索结果-内蒙古大学图书馆

Temporal change detection in SAR Images Using Log Cumulants and Stacked Autoencoder

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2018年第2期15卷 297-301页

作者： Planinsic, Peter Gleich, Dusan Univ Maribor Fac Elect Engn & Comp Sci SLO-2000 Maribor Slovenia

This letter proposes a change detection algorithm for damage assessment caused by fires in Ireland using Sentinel 1 data. The novelty, in this letter, is a feature extraction within tunable Q discrete wavelet transform (TQWT) using higher order log cumulants of fractional Fourier transform (FrFT), which were fed into a stacked autoencoder (SAE) to distinguish changed and unchanged areas. The extracted features were used to train the SAE layerwise using an unsupervised learning algorithm. After training the decoding layer was replaced by a logistic regression layer to perform supervised fine-tuning and classification. The proposed algorithm was compared with the algorithm that used log cumulants of FrFT within the oriented dual-tree wavelet transform using support vector machine (SVM) classifier. The experimental results showed that the proposed combination of algorithms decreased the overall error (OE) for real synthetic aperture radar images by 6%, when TQWT was used instead of oriented dual-tree wavelet transform and OE was decreased by another 5% when SAE was used instead of the SVM classifier.

关键词： change detection algorithms feature extraction image processing neural networks synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Low-Rank Transfer Learning for Multi-stream Data Classification

Low-Rank Transfer Learning for Multi-stream Data Classificat...

引用

International Conference on Information Science and Technology (ICIST)

作者： Jingbo Sun Hongzu Su Yue Xie Jingjing Li Glasgow College University of Electronic Science and Technology of China Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9781665412667;9781665429412

Leveraging the labeled data from source stream to handle unlabeled data from target stream is a promising method for multi-stream classification. However, there are still two main issues, concept drifts and concept revolution, needed to be addressed. A couple of methods is proposed to solve them, such as adding a change detection module, modifying sliding window size and setting concept confidence. However, the majority of these approaches did not consider shared data structures among multiple data streams, which can be employed to handle these two issues. At the same time, a lot of algorithms assume that the source data stream and the target data stream are all come from the same domain. In reality, however, most data streams are from different domains with different data distributions. In this paper, therefore, we propose a novel framework Low-Rank Transfer Learning (LRTL) to address cross-domain multi-stream classification. LRTL is mainly composed of three modules, i.e., domain adaptation module, change detection module and classification module. Different from these existing multi-stream classification frameworks, we design a novel domain adaptation module, which utilizes low-rank representation and graph embedding to preserve data structures that have many benefits in dealing with concept drifts and concept revolution. Extensive experiments are carried out on the domain adaptation module and the proposed framework LRTL on multiple benchmarks, which verifies that our domain adaptation methods and frameworks can achieve the state-of-the-art results with significant improvements.

关键词： Information science change detection algorithms Transfer learning Benchmark testing Data structures Real-time systems Data models

来源：评论

学校读者我要写书评

暂无评论

A Novel Visual Perception Framework for Unmanned Aerial Vehicles: Challenges and Approaches

A Novel Visual Perception Framework for Unmanned Aerial Vehi...

引用

Chinese Automation Congress (CAC)

作者： Xuan Li Haibin Duan Hong Mo Fei-Yue Wang Peng Cheng Laboratory Shenzhen China The State Key Laboratory of Virtual Reality Technology and Systems School of Automation Science and Electrical Engineering Beihang University Beijing China The School of Electrical and Information Engineering Changsha University of Science and Technology Changsha China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665426480

change detection (CD) is an important preprocessing process in visual perception. Due to the difficulties of collection and labeling images in water scnens, the design and validation of the change detection algorithm is more difficult than expected. In this paper, we present a novel visual perception framework based on parallel vision for unmanned aerial vehicle (UAV). The visual perception framework consists of artificial scenes, computational experiments and parallel execution. In artificial scenes, we construct a water scene and automatically generated pixel-level image annotation. Next, computational experiments are carried out on different domain dataset. The experiment results show that: 1) mixed images effectively improve the performance of change detection model; 2) domain shift problems still greatly affect the algorithm performance.

关键词： Automation change detection algorithms Computational modeling Image annotation Autonomous aerial vehicles Labeling detection algorithms

来源：评论

学校读者我要写书评

暂无评论

change Point detection using the Kantorovich Distance Algorithm

引用

IFAC-PapersOnLine 2018年第18期51卷 708-713页

作者： Arifin, B.M.S. Li, Zukui Shah, Sirish L. Department of Chemical and Materials Engineering University of Alberta EdmontonT6G 2V4 Canada

In this article, a novel change detection algorithm is proposed based on the Kantorovich distance concept. Incorporating the proposed change detection algorithm with the existing process monitoring tools may assist the operator in detecting dynamic changes in process plants and provide fewer unnecessary (false) alarms as well as fewer missed alarms. The proposed change detection method was tested through simulation data. It is applied to the benchmark Tennessee Eastman (TE) process in online mode. Results prove the efficacy of the proposed method to detect both the sharp and incipient changes. © 2018

关键词： Linear programming Process monitoring Signal detection change detection change detection algorithms change point detection Distance algorithm Dynamic changes Kantorovich Distance Tennessee Eastman Transient process

来源：评论

学校读者我要写书评

暂无评论

Deforestation Monitoring Using Sentinel-L SAR Images in Humid Tropical Areas

Deforestation Monitoring Using Sentinel-L SAR Images in Humi...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： B. Ygorra F. Frappart J–P. Wigneron C. Moisy T. Catry F. Baup E. Hamunyela S. Riazanoff INRAE UMR1391 ISPA Villenave d'Ornon France VisioTerra Champs-sur-Marne France Université de Bordeaux Talence France LEGOS Toulouse France ESPACE-DEV Univ Montpellier IRD Univ Antilles Univ Guyane Univ Réunion Montpellier France CESBIO Toulouse France University of Namibia Private Bag Windhoek Namibia

Tropical forests are vulnerable to deforestation and various monitoring techniques have been developed based on remotely sensed data to map deforestation, but are facing multiple problems in the tropical areas. For instance, the techniques based optical data, which are widely used to monitor deforestation, face severe limitations in the humid tropical forest due to high cloud cover. Sentinel-l C-SAR dense time series can be used for a temporally more accurate monitoring. In this study, a change detection algorithm commonly used in the financial domain, the Cumulative Sum (CuSum) algorithm, was modified to be applied on time-series of Sentinel-l images in a forest concession of Democratic Republic of Congo (DRC) near Kisangani. The validation was made through the visual interpretation of PlanetScope OrthoScene images as in-situ data were missing. The results show a precision up to 0.75, an accuracy up to 0.95 and a kappa coefficient up to 0.40 for clear cut detection. The algorithm is able to detect forest degradation activities before the clear cuts.

关键词： Visualization change detection algorithms Time series analysis Vegetation mapping Forestry Optical imaging Radar polarimetry

来源：评论

学校读者我要写书评

暂无评论

Temperature data prediction and anomaly detection of Ethylene Cracking Furnace based on SVR

Temperature data prediction and anomaly detection of Ethylen...

引用

Fault detection, Supervision and Safety for Technical Processes (SAFEPROCESS), CAA Symposium on

作者： Wenzhuo Chen Shaolin Hu He Song School of Automation and Engineering Xi’an University of Technology Xian China School of Automation Guangdong University of Petrochemical Technology Maoming China

ISBN: (纸本)9781665401166

The temperature data in the chamber of ethylene cracking furnace is one of the important indexes for the combustion health of ethylene cracking furnace, and it is abnormal changes directly affect the stability and reliability of ethylene cracking furnace. Predicting the change trend of the temperature data in the chamber of ethylene cracking furnace is an important basis for timely understanding the working status of the ethylene cracking furnace. In this paper, based on support vector machine regression optimized by bayesian (BSVR), a prediction algorithm and model of the trend for the temperature data in the chamber of ethylene cracking furnace are established, and the prediction algorithm is compared with linear regression and random forest prediction algorithms to verify the effectiveness of the BSVR model. On this basis, an algorithm for abnormal change detection the temperature data in the chamber of ethylene cracking furnace is proposed. Based on the measured temperature data of ethylene cracking furnace in a petrochemical plant, simulation results show that the prediction and anomaly detection algorithms have high accuracy and effectiveness.

关键词： Temperature measurement Temperature distribution change detection algorithms Furnaces Linear regression Predictive models Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Land Cover change Estimation Using Region Covariance Estimates

引用

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS 2019年第3期16卷 347-351页

作者： Olding, W. C. Olivier, J. C. Salmon, B. P. Kleynhans, W. Univ Tasmania Sch Engn Hobart Tas 7005 Australia CSIR Meraka Inst Remote Sensing Res Unit ZA-0081 Pretoria South Africa

In this letter, we demonstrate the utility of estimating a probabilistic model of the underlying seasonal and interannual variations experienced by land cover time series in a given geographical region. Time series that deviate from these trajectories due to the human-induced change appear as outliers and can be detected using their Mahalanobis distance from the mean under the joint distribution of time samples. We apply this model to a collection of pixel time series acquired by the Moderate Resolution Imaging Spectroradiometer platform over Limpopo province, South Africa, for the task of identifying human settlement expansion. For estimation of the time of change, we present a hypothesis testing approach that tests for a decrease in correlation between samples before and after the change. This was found to be highly effective, yielding a mean absolute error of 52 days.

关键词： change detection algorithms covariance matrices density estimation robust algorithm remote sensing time series analysis

来源：评论

学校读者我要写书评

暂无评论

Efficient Application of AI for Target Tracking and Monitoring in Airborne Images:

Efficient Application of AI for Target Tracking and Monitori...

引用

Remote Sensing Symposium (InGARSS), 2020 IEEE India Geoscience and

作者： Vatsala Singh K.P. Singh Mody University of Science and Technology Rajasthan India Indian Institute of Technology Banaras Hindu University Varanasi India

ISBN: (纸本)9781665442503

With evolution of computing technology, its capability of solving complex problems faced in real life scenario have certainly escalated. One such problem of extraction and counting of building footprints using aerial images obtained from drone is looked upon in this paper.A typical image obtained from drone has many characteristic features like the spatial resolution i.e. the area that a single pixel of the image covers, pixel resolution and many more, and provides users with a 3 channel(RGB) image of a certain region which helps in assessing the landscape distribution, vegetation cover urbanization and monitoring the area. With so many efficient and intriguing applications, drone images have seen a definite upsurge in recent years. However, all such applications are painstakingly tedious and certainly require automation. Researchers are constantly working towards solving this problem and providing an optimal solution economically and computationally *** paper proposes to solve this problem by carrying out basic image processing steps enhanced using Deep Learning by efficiently harnessing the statistical features of image and applying adaptive thresholding to semantically segment and count building footprints, thus deriving a holistic algorithm that is capable of handling image with different spatial or pixel resolution.

关键词： Thresholding (Imaging) Target tracking change detection algorithms Buildings Vegetation mapping Prediction algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Combined Data-Driven and Model-Based Residual Selection Algorithm for Fault detection and Isolation

引用

IEEE TRANSACTIONS ON CONTROL SYSTEMS TECHNOLOGY 2019年第2期27卷 616-630页

作者： Jung, Daniel Sundstrom, Christofer Linkoping Univ Dept Elect Engn S-58183 Linkoping Sweden Ohio State Univ Ctr Automot Res Columbus OH 43210 USA

Selecting residual generators for detecting and isolating faults in a system is an important step when designing model-based diagnosis systems. However, finding a suitable set of residual generators to fulfill performance requirements is complicated by model uncertainties and measurement noise that have negative impact on fault detection performance. The main contribution is an algorithm for residual selection that combines model-based and data-driven methods to find a set of residual generators that maximizes fault detection and isolation performance. Based on the solution from the residual selection algorithm, a generalized diagnosis system design is proposed where test quantities are designed using multivariate residual information to improve detection performance. To illustrate the usefulness of the proposed residual selection algorithm, it is applied to find a set of residual generators to monitor the air path through an internal combustion engine.

关键词： Automotive applications change detection algorithms fault detection fault diagnosis machine learning

来源：评论

学校读者我要写书评

暂无评论

GraphBGS: Background Subtraction via Recovery of Graph Signals

GraphBGS: Background Subtraction via Recovery of Graph Signa...

引用

International Conference on Pattern Recognition

作者： Jhony H. Giraldo Thierry Bouwmans Laboratoire MIA La Rochelle Université La Rochelle France

Background subtraction is a fundamental preprocessing task in computer vision. This task becomes challenging in real scenarios due to variations in the background for both static and moving camera sequences. Several deep learning methods for background subtraction have been proposed in the literature with competitive performances. However, these models show performance degradation when tested on unseen videos; and they require huge amount of data to avoid overfitting. Recently, graph-based algorithms have been successful approaching unsupervised and semi-supervised learning problems. Furthermore, the theory of graph signal processing and semi-supervised learning have been combined leading to new insights in the field of machine learning. In this paper, concepts of recovery of graph signals are introduced in the problem of background subtraction. We propose a new algorithm called Graph BackGround Subtraction (GraphBGS), which is composed of: instance segmentation, background initialization, graph construction, graph sampling, and a semi-supervised algorithm inspired from the theory of recovery of graph signals. Our algorithm has the advantage of requiring less labeled data than deep learning methods while having competitive results on both: static and moving camera videos. GraphBGS outperforms unsupervised and supervised methods in several challenging conditions on the publicly available change detection (CDNet2014), and UCSD background subtraction databases.

关键词： Deep learning Machine learning algorithms change detection algorithms Pipelines Signal processing algorithms Semisupervised learning Signal processing

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：