检索结果-内蒙古大学图书馆

A Novel Cluster Kernel RX Algorithm for Anomaly and change detection Using Hyperspectral Images

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2016年第11期54卷 6497-6504页

作者： Zhou, Jin Kwan, Chiman Ayhan, Bulent Eismann, Michael T. Google Inc Mountain View CA USA Signal Proc Inc Rockville MD 20850 USA Air Force Res Lab Dayton OH 45433 USA Air Force Inst Technol Wright Patterson AFB OH 45433 USA

The Reed-Xiaoli (RX) algorithm has been widely used as an anomaly detector for hyperspectral images. Recently, kernel RX (KRX) has been proven to yield high performance in anomaly detection and change detection. In this paper, we present a generalization of the KRX algorithm. The novel algorithm is called cluster KRX (CKRX), which becomes KRX under certain conditions. The key idea is to group background pixels into clusters and then apply a fast eigendecomposition algorithm to generate the anomaly detection index. Both global and local versions of CKRX have been implemented. Application to anomaly detection using actual hyperspectral images is included. In addition to anomaly detection, the CKRX algorithm has been integrated with other prediction algorithms for change detection. Spatially registered visible and near-infrared hyperspectral images collected from a tower-based geometry have been used in the anomaly and change detection studies. Receiver operating characteristics curves and actual computation times were used to compare different algorithms. It was demonstrated that CKRX has comparable detection performance as KRX, but with much lower computational requirements.

关键词： Anomaly detection change detection algorithms cluster kernel RX (CKRX) hyperspectral imaging kernel RX (KRX) receiver operating characteristics (ROC) Reed-Xiaoli (RX)

来源：评论

学校读者我要写书评

暂无评论

NEWMA: A New Method for Scalable Model-Free Online change-Point detection

引用

IEEE TRANSACTIONS ON SIGNAL PROCESSING 2020年 68卷 3515-3528页

作者： Keriven, Nicolas Garreau, Damien Poli, Iacopo CNRS GIPSA Lab F-38000 Grenoble France Univ Cote Azur INRIA CNRS LJAD F-06108 Nice France LightOn F-75005 Paris France

We consider the problem of detecting abrupt changes in the distribution of a multi-dimensional time series, with limited computing power and memory. In this paper, we propose a new, simple method for model-free online change-point detection that relies only on fast and light recursive statistics, inspired by the classical Exponential Weighted Moving Average algorithm (EWMA). The proposed idea is to compute two EWMA statistics on the stream of data with different forgetting factors, and to compare them. By doing so, we show that we implicitly compare recent samples with older ones, without the need to explicitly store them. Additionally, we leverage Random Features (RFs) to efficiently use the Maximum Mean Discrepancy as a distance between distributions, furthermore exploiting recent optical hardware to compute high-dimensional RFs in near constant time. We show that our method is significantly faster than usual non-parametric methods for a given accuracy.

关键词： Microsoft Windows Radio frequency Signal processing algorithms Kernel Brain modeling Computational modeling Streaming media change detection algorithms Hilbert space method of moments optical computing

来源：评论

学校读者我要写书评

暂无评论

Automatic SAR change detection Based on Visual Saliency and Multi-Hierarchical Fuzzy Clustering

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING 2022年 15卷 7755-7769页

作者： Peng, Yao Bin Cui Yin, Hujun Zhang, Yonghong Du, Peijun Nanjing Univ Posts & Telecommun Sch Geog & Biol Informat Nanjing 210023 Peoples R China Nanjing Univ Sch Geog & Ocean Sci Nanjing 210023 Peoples R China Univ Manchester Dept Elect & Elect Engn Manchester M13 9PL Lancs England Chinese Acad Surveying & Mapping Beijing 100830 Peoples R China

change detection based on multi-temporal synthetic aperture radar (SAR) images plays a significant role in environmental and earth observations. With the advancement in deep neural networks, existing work in the literature mainly concentrates on developing self-supervised methods to generate pseudo-labeled samples to guide the subsequent deep learning based detection. However, this way of selecting sample inevitably introduces erroneous labels and imbalance between unchanged and changed classes, thus causing deterioration in change detection performance. To mitigate these issues, we have proposed a SAR change detection network based on visual saliency and multi-hierarchical fuzzy clustering. Specifically, with multi-dimensional difference feature representations, a visual saliency based difference map is constructed for accurate difference feature extraction. By integrating neighborhood information and hierarchical clustering, the multi-hierarchical fuzzy local information C-means clustering algorithm has been developed to identify potential changed regions for sample selection. A class-balanced adaptive focal loss has further been incorporated into the network training to obtain accurate predictions. Extensive experiments and comparisons on five datasets have been performed. The proposed method has achieved averaged accuracy of 99.07% and Kappa coefficient of 79.87%, outperforming other state-of-the-art algorithms both visually and quantitatively.

关键词： Visualization Feature extraction Radar polarimetry Clustering algorithms Synthetic aperture radar change detection algorithms Adaptive systems change detection classed-balanced adaptive focal loss fuzzy clustering synthetic aperture radar (SAR) visual saliency difference map

来源：评论

学校读者我要写书评

暂无评论

3M-CDNet-V2: An Efficient Medium-Weight Neural Network for Remote Sensing Image change detection

引用

IEEE ACCESS 2022年 10卷 89581-89597页

作者： Zhao, Bo Tang, Panpan Luo, Xiaoyan Liu, Dongsheng Wang, Hui Res Ctr Big Data Technol Nanhu Lab Jiaxing 314000 Peoples R China PIESAT Int Informat Technol Ltd Beijing 100195 Peoples R China

Remote sensing-based change detection (CD) is a critical technique of detecting land surface changes in earth observation. Inspired by recent success of a lightweight CD network- 3M-CDNet, we implemented 9 meaningful modifications to it, for example, the incorporation of MHSA (Multi-Head Self-Attention). This elaborately designed model is termed as 3M-CDNet-V2. Its effectiveness and advantages were demonstrated on three engineering CD datasets, and experimental results indicated that: (1) relative to other state-of-the-art algorithms, the proposed model obtained very competitive or slight better performance on both visual comparison and quantitative metrics evaluation. (2) By applying a novel transfer learning strategy, 3M-CDNet-V2 could perform well on the small dataset. (3) The incorporation of MHSA brings a substantial accuracy improvement while moderately increasing the computational complexity. (4) The late fusion framework and deep supervision contribute most to the performance gain of 3M-CDNet-V2, while the introduction of low-level features to the classifier by skip connection could guide the model to focus on detailed spatial information such as small changes, narrow shaped objects, or accurate boundaries. We hope that our 3M-CDNet-V2 model helps in improving the understanding of network architecture design for CD.

关键词： Feature extraction Semantics Transformers Remote sensing Computer architecture Computational modeling Neural networks change detection algorithms Neural network remote sensing medium weight change detection

来源：评论

学校读者我要写书评

暂无评论

Graphical Models in Meshed Distribution Grids: Topology Estimation, change detection & Limitations

引用

IEEE TRANSACTIONS ON SMART GRID 2020年第5期11卷 4299-4310页

作者： Deka, Deepjyoti Talukdar, Saurav Chertkov, Michael Salapaka, Murti V. Los Alamos Natl Lab Los Alamos NM 87545 USA Univ Minnesota Coll Sci & Engn Minneapolis MN 55455 USA Univ Arizona Tucson AZ 85721 USA Univ Minnesota Dept Elect & Comp Engn Minneapolis MN 55455 USA

Graphical models is a succinct way to represent the structure of a probability distributions. This article analyzes the graphical model of nodal voltages in non-radial power distribution grids. Using algebraic and structural properties of graphical models, algorithms exactly determining topology and detecting line changes for distribution grids are presented along with their theoretical limitations. We show that if distribution grids have cycles/loops of size greater than three, then nodal voltages are sufficient for efficient topology estimation without additional assumptions on system parameters. In contrast, line failure or change detection using nodal voltages does not require any structural assumption. Under noisy measurements, we provide the first non-trivial bounds on the maximum noise that the system can tolerate for asymptotically correct topology recovery. The performance of the designed algorithms is validated with non-linear AC power flow samples generated by Matpower on test grids, including scenarios with injection correlations and system noise.

关键词： Topology Graphical models Voltage measurement Estimation change detection algorithms Noise measurement Mathematical model Concentration matrix conditional independence distribution grids graphical lasso graphical models power flows line outage measurement noise

来源：评论

学校读者我要写书评

暂无评论

Asymptotic Performance Analysis of Distributed Non-Bayesian Quickest change detection With Energy Harvesting Sensors

引用

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS 2022年第4期58卷 3697-3707页

作者： Biswas, Sinchan Dey, Subhrakanti Lund Univ Dept Elect & Informat Technol S-22100 Lund Sweden Uppsala Univ Div Signals & Syst S-75105 Uppsala Sweden NUI Maynooth Hamilton Inst Maynooth W23 F2H6 Kildare Ireland

This article focuses on the distributed non-Bayesian quickest change detection based on the cumulative sum (CUSUM) algorithm in an energy harvesting wireless sensor network, where the distributions before and after the change point are assumed to be known. Each sensor is powered by randomly available harvested energy from the surroundings. It samples the observation signal and computes the log-likelihood ratios (LLRs) of the aforementioned two distributions if enough energy is available in its battery for sensing and processing the sample (E-s). Otherwise, the sensor decides to abstain from the sensing process during that time slot and waits until it accumulates enough energy to perform the sensing and processing of a sample. This LLR is used for performing the CUSUM test to arrive at local decisions about the change point, which are then combined at the fusion center (FC) by a predecided fusion rule to arrive at a global decision. In this article, we derive the asymptotic expressions (as the average time to a false alarm goes to infinity) for the expected detection delay and the expected time to a false alarm at the FC for three common fusion rules, namely, OR, AND, and r out of N majority rule, respectively, by considering the scenario, where the average harvested energy at each sensor is greater than the energy required for sensing and processing a sample E-s. To this end, we use the theory of order statistics and the asymptotic distribution of the first passage times of the local decisions. Numerical results are also provided to support the theoretical claims.

关键词： Sensors Wireless sensor networks Energy harvesting Delays Sensor fusion detection algorithms change detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Land-use and vegetation change detection in Plastira artificial lake catchment (Greece) by using remote-sensing and GIS techniques

引用

INTERNATIONAL JOURNAL OF REMOTE SENSING 2013年第4期34卷 1265-1281页

作者： Markogianni, V. Dimitriou, E. Kalivas, D. P. Inst Inland Waters Hellenic Ctr Marine Res Anavissos Attikis 19013 Greece Agr Univ Athens Lab Soils & Agr Chem Athens 11855 Greece

Detecting changes in the land-use and vegetation conditions by using remote-sensing techniques is a common approach nowadays to assessing human-induced impacts in a specific area. For this purpose, a series of vegetation indices and change detection algorithms such as the normalized difference vegetation index (NDVI), Iterative Self-Organizing Data Analysis Technique (ISODATA), and k-means have been efficiently developed and used in many studies worldwide. However, identifying the driving forces for the estimated changes in land use and vegetation has always been a difficult and challenging task. In this study, Landsat and Systeme Pour l'Observation de la Terre (SPOT) images have been used to estimate the NDVI and land-use changes at the Plastira artificial lake catchment in the period 1984-2009. The recorded vegetation changes were correlated with a series of environmental and human-related parameters such as precipitation, temperature, specific land uses, and topography to identify the dominant factors of the aforementioned changes. This was done using both linear and geographically weighted regression methods. The results indicate that the precipitation and temperature fluctuations are strongly correlated with the vegetation conditions, whereas, as far as the topographic parameters are concerned, the aspect and slope affect mostly the particular vegetation index (the NDVI) of the study area.

关键词： normalized difference vegetation index change detection algorithms Land use remote sensing Catchment area vegetation Vegetation changes Vegetation Index DRIVING FORCE artificial lake

来源：评论

学校读者我要写书评

暂无评论

change detection in SAR images based on the logarithmic transformation and total variation denoising method

引用

REMOTE SENSING LETTERS 2017年第3期8卷 214-223页

作者： Wang, Xueguo Jia, Zhenhong Yang, Jie Kasabov, Nikola Xinjiang Univ Coll Informat Sci & Engn Urumqi 830046 Peoples R China Shanghai Jiao Tong Univ Inst Image Proc & Pattern Recognit Shanghai Peoples R China Auckland Univ Technol Knowledge Engn & Discovery Res Inst Auckland New Zealand

Noise interference and the need to process massive image data present challenges to change detection in synthetic aperture radar (SAR) images. In order to improve the change detection accuracy and decrease the processing time, this paper proposes a novel unsupervised change detection algorithm for SAR images. The logarithmic transformation is applied to transform images into the logarithmic domain, while the multiplicative noise in images is transformed into additive noise. The total variation (TV) denoising algorithm is then used to reduce image noise, and the difference operator in the logarithmic domain is employed to provide the difference image. The k-means clustering algorithm, which does not require consideration of the statistical properties of an image, is employed to cluster the difference image into two disjointed classes: changed and unchanged. The experimental results demonstrate that change detection results achieved by the proposed algorithm offer great improvement over existing algorithms in terms of objective quantitative indices and the visual effect.

关键词： difference image image noise Specific absorption rate multiplicative noise difference operator Rescue Visual effects logarithmic transformation Radar polarimetry algorithms Noise reduction images change detection algorithms

来源：评论

学校读者我要写书评

暂无评论

A Novel Video Dataset for change detection Benchmarking

引用

IEEE TRANSACTIONS ON IMAGE PROCESSING 2014年第11期23卷 4663-4679页

作者： Goyette, Nil Jodoin, Pierre-Marc Porikli, Fatih Konrad, Janusz Ishwar, Prakash Univ Sherbrooke Fac Sci Dept Informat Sherbrooke PQ J1K 2R1 Canada Mitsubishi Elect Res Labs Cambridge MA 02139 USA Boston Univ Dept Elect & Comp Engn Boston MA 02215 USA

change detection is one of the most commonly encountered low-level tasks in computer vision and video processing. A plethora of algorithms have been developed to date, yet no widely accepted, realistic, large-scale video data set exists for benchmarking different methods. Presented here is a unique change detection video data set consisting of nearly 90 000 frames in 31 video sequences representing six categories selected to cover a wide range of challenges in two modalities (color and thermal infrared). A distinguishing characteristic of this benchmark video data set is that each frame is meticulously annotated by hand for ground-truth foreground, background, and shadow area boundaries-an effort that goes much beyond a simple binary label denoting the presence of change. This enables objective and precise quantitative comparison and ranking of video-based change detection algorithms. This paper discusses various aspects of the new data set, quantitative performance metrics used, and comparative results for over two dozen change detection algorithms. It draws important conclusions on solved and remaining issues in change detection, and describes future challenges for the scientific community. The data set, evaluation tools, and algorithm rankings are available to the public on a website(1) and will be updated with feedback from academia and industry in the future.

关键词： change detection algorithms benchmark testing video surveillance

来源：评论

学校读者我要写书评

暂无评论

change detection Algorithm for Multi-Temporal Remote Sensing Images Based on Adaptive Parameter Estimation

引用

IEEE ACCESS 2020年 8卷 106083-106096页

作者： Chen, Yu Ming, Zutao Menenti, Massimo China Univ Geosci Sch Geog & Informat Engn Wuhan 430078 Peoples R China Delft Univ Technol Fac Civil Engn & Geosci Dept Geosci & Remote Sensing NL-2628 CN Delft Netherlands

This paper proposes a multi-temporal image change detection algorithm based on adaptive parameter estimation, which is used to solve the problems of severe interference of coherent speckle noise and the retention of detailed information about changing regions in synthetic aperture radar remote sensing images. The change area in the initial differential image has local consistency and global prominence. By detecting the significant area to locate similar change areas, the coherent speckle noise outside the area can be eliminated. The use of hierarchical FCM clustering to automatically generate training samples can improve the reliability of training samples. In addition, in order to increase the distinction between the changed area and the non-changed area, a sparse automatic encoder is used to extract the changed features and generate a change detection map. Experiments using 4 sets of SAR images show that the algorithm can effectively reduce the effect of speckle noise on detection accuracy, the extraction of changing areas is more complete and meticulous, and the false detection rate is greatly reduced. Since the images in different time phases will be disturbed by weather, clouds, sea water, etc., the target segmentation algorithm can be used to extract the target of interest and highlight the changing area. Principal component analysis and k-means clustering method are used to reduce the influence of isolated pixels, and change information is extracted to obtain different images. The experiment uses four sets of image data of islands and reefs. The experiment proves that the algorithm can well eliminate external interference, improve the accuracy of change detection, and have a good detection effect on the area of islands and reefs. The adaptive parameter estimation plays a good role in the detection of changing areas, and the visual effect is better, which can improve the accuracy of the detection results.

关键词： Remote sensing Image segmentation Feature extraction change detection algorithms Sparse matrices Synthetic aperture radar detection algorithms Adaptive parameters multi-temporal remote sensing images change detection model superficial superposition

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：