Showing papers on "Change detection published in 2004"

Change detection techniques

Abstract: Timely and accurate change detection of Earth's surface features is extremely important for understanding relationships and interactions between human and natural phenomena in order to promote better decision making. Remote sensing data are primary sources extensively used for change detection in recent decades. Many change detection techniques have been developed. This paper summarizes and reviews these techniques. Previous literature has shown that image differencing, principal component analysis and post-classification comparison are the most common methods used for change detection. In recent years, spectral mixture analysis, artificial neural networks and integration of geographical information system and remote sensing data have become important techniques for change detection applications. Different change detection algorithms have their own merits and no single approach is optimal and applicable to all cases. In practice, different algorithms are often compared to find the best change detection results for a specific application. Research of change detection techniques is still an active topic and new techniques are needed to effectively use the increasingly diverse and complex remotely sensed data available or projected to be soon available from satellite and airborne sensors. This paper is a comprehensive exploration of all the major change detection approaches implemented as found in the literature.

Digital change detection methods in ecosystem monitoring: a review

Abstract: Techniques based on multi-temporal, multi-spectral, satellite-sensor-acquired data have demonstrated potential as a means to detect, identify, map and monitor ecosystem changes, irrespective of their causal agents. This review paper, which summarizes the methods and the results of digital change detection in the optical/infrared domain, has as its primary objective a synthesis of the state of the art today. It approaches digital change detection from three angles. First, the different perspectives from which the variability in ecosystems and the change events have been dealt with are summarized. Change detection between pairs of images (bi-temporal) as well as between time profiles of imagery derived indicators (temporal trajectories), and, where relevant, the appropriate choices for digital imagery acquisition timing and change interval length definition, are discussed. Second, pre-processing routines either to establish a more direct linkage between remote sensing data and biophysical phenomena, or to temporally mosaic imagery and extract time profiles, are reviewed. Third, the actual change detection methods themselves are categorized in an analytical framework and critically evaluated. Ultimately, the paper highlights how some of these methodological aspects are being fine-tuned as this review is being written, and we summarize the new developments that can be expected in the near future. The review highlights the high complementarity between different change detection methods.

Statistical modeling of complex backgrounds for foreground object detection

Abstract: This paper addresses the problem of background modeling for foreground object detection in complex environments. A Bayesian framework that incorporates spectral, spatial, and temporal features to characterize the background appearance is proposed. Under this framework, the background is represented by the most significant and frequent features, i.e., the principal features , at each pixel. A Bayes decision rule is derived for background and foreground classification based on the statistics of principal features. Principal feature representation for both the static and dynamic background pixels is investigated. A novel learning method is proposed to adapt to both gradual and sudden "once-off" background changes. The convergence of the learning process is analyzed and a formula to select a proper learning rate is derived. Under the proposed framework, a novel algorithm for detecting foreground objects from complex environments is then established. It consists of change detection, change classification, foreground segmentation, and background maintenance. Experiments were conducted on image sequences containing targets of interest in a variety of environments, e.g., offices, public buildings, subway stations, campuses, parking lots, airports, and sidewalks. Good results of foreground detection were obtained. Quantitative evaluation and comparison with the existing method show that the proposed method provides much improved results.

Object-based classification of remote sensing data for change detection

Abstract: In this paper, a change detection approach based on an object-based classification of remote sensing data is introduced. The approach classifies not single pixels but groups of pixels that represent already existing objects in a GIS database. The approach is based on a supervised maximum likelihood classification. The multispectral bands grouped by objects and very different measures that can be derived from multispectral bands represent the n -dimensional feature space for the classification. The training areas are derived automatically from the geographical information system (GIS) database. After an introduction into the general approach, different input channels for the classification are defined and discussed. The results of a test on two test areas are presented. Afterwards, further measures, which can improve the result of the classification and enable the distinction between more land-use classes than with the introduced approach, are presented.

Particle methods for change detection, system identification, and control

Abstract: Particle methods are a set of powerful and versatile simulation-based methods to perform optimal state estimation in nonlinear non-Gaussian state-space models. The ability to compute the optimal filter is central to solving important problems in areas such as change detection, parameter estimation, and control. Much recent work has been done in these areas. The objective of this paper is to provide a detailed overview of them.

Application of anomaly detection algorithms for detecting SYN flooding attacks

Abstract: We investigate statistical anomaly detection algorithms for detecting SYN flooding, which is the most common type of denial of service (DoS) attack. The two algorithms considered are an adaptive threshold algorithm and a particular application of the cumulative sum (CUSUM) algorithm for change point detection. The performance is investigated in terms of the detection probability, the false alarm ratio, and the detection delay. Particular emphasis is on investigating the tradeoffs among these metrics and how they are affected by the parameters of the algorithm and the characteristics of the attacks. Such an investigation can provide guidelines to effectively tune the parameters of the detection algorithm to achieve specific performance requirements in terms of the above metrics.

Change-point monitoring for the detection of DoS attacks

Abstract: This paper presents a simple and robust mechanism, called change-point monitoring (CPM), to detect denial of service (DoS) attacks. The core of CPM is based on the inherent network protocol behavior and is an instance of the sequential change point detection. To make the detection mechanism insensitive to sites and traffic patterns, a nonparametric cumulative sum (CUSUM) method is applied, thus making the detection mechanism robust, more generally applicable, and its deployment much easier. CPM does not require per-flow state information and only introduces a few variables to record the protocol behaviors. The statelessness and low computation overhead of CPM make itself immune to any flooding attacks. As a case study, the efficacy of CPM is evaluated by detecting a SYN flooding attack - the most common DoS attack. The evaluation results show that CPM has short detection latency and high detection accuracy

On the possibility of automatic multisensor image registration

Abstract: Multisensor image registration is needed in a large number of applications of remote sensing imagery. The accuracy achieved with usual methods (manual control points extraction, estimation of an analytical deformation model) is not satisfactory for many applications where a subpixel accuracy for each pixel of the image is needed (change detection or image fusion, for instance). Unfortunately, there are few works in the literature about the fine registration of multisensor images and even less about the extension of approaches similar to those based on fine correlation for the case of monomodal imagery. In this paper, we analyze the problem of the automatic multisensor image registration and we introduce similarity measures which can replace the correlation coefficient in a deformation map estimation scheme. We show an example where the deformation map between a radar image and an optical one is fully automatically estimated.

Robust speaker change detection

Abstract: Most commonly used criteria for speaker change detection like log likelihood ratio (LLR) and Bayesian information criterion (BIC) have an adjustable threshold/penalty parameter to make speaker change decisions. These parameters are not always robust to different acoustic conditions and have to be tuned. In this letter, we present a criterion which can be used to identify speaker changes in an audio stream without such tuning. The criterion consists of calculating the LLR of two models with the same number of parameters. Results on the Hub4 1997 evaluation set indicate that we achieve a performance comparable to using BIC with optimal penalty term.

Algorithms and methods of airborne laser-scanning for forest measurements

Abstract: Extracting forest variables from airborne laser scanner has less than 10 years of history. During that time, however, a new area in the field of forest studies has emerged. This paper describes existing algorithms and methods of airborne laser scanning that are used for forest measurements. The methods are divided into the following categories: 1) extraction of DTM (digital terrain model), 2) extraction of canopy height, 3) extraction of statistical variables from laser data, 4) extraction of individual tree information using image processing techniques, 5) integrating aerial image data with laser scanner, 6) use of intensity and waveform information, and 7) use of change detection methods.

Accuracy analysis of remote sensing change detection by rule-based rationality evaluation with post-classification comparison

Abstract: Accuracy assessment for remote sensing classification is commonly based on using an error matrix, or confusion table, which needs reference, or ‘ground truthing’, data to support. When undertaking ...

Segmentation of the face and hands in sign language video sequences using color and motion cues

Abstract: We present a hand and face segmentation methodology using color and motion cues for the content-based representation of sign language video sequences. The methodology consists of three stages: skin-color segmentation; change detection; face and hand segmentation mask generation. In skin-color segmentation, a universal color-model is derived and image pixels are classified as skin or nonskin based on their Mahalanobis distance. We derive a segmentation threshold for the classifier. The aim of change detection is to localize moving objects in a video sequences. The change detection technique is based on the F test and block-based motion estimation. Finally, the results from skin-color segmentation and change detection are analyzed to segment the face and hands. The performance of the algorithm is illustrated by simulations carried out on standard test sequences.

Neural Correlates of Change Detection and Change Blindness in a Working Memory Task

Abstract: Detecting changes in an ever-changing environment is highly advantageous, and this ability may be critical for survival. In the present study, we investigated the neural substrates of change detection in the context of a visual working memory task. Subjects maintained a sample visual stimulus in short-term memory for 6 s, and were asked to indicate whether a subsequent, test stimulus matched or did not match the original sample. To study change detection largely uncontaminated by attentional state, we compared correct change and correct no-change trials at test. Our results revealed that correctly detecting a change was associated with activation of a network comprising parietal and frontal brain regions, as well as activation of the pulvinar, cerebellum, and inferior temporal gyrus. Moreover, incorrectly reporting a change when none occurred led to a very similar pattern of activations. Finally, few regions were differentially activated by trials in which a change occurred but subjects failed to detect it (change blindness). Thus, brain activation was correlated with a subject’s report of a change, instead of correlated with the physical change per se. We propose that frontal and parietal regions, possibly assisted by the cerebellum and the pulvinar, might be involved in controlling the deployment of attention to the location of a change, thereby allowing further processing of the visual stimulus. Visual processing areas, such as the inferior temporal gyrus, may be the recipients of top-down feedback from fronto-parietal regions that control the reactive deployment of attention, and thus exhibit increased activation when a change is reported (irrespective of whether it occurred or not). Whereas reporting that a change occurred, be it correctly or incorrectly, was associated with strong activation in fronto-parietal sites, change blindness appears to involve very limited territories.

Inferring Driver Intent: A Case Study in Lane-Change Detection:

Abstract: This paper introduces a robust, real-time system for detecting driver lane changes. Under the framework of a “mind-tracking architecture,” the system simulates a set of possible driver intentions a...

Application of log-cumulants to the detection of spatiotemporal discontinuities in multitemporal SAR images

Abstract: Multitemporal satellite synthetic aperture radar (SAR) images are a useful source of information for geophysicists to monitor changing regions. In this paper, a new approach is proposed to extract from multitemporal SAR images two kinds of information: temporal changes (flooded areas, coastline erosion, etc.) and stable spatial features (roads, rivers, etc.). The novelty of the proposed approach is to detect simultaneously these two kinds of discontinuities. In a first step, the contrast and the heterogeneity information is extracted by a "multitemporal" application of the ratio of local means and by new three-dimensional texture parameters based on the log-cumulants. In a second step, the resulting attributes that measure the time variability or the presence of spatial features are merged. An interactive fuzzy fusion approach is proposed to provide end-users with a simple and easily understandable tool for tuning the change-detection results. The performances of the proposed attributes and fusion technique are presented on a set of seven multitemporal SAR images acquired by the European Remote Sensing (ERS-1) satellite.

Hyperspectral change detection and supervised matched filtering based on covariance equalization

Abstract: For hyperspectral remote sensing, the physics-based transformation connecting two multivariate sets of spectral radiance data of the same scene collected at two disparate times is approximately linear (plus an offset). Generally, the covariance structures of two such data sets provide partial information about any linear transformation connecting them. The remaining unknown degrees of freedom of the transformation must be deduced from other statistics, or from a knowledge of the underlying phenomenology. Among all the possible transformations consistent with measured pairs of hyperspectral covariance structures, a particularly simple and accurate one has been found. This "rotation free" flavor of "Covariance Equalization" (CE) has led to a simplified signal processing architecture that has been implemented in a real time VNIR hyperspectral target detection system. This paper describes that architecture, presents detection performance results, and introduces a new algorithm for long-interval change detection, Matched Change Detection.

A robust and computationally efficient motion detection algorithm based on sigma-delta background estimation

Abstract: This paper presents a new algorithm to detect moving objects within a scene acquired by a stationary camera. A simple recursive non linear operator, the Sigma-Delta filter, is used to estimate two orders of temporal statistics for every pixel of the image. The output data provide a scene characterization allowing a simple and efficient pixel-level change detection framework. For a more suitable detection, exploiting spatial correlation in these data is necessary. We use them as a multiple observation field in a Markov model, leading to a spatiotemporal regularization of the pixel-level solution. This method yields a good trade-off in terms of robustness and accuracy, with a minimal cost in memory and a low computational complexity.

LIDAR-based change detection of buildings in dense urban areas

Abstract: An automatic method for LIDAR-based (Light Detection And Ranging) change detection is proposed. Highly dense LIDAR point clouds are recommended as the most suitable gathered data for dense urban areas. The main goal is to develop an up-to-date building inventory database, which is in great demand for the earthquake-prone areas like Japan, using LIDAR as primary data. Two LIDAR surveying flights in 1999 and 2004 provide the test data over Roppongi, Tokyo, Japan. Detected results are visual evaluation using orthophoto produced by LIDAR surveying flights. The highly automated processing proved the efficiency of using LIDAR for a quick and reliable updating. Moreover, it also implies the feasibility for detection of damaged buildings due to earthquake.

Perceptual grouping in change detection.

Abstract: Detection of an item’s changing of its location from one instance to another is typically unaffected by changes in the shape or color of contextual items. However, we demonstrate here that such location change detection is severely impaired if the elongated axes of contextual items change orientation, even though individual locations remain constant and even though the orientation was irrelevant to the task. Changing the orientations of the elongated stimuli altered the perceptual organization of the display, which had an important influence on change detection. In detecting location changes, subjects were unable to ignore changes in orientation unless additional, invariant grouping cues were provided or unless the items changing orientation could be actively ignored using feature-based attention (color cues). Our results suggest that some relational grouping cues are represented in change detection even when they are task irrelevant.

Geographic Resources Decision Support System for land use, land cover dynamics analysis

Abstract: Change detection is the measure of the distinct data framework and thematic change information that can guide to more tangible insights into underlying process involving land cover and land use changes than the information obtained from continuous change. Digital change detection is the process that helps in determining the changes associated with landuse and land cover properties with reference to geo-registered multitemporal remote sensing data. It helps in identifying change between two (or more) dates that is uncharacterised of normal variation. Change detection is useful in many applications such as landuse changes, habitat fragmentation, rate of deforestation, coastal change, urban sprawl, and other cumulative changes through spatial and temporal analysis techniques such as GIS (Geographic Information System) and Remote Sensing along with digital image processing techniques. GIS is the systematic introduction of numerous different disciplinary spatial and statistical data, that can be used in inventorying the environment, observation of change and constituent processes and prediction based on current practices and management plans. Remote Sensing helps in acquiring multi spectral spatial and temporal data through space borne remote sensors. Image processing technique helps in analyzing the dynamic changes associated with the earth resources such as land and water using remote sensing data. Thus, spatial and temporal analysis technologies are very useful in generating scientifically based statistical spatial data for understanding the land ecosystem dynamics. Successful utilization of remotely sensed data for land cover and landuse change detection requires careful selection of appropriate data set. This paper discusses the land use/land cover analysis and change detection techniques using GRDSS (Geographic Resources Decision Support System) for Kolar district considering temporal multispectral data (1998 and 2002) of the IRS 1C / 1D (Indian Remote Sensing Satellites). GRDSS is a freeware GIS Graphic user interface (GUI) developed in Tcl/Tk is based on command line arguments of GRASS (Geographic Resources Analysis Support System). It has the capabilities to capture, store, process, display, organize, and prioritize spatial and temporal data. GRDSS serves as a decision support system for decision making and resource planning. It has functionality for raster analysis, vector analysis, site analysis, image

Context-driven automated target detection in 3D data

Abstract: This paper summarizes a system, and its component algorithms, for context-driven target vehicle detection in 3-D data that was developed under the Defense Advanced Research Projects Agency (DARPA) Exploitation of 3-D Data (E3D) Program. In order to determine the power of shape and geometry for the extraction of context objects and the detection of targets, our algorithm research and development concentrated on the geometric aspects of the problem and did not utilize intensity information. Processing begins with extraction of context information and initial target detection at reduced resolution, followed by a detailed, full-resolution analysis of candidate targets. Our reduced-resolution processing includes a probabilistic procedure for finding the ground that is effective even in rough terrain; a hierarchical, graph-based approach for the extraction of context objects and potential vehicle hide sites; and a target detection process that is driven by context-object and hide-site locations. Full-resolution processing includes statistical false alarm reduction and decoy mitigation. When results are available from previously collected data, we also perform object-level change detection, which affects the probabilities that objects are context objects or targets. Results are presented for both synthetic and collected LADAR data.

Detecting building changes from multitemporal aerial stereopairs

Abstract: Our goal is to detect changes in an aerial scene by comparing grey scale stereopairs taken several years apart in order to update a geographic database. A set of image locations that have a high likelihood to contain changes will be submitted to a human operator who will either reject the proposed change or validate it and update the database accordingly. We are mainly interested in changes in buildings. To isolate new construction and buildings, which disappear, we provide an algorithm that works in two steps. First, during a focusing phase, we eliminate a large part of the scene without losing any actual changes by comparing a Digital Elevation Model (DEM) for the two dates. Second, we classify the resulting regions of interest (ROI) based on four images—stereopairs of the area at the two dates. To decide whether or not the ROI contains a change, we classify each of the four images as “building” or “no-building”. This classifier is a combination of several decision trees induced from training data. Each node of each decision tree is identified with a graph of features which is more likely to occur on buildings than background. Finally, the classification results at the two different dates are compared. The final set of locations submitted to an operator omits less than 10% of the true changes. The false positive rate represents less than 5% of the scene surface.

Change detection for updating medium scale maps using laster altimetry

Abstract: To increase the update rates of topographical databases, research is performed to automatically detect changes using airborne laser scanning data. After the determination of the bare-Earth points, the remaining points have been classified as either points on buildings or points on vegetation. Additional usage was made of registered colour imagery taken during the laser scanning survey. The results show that buildings can be detected reliably using laser altimetry data sets. However, they also show that mapping rules (which buildings should be in the map and which can be neglected) need to be implemented accurately. Otherwise, the change detection procedure would signal a need for map updating for buildings that are not to be mapped.

Automatic processing of aerial images

Abstract: Change detection apparatus for detection of changes between first and second stereoscopic image pairs obtained at different times of a substantially similar view, comprises: a two-dimensional image filter (70) for comparing first and second image pairs to obtain an initial list of change candidates (72) from two-dimensional information in the image pairs, and a three-dimensional image filter (74) for comparing the image pairs at locations of the change candidates using three-dimensional image information. The apparatus retains those change candidates correlating with three-dimensional image change and rejects change candidates not correlating with three-dimensional image change, and produces a refined list of change candidates.(76)

Analysis of four change detection algorithms in bi-temporal space with a case study

Abstract: Although change detection algorithms for temporal remote sensing images have been compared using various datasets, there is no general agreement on their performance for separating change and no-change. This study compared image differencing, image ratioing, image regression, and principal component analysis (PCA) from a mathematical perspective. Error analysis showed that no-change pixels with errors are expected to be located within an error zone in bi-temporal space. Bi-temporal space consists of two temporal axes of target pixel values observed successively. All algorithms confine a no-change area to a zone delineating change and no-change pixels in the space. Image ratioing defines a fan-like sector as a no-change area, generally unsuitable for change detection. The other algorithms confine a no-change area to a strip-like zone. Image differencing defines a no-change zone with a fixed slope, leading to its inability to specify flexibly the error zone that varies with different conditions. In the exam...