A real-time unsupervised background extraction-based target detection method for hyperspectral imagery

Target detection is an important technique in hyperspectral image analysis. The high dimensionality of hyperspectral data provides the possibility of deeply mining the information hiding in spectra, and many targets that cannot be visualized by inspection can be detected. But this also brings some problems such as unknown background interferences at the same time. In this way, extracting and taking advantage of the background information in the region of interest becomes a task of great significance. In this paper, we present an unsupervised background extraction-based target detection method, which is called UBETD for short. The proposed UBETD takes advantage of the method of endmember extraction in hyperspectral unmixing, another important technique that can extract representative material signatures from the images. These endmembers represent most of the image information, so they can be reasonably seen as the combination of targets and background signatures. Since the background information is known, algorithm like target-constrained interference-minimized filter could then be introduced to detect the targets while inhibiting the interferences. To meet the rapidly rising demand of real-time processing capabilities, the proposed algorithm is further simplified in computation and implemented on a FPGA board. Experiments with synthetic and real hyperspectral images have been conducted comparing with constrained energy minimization, adaptive coherence/cosine estimator and adaptive matched filter to evaluate the detection and computational performance of our proposed method. The results indicate that UBETD and its hardware implementation RT-UBETD can achieve better performance and are particularly prominent in inhibiting interferences in the background. On the other hand, the hardware implementation of RT-UBETD can complete the target detection processing in far less time than the data acquisition time of hyperspectral sensor like HyMap, which confirms strict real-time processing capability of the proposed system.     

Speckle filtering in satellite SAR change detection imagery

Repeat-pass Synthetic Aperture Radar (SAR) imagery is useful for change detection. A disadvantage of SAR is the system-inherent speckle noise. This can be reduced by filtering. Various filter types and methods are described in the literature, but not one fits the speckle noise in change detection imagery. A new method is therefore developed in this paper. The new method is based on filtering the logarithmic-scaled ratio of SAR images. Logarithmic scaling changes the multiplicative speckle noise in the ratio-image into additive noise and alters the distribution, which simplifies and optimizes the subsequent filter process. The filter in the new method consists of an additive LLMMSE filter (Kuan et al. 1985), preceded by a structure detection stage for a better contour preserving performance. Testing the new method on a repeat-pass satellite SAR image-set gave an accurate overview of changes compared to a colour-composite of both images, other optical remote sensing images and maps of the same area.     

A minimum-cost thresholding technique for unsupervised change detection

We propose an automatic thresholding technique for difference images in unsupervised change detection. Such a technique takes into account the different costs that may be associated with commission and omission errors in the selection of the decision threshold. This allows the generation of maps in which the overall change-detection cost is minimized, i.e. the more critical kind of error is reduced according to end-user requirements.     

Early fire detection using non-linear multitemporal prediction of thermal imagery

This paper presents a sub-pixel thermal anomaly detection method based on predicting background pixel intensities using a non-linear function of a plurality of past images of the inspected scene. At present, the multitemporal approach to thermal anomaly detection is in its early development stage. In case of space-borne surveillance the multitemporal detection is complicated by both spatial and temporal variability of background surface properties, weather influences, viewing geometries, sensor noise, residual misregistration, and other factors. We use the problem of fire detection and the MODIS data to demonstrate that advanced multitemporal detection methods can potentially outperform the operationally used optimized contextual algorithms both under morning and evening conditions.     

An unsupervised change detection and recognition system for forestry

This article presents a new unsupervised method (AutoChange) for change detection and identification. It uses, as an input, two images, acquired on different dates, and a parameter list given by the user. Change detection and identification are performed in separate procedures, and the output is a five channel image estimating the change magnitude and characterizing the changed and unchanged areas. The method carries out the change analysis using homogeneous units selected from the images and only in the ultimate phase the whole image is classified. Changes are detected and identified using clustering in two phases. First, clustering is performed on the earlier and later images to form the so called 'primary clusters'. Second, clustering is performed within the primary clusters of the later image to produce the 'secondary clusters'. Then the change magnitude and change type are obtained by comparing the primary clusters in the earlier image to the secondary clusters in the later image. The method, which was tested in southern Finnish Boreal forest using Landsat Thematic Mapper data, could reliably detect and identify clearcuts. In addition, the method provided information on forest damage since the type of the spectral change was consistent on damaged areas despite a minor magnitude of the change.     

Fuzzy clustering algorithms for unsupervised change detection in remote sensing images

In this paper, we propose a context-sensitive technique for unsupervised change detection in multitemporal remote sensing images. The technique is based on fuzzy clustering approach and takes care of spatial correlation between neighboring pixels of the difference image produced by comparing two images acquired on the same geographical area at different times. Since the ranges of pixel values of the difference image belonging to the two clusters (changed and unchanged) generally have overlap, fuzzy clustering techniques seem to be an appropriate and realistic choice to identify them (as we already know from pattern recognition literatures that fuzzy set can handle this type of situation very well). Two fuzzy clustering algorithms, namely fuzzy c-means (FCM) and Gustafson-Kessel clustering (GKC) algorithms have been used for this task in the proposed work. For clustering purpose various image features are extracted using the neighborhood information of pixels. Hybridization of FCM and GKC with two other optimization techniques, genetic algorithm (GA) and simulated annealing (SA), is made to further enhance the performance. To show the effectiveness of the proposed technique, experiments are conducted on two multispectral and multitemporal remote sensing images. A fuzzy cluster validity index (Xie-Beni) is used to quantitatively evaluate the performance. Results are compared with those of existing Markov random field (MRF) and neural network based algorithms and found to be superior. The proposed technique is less time consuming and unlike MRF does not require any a priori knowledge of distributions of changed and unchanged pixels.     

Histogram thresholding for unsupervised change detection of remote sensing images

The change-detection problem can be viewed as an unsupervised classification problem with two classes corresponding to changed and unchanged areas. Image differencing is a widely used approach to change detection. It is based on the idea of generating a difference image that represents the modulus of the spectral change vectors associated with each pixel in the study area. To separate out the changed and unchanged classes in the difference image automatically, any unsupervised technique can be used. Thresholding is one of the cheapest techniques among them. However, in thresholding approaches, selection of the best threshold value is not a trivial task. In this work, several non-fuzzy and fuzzy histogram thresholding techniques are investigated and compared for the change-detection problem. Experimental results, carried out on different multitemporal remote sensing images (acquired before and after an event), are used to assess the effectiveness of each of the thresholding techniques. Among all the thresholding techniques investigated here, Liu's fuzzy entropy followed by Kapur's entropy are found to be the most robust techniques.     

Gradual land cover change detection based on multitemporal fraction images

This study proposes a new approach to change detection in remote sensing multi-temporal image data. Rather than allocating pixels to one of two disjoint classes (change, no-change) which is the approach most commonly found in the literature, we propose in this study to define change in terms of degrees of membership to the class change. The methodology aims to model images depicting the natural environment more realistically, taking into account that changes tend to occur in a continuum rather than being sharply distinguished. To this end, a sub-pixel approach is implemented to help detect degrees of change in every pixel. Three experiments employing the proposed approach using synthetic and real image data are reported and their results discussed.     

Correlation-based feature partition regression method for unsupervised anomaly detection

Applied Intelligence - Anomaly detection problem has been extensively studied in a variety of application domains, where the data tags are difficult to obtain. Most unsupervised algorithms rely on...     

Superpixel-based active contour model for unsupervised change detection from satellite images

This study proposes a superpixel-based active contour model (SACM) for unsupervised change detection from satellite images. The accuracy of change detection produced by the traditional active contour model suffers from the trade-off parameter. The SACM is designed to address this limitation through the incorporation of the spatial and statistical information of superpixels. The proposed method mainly consists of three steps. First, the difference image is created with change vector analysis method from two temporal satellite images. Second, statistical region merging method is applied on the difference image to produce a superpixel map. Finally, SACM is designed based on the superpixel map to detect changes from the difference image. The SACM incorporates spatial and statistical information and retains the accurate shapes and outlines of superpixels. Experiments were conducted on two data sets, namely Landsat-7 Enhanced Thematic Mapper Plus and SPOT 5, to validate the proposed method. Experimental results show that SACM reduces the effects of the trade-off parameter. The proposed method also increases the robustness of the traditional active contour model for input parameters and improves its effectiveness. In summary, SACM often outperforms some existing methods and provides an effective unsupervised change detection method.     

A genetic clustering method for intrusion detection

Traditional intrusion detection methods lack extensibility in face of changing network configurations as well as adaptability in face of unknown attack types. Meanwhile, current machine-learning algorithms need labeled data for training first, so they are computational expensive and sometimes misled by artificial data. In this paper, a new detection algorithm, the Intrusion Detection Based on Genetic Clustering (IDBGC) algorithm, is proposed. It can automatically establish clusters and detect intruders by labeling normal and abnormal groups. Computer simulations show that this algorithm is effective for intrusion detection.     

混合的SAR图像变化检测算法

为尽可能多地消除遥感图像变化检测过程中“伪变化”信息的影响,获得比较客观的感兴趣区域变化检测结果,针对遥感图像中SAR图像的特点,提出一种混合的SAR图像变化检测算法。对已配准好的图像进行Frost滤波,用邻域比值的方法构造差异图,对得到的差异图进行非下采样轮廓波变换（NSCT）,对变换得到的高频子带和低频子带分别处理,用模糊C均值（FCM）聚类算法得到变化检测的结果。实验结果表明,该算法模型很好地保留了图像变化区域的细节,提高了变化检测准确性。     

Detection of vegetation abundance change in the alpine tree line using multitemporal Landsat Thematic Mapper imagery

Detection of alpine tree line change using pixel-based approaches on medium spatial resolution imagery is challenging because of very slow tree sprawl without obvious boundaries. However, vegetation abundance or density in the tree line zones may change over time and such a change may be detected using subpixel-based approaches. In this research, a linear spectral mixture analysis (LSMA)-based approach was used to examine alpine tree line change in the Northern Tianshan Mountains located in Northwestern China. Landsat Thematic Mapper (TM) imagery was unmixed into three fraction images (i.e. green vegetation – GV, shade, and soil) using the LSMA approach. The GV and soil fractions at different years were used to examine vegetation abundance change based on samples in the alpine tree line. The results show that Picea schrenkiana abundance around the top of the forested area increased approximately by 18.6% between 1990 and 2010, but remained stable in the central forest region over this period. Juniperus sabina abundance around the top of the forested area, in the central scrub region, and at the top of the scrub region increased approximately by 19.3%, 8.2%, and 15.6%, respectively. The increased vegetation abundance and decreased soil abundance of both P. schrenkiana and J. sabina indicate vegetation sprawl in the alpine tree line between 1990 and 2010. This research will be valuable for better understanding the impacts of climate change on vegetation change in the alpine tree line of central Asia.     

A novel approach based on structural information for change detection in SAR images

Structural information, extracted by simulating the human visual system (HVS), is independent of viewing conditions and individual observers. Structural similarity (SSIM), a measure of similarity between two images, has been widely used in image quality assessment. Given the fact that the change detection techniques identify the changed area by the similarity of multi-temporal images, SSIM has significant prospect in change detection of synthetic aperture radar (SAR) images. However, the experimental results show that SSIM performs worse in change detection of multi-temporal SAR images. In this study, we first propose an advanced SSIM (ASSIM) based on a two-step assumption of extracting structural information and a visual attention measure (VAM) model. Then, we propose a novel approach based on ASSIM for change detection in SAR images. SSIM, ASSIM, and state-of-the-art methods are tested on two datasets to compare their performances in change detection of SAR images. Experimental results show that the proposed method can acquire a better difference image than SSIM and other state-of-the-art methods, and improve the accuracy of change detection in SAR images effectively.     

Dark-spot detection from SAR intensity imagery with spatial density thresholding for oil-spill monitoring

Dark-spot detection is a critical and fundamental step in marine oil-spill detection and monitoring. In this paper, a novel approach for automated dark-spot detection using synthetic aperture radar (SAR) intensity imagery is presented. The key to the approach is making use of a spatial density feature to differentiate between dark spots and the background. A detection window is passed through the entire SAR image. First, intensity threshold segmentation is applied to each window. Pixels with intensities below the threshold are regarded as potential dark-spot pixels while the others are potential background pixels. Second, the density of potential background pixels is estimated using kernel density estimation within each window. Pixels with densities below a certain threshold are the real dark-spot pixels. Third, an area threshold and a contrast threshold are used to eliminate any remaining false targets. In the last step, the individual detection results are mosaicked to produce the final result. The proposed approach was tested on 60 RADARSAT-1 ScanSAR intensity images which contain verified oil-spill anomalies. The same parameters were used in all tests. For the overall dataset, the average of commission error, omission error, and average difference were 7.0%, 6.1%, and 0.4 pixels, respectively. The average number of false alarms was 0.5 per unit image and the average computational time for a detection window was 1.2 s using a PC-based MATLAB platform. Our experimental results demonstrate that the proposed approach is fast, robust and effective.     

基于Otsu方法和数学形态学的SAR图像海岸线检测

合成孔径雷达(SAR)图像海岸线检测,在很多海洋应用中具有重要意义。由于受海风和海浪影响,海面有时会产生强回波信号,以及受speckle噪声等其他因素的影响,SAR图像中海洋和陆地缺乏对比度,边界不清晰,用传统的阈值门限法等进行海岸线检测很困难。本文提出一种改进的海岸线检测方法,该算法引入最大类间方差法(Otsu方法)和数学形态学算法,以较小的计算量检测出了海岸线。通过使用Envisat ASAR图像进行实验,证明该方法具有较好的检测效果和检测速度,检测出的海岸线和原始图像的海岸线有很好的匹配,检测精度与边界追踪算法比较有所提高。     

A method for detecting large-scale forest cover change using coarse spatial resolution imagery

Many large countries, including Canada, rely on earth observation as a practical and cost-effective means of monitoring their vast inland ecosystems. A potentially efficient approach is one that detects vegetation changes over a hierarchy of spatial scales ranging from coarse to fine. This paper presents a Change Screening Analysis Technique (Change-SAT) designed as a coarse filter to identify the location and timing of large (>5-10 km²) forest cover changes caused by anthropogenic and natural disturbances at an annual, continental scale. The method uses change metrics derived from 1-km multi-temporal SPOT VEGETATION and NOAA AVHRR imagery (reflectance, temperature, and texture information) and ancillary spatial variables (proximity to active fires, roads, and forest tenures) in combination with logistic regression and decision tree classifiers. Major forest changes of interest include wildfires, insect defoliation, forest harvesting, and flooding. Change-SAT was tested for 1998-2000 using an independent sample of change and no-change sites over Canada. Overall accuracy was 94% and commission error, especially critical for large-area change applications, was less than 1%. Regions identified as having major or widespread changes could be targeted for more detailed investigation and mapping using field visits, aerial survey, or fine resolution EO methods, such as those being applied under Canadian monitoring programs. This multi-resolution approach could be used as part of a forest monitoring system to report on carbon stocks and forest stewardship.     

Research on SAR image change detection algorithm based on hybrid genetic FCM and image registration

Multimedia Tools and Applications - At present, image change detection technology as an important image processing technology has been widely used, and a novel synthetic aperture radar (SAR) image...     

A robust unsupervised anomaly detection framework

Applied Intelligence - Anomaly detection plays an essential role in monitoring dependable systems and networks such as computer clusters, water treatment systems, sensor networks, etc. However,...     

Latent representation learning based autoencoder for unsupervised feature selection in hyperspectral imagery

In hyperspectral image (HSI) analysis, high-dimensional data may contain noisy, irrelevant and redundant information. To mitigate the negative effect from these information, feature selection is one of the useful solutions. Unsupervised feature selection is a data preprocessing technique for dimensionality reduction, which selects a subset of informative features without using any label information. Different from the linear models, the autoencoder is formulated to nonlinearly select informative features. The adjacency matrix of HSI can be constructed to extract the underlying relationship between each data point, where the latent representation of original data can be obtained via matrix factorization. Besides, a new feature representation can be also learnt from the autoencoder. For a same data matrix, different feature representations should consistently share the potential information. Motivated by these, in this paper, we propose a latent representation learning based autoencoder feature selection (LRLAFS) model, where the latent representation learning is used to steer feature selection for the autoencoder. To solve the proposed model, we advance an alternative optimization algorithm. Experimental results on three HSI datasets confirm the effectiveness of the proposed model.