Showing papers on "Change detection published in 1997"

Meaningful change detection in structured data

Abstract: Detecting changes by comparing data snapshots is an important requirement for difference queries, active databases, and version and configuration management. In this paper we focus on detecting meaningful changes in hierarchically structured data, such as nested-object data. This problem is much more challenging than the corresponding one for relational or flat-file data. In order to describe changes better, we base our work not just on the traditional “atomic” insert, delete, update operations, but also on operations that move an entire sub-tree of nodes, and that copy an entire sub-tree. These operations allows us to describe changes in a semantically more meaningful way. Since this change detection problem is NP-hard, in this paper we present a heuristic change detection algorithm that yields close to “minimal” descriptions of the changes, and that has fewer restrictions than previous algorithms. Our algorithm is based on transforming the change detection problem to a problem of computing a minimum-cost edge cover of a bipartite graph. We study the quality of the solution produced by our algorithm, as well as the running time, both analytically and experimentally.

Thresholding for Change Detection.

Abstract: Image differencing is used for many applications involving change detection. Although it is usually followed by a thresholding operation to isolate regions of change there are few methods available in the literature specific to (and appropriate for) change detection. We describe four different methods for selecting thresholds that work on very different principles. Either the noise or the signal is modeled, and the model covers either the spatial or intensity distribution characteristics. The methods are as follows: (1) a Normal model is used for the noise intensity distribution, (2) signal intensities are tested by making local intensity distribution comparisons in the two image frames (i.e., the difference map is not used), (3) the spatial properties of the noise are modeled by a Poisson distribution, and (4) the spatial properties of the signal are modeled as a stable number of regions (or stable Euler number).

Detection and analysis of change in remotely sensed imagery with application to wide area surveillance

Abstract: A new approach to wide area surveillance is described that is based on the detection and analysis of changes across two or more images over time. Methods for modeling and detecting general patterns of change associated with construction and other kinds of activities that can be observed in remotely sensed imagery are presented. They include a new nonlinear prediction technique for measuring changes between images and temporal segmentation and filtering techniques for analyzing patterns of change over time. These methods are applied to the problem of detecting facility construction using Landsat Thematic Mapper imagery. Full scene results show the methods to be capable of detecting specific patterns of change with very few false alarms. Under all conditions explored, as the number of images used increases, the number of false alarms decreases dramatically without affecting the detection performance. It is argued that the processing gain that results in using more than two images justifies the increased computational complexity and storage requirements of our approach over single image object detection and conventional change detection techniques.

Detection of vegetation changes associated with extensive flooding in a forested ecosystem.

Abstract: Monitoring broad-scale ecological responses to disturbance can be facilitated by automated change-detection approaches using remotely sensed data. This study evaluated the effectiveness of five unsupem'sed change-detection techniques using multispectral, multitemporal SPOT High Resolution Visible (HRV) data for identifying vegetation responses to extensive flooding of a forested ecosystem associated with Tropical Storm Alberto in July 1994. Standard statistical techniques, logistic multiple regression, and a probability vector model were used to quantitatively and visually assess classification accuracy. The change-detection techniques were (I) spectral-temporal change classification, (2) temporal change classification based on the Normalized Difference Vegetation Index (NDVI), (3) principal components analysis (PCA) of spectral data, (4) PCA of NDVI data, and (5) NDVI image differencing. Spectral-temporal change classification was the least effective of the techniques evaluated. Classification accuracy improved when temporal change classification was based on NDVI data. Both PCA methods were more sensitive to flood-affected vegetation than the temporal change classifications based on spectral and NDVI data. Vegetation changes were most accurately identified by image differencing of NDVI data. Logistic multiple regression and a probability vector model were especially useful for relating spectral responses to vegetation changes observed during field surveys and identifying areas of agreement and disagreement among the different classification methods. to utilize satellite data to assess vegetation responses to flooding in a forested ecosystem and to compare analytical approaches for vegetation change detection. Minimal wind and storm surge damage accompanied Alberto as it made landfall on the Florida panhandle near Fort Walton Beach on 3 July 1994 and traveled inland. However, due to weak steer

Some Problems with Application of Change-Point Detection Methods to Environmental Data

Abstract: This paper summarizes the author's experience in researching methods of discovering a change in the behaviour of meteorological and hydrological series. Basic statistical tests applying 'maximum' type statistics to detect a sudden or gradual change in location are given. The author stresses that the characteristic properties of the meteorological and hydrological data, especially the dependence between neighbouring observations, have to be considered by performing statistcal tests for change-point detection.

Detection of changes in remotely-sensed images by the selective use of multi-spectral information

Abstract: In this Letter, an unsupervised algorithm for detecting changes in multi-spectral and multi-temporal remotely-sensed images is presented. Such an algorithm makes it possible to reduce the effects of 'registration noise' on the accuracy of change detection. In addition, it can be used to reduce the typologies of detected changes in order to better locate the changes under investigation.

Universal scene change detection on MPEG-coded data domain

Abstract: In this paper, we propose scene decomposition algorithm from MPEG compressed video data. As a preprocessing for scene decomposition, partial reconstruction methods of DC image for P- and B-pictures as well as I-pictures directly from MPEG bitstream are used. As for detection algorithms, we have exploited several methods for detection of abrupt scene change, dissolve and wipe transitions using comparison of DC images between frames and coding information such as motion vectors. It is also proposed the method for exclusion of undesired detection such as flashlight in order to enhance scene change detection accuracy. It is shown that more than 95 percent of decomposition accuracy has been obtained in the experiment using more than one hour TV program. It is also found that in the proposed algorithm scene change detection can be performed more than 5 times faster than normal playback speed using 130MIPS workstation.© (1997) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Unsupervised robust change detection on multispectral imagery using spectral and spatial features

Abstract: Change detection is a central task for land cover monitoring by remote sensing. It uses multitemporal image data sets in order to detect land cover changes from spectral discrepancies. This paper describes a change detection strategy which integrates various concepts in order to make change detection robust against varying recording conditions, to utilize additional spatial features from local neighborhoods, and to enable unsupervised change detection. We consider change detection as an unsupervised classification problem with the two classes ' Change' and ' NoChange' . The decision can be made using Bayes Rule ,w hich minimizes the probability of error. We have successfully applied the described change detection strategy both to simulated imagery and real remotely sensed multispectral image data. The result of our unsupervised iterative algorithm are binary images showing the locations of ' Change' -areas, and probability images giving the Bayesian probability of ' Change' versus ' NoChange' for each pixel.

Two strategies in the problem of change detection and isolation

Abstract: The comparison between optimal sequential and nonsequential (fixed-size sample) strategies in the problem of abrupt change detection and isolation is discussed. In particular, we show that sometimes a simple fixed-size sample algorithm is almost as efficient as an optimal sequential algorithm which leads to a burdensome number of arithmetical operations.

An Iterative Spectral-Spatial Bayesian Labeling Approach for Unsupervised Robust Change Detection on Remotely Sensed Multispectral Imagery

Abstract: In multispectral remote sensing, change detection is a central task for all kinds of monitoring purposes. We suggest a novel approach where the problem is formulated as a Bayesian labeling problem. Considering two registered images of the same scene but different recording time, a Bayesian probability for ‘Change’ and ‘NoChange’ is determined for each pixel from spectral as well as spatial features. All necessary parameters are estimated from the image data itself during an iterative clustering process which updates the current probabilities.

Metrics for scene change detection in digital video sequences

Abstract: Five metrics for scene change detection in video sequences are presented. Metrics previously applied to this problem are surveyed, and are quantitatively compared to the new metrics. Results show that the proposed metrics are superior.

Scene change detection

Abstract: A scene change detector sums the correlation maximum values of correlation surfaces produced by a motion vector determining circuit (2) across a current image and compares this with a threshold value (Thres) to detect scene changes. A statistical analysis of signals (V x , V y , Y) representing the current image may be made and a resulting value differentiated. Peaks in this differentiated value represent scene changes. Finally, rapid changes in the number of valid vectors found in a motion analysis of a current image may also be used to indicate a scene change.

Land applications using ERS-1/2 Tandem data

Abstract: The potential of ERS-1/2 data for landuse classification and change detection and monitoring is discussed. For repeat-pass interferometer systems, such as the ERS satellites, low interferometric correlation indicates random dislocation of the individual scatterers between the two acquisitions of an interferometric image pair. This additional information significantly improves the potential of SAR data for landuse classification, change detection, and the retrieval of geophysical and biophysical parameters. Results obtained with ERS-1/2 Tandem data will be presented and compared to results of the ERS-1 Commissioning and Ice Phases. Finally, a short overview on GAMMA Remote Sensing's products and user services will be given.

Land cover change: a method for assessing the reliability of land cover changes measured from remotely-sensed data

Abstract: A method for assessing the reliability of land cover changes measured using data from different dates is presented and tested using a study area in the Cairngorm mountains, Scotland. Two sources of uncertainty are recognised in the change detection process: a) slivers resulting from misalignment of boundaries of land cover polygons and b) false positive changes associated with misclassification error in production of the land cover maps.

Decoding real-number convolutional codes: change detection, Kalman estimation

Abstract: Convolutional codes which employ real-number symbols are difficult to decode because of the size of the alphabet and the numerical and roundoff noise inherent in arithmetic operations. Such codes find applications in both channel coding for communication systems and in fault-tolerance support for signal processing subsystems. A new method for error correction based on optimum mean-square recursive Kalman estimation techniques incorporates time-varying models for the system and associated disruptive noise sources. The underlying common model for communications and fault tolerance applications assumes the system operates nominally with low levels of channel or numerical and roundoff noise, occasionally experiencing temporarily larger noise statistics. A time-varying Kalman estimation structure which uses single-step and fixed-lag smoothing predictors can correct errors to within the nominal low-noise levels. Correction actions may be activated only when larger activity is detected, so methods for detecting possible error situations are developed. However, misdetection is not a serious problem because the Kalman correction methods only track significant errors in the data. Two activity detection techniques are examined; one is based on likelihood ratio tests while another uses clipped samples and binary pattern matching. Several examples showing simulated mean-square error performance and decoded waveforms from error injection experiments are presented.

A new approach for satellite image analysis by means of a semantic network

Abstract: This paper investigates synergy effects between satellite images and a digital topographic database. The use of such topographic databases, which are actually built up in many countries (e.g. ATKISDLM200 data in Germany), can support the satellite image analysis. This digital database offers a geometric as well as a semantic prediction for every object in the satellite image. Therefore, an automated, knowledge based feature extraction can be performed. Because of the relatively poor geometric resolution of common satellite sensors the project will concentrate on main areabased landuse classes like ’settlement’, ’forest’, ’water’ or ’agriculture’. The result of this feature extraction is a symbolic description of the image content. Both, the symbolic description and the digital database, are transfered in a semantic network, a compact formalism for structuring the entire knowledge. Beside this, the semantic network is used for verification and classification of the above mentioned objects. Therefore, suitable valuation and analysis functions have to be created. In the last step, a change detection between satellite image and database information will lead to an update process of the topographic database.

Robust thermophysics-based interpretation of radiometrically uncalibrated IR images for ATR and site change detection

Abstract: We previously formulated a new approach for computing invariant features from infrared (IR) images. That approach is unique in the field since it considers not just surface reflection and surface geometry in the specification of invariant features, but it also takes into account internal object composition and thermal state that affect images sensed in the nonvisible spectrum. In this paper, we extend the thermophysical algebraic invariance (TAI) formulation for the interpretation of uncalibrated infrared imagery and further reduce the information that is required to be known about the environment. Features are defined such that they are functions of only the thermophysical properties of the imaged objects. In addition, we show that the distribution of the TAI features can be accurately modeled by symmetric alpha-stable models. This approach is shown to yield robust classifier performance. Results on ground truth data and real infrared imagery are presented. The application of this scheme for site change detection is discussed.

Development of a new automated land cover change detection system from remotely sensed imagery based on artificial neural networks

Abstract: The research is designed to develop and implement the algorithms for an automated spatial change information extraction system from remotely sensed imagery based on artificial neural networks. First, the authors investigate the suitability of the application of neural networks in automated change detection using TM imagery and its related network design problems unique to change detection. They then develop a neural networks-based change detection system using backpropagation training algorithm. This trained network is then able to efficiently detect land cover changes and provide complete information about the nature of change. Based on their experiments, it has been proven that this technique is successful and has immense implications on land cover change detection and quantification at all levels of applications ranging from local to global in scale.

Detecting changes in a dynamic environment for updating its maps by using a mobile robot

Abstract: For mobile robots working in a dynamic environment, there is a great need for a global environment map that is updated frequently. In the paper, we propose a new method by which a mobile robot with an original environment map automatically detects changes in the environment and modifies the map into a new version. The changes are identified by performing robot localization and change detection alternatively at some planned observation positions. To deal with robot position errors caused by dead reckoning, available information on the original map and a local map recording already detected changes is utilized as much as possible. Simulation results show this method is efficient even for detecting large changes in a complex environment.

A chromatic contour detector based on abrupt change techniques

Abstract: A method for segmenting colored images based on contour detection is described. It involves the use of techniques based on abrupt change detection used in signal processing and control systems. This work is based on a theoretical framework: differential geometry, tensors, Neyman-Pearson's optimal decision. Good results are obtained with Gaussian and exponential noises. This method also provides a very good location of contours.

Quantification of the impact of misregistration on the accuracy of remotely sensed change detection

Abstract: The impact of misregistration on the accuracy of change detection is quantitatively investigated using TM imagery. This simulation study focuses on two interconnected issues. First, the statistical properties of the difference images are evaluated using semivariograms when images are progressively misregistered in order to investigate the band sensitivity, temporal sensitivity, and spatial frequency sensitivity of change detection to misregistration. The ellipsoidal change detection technique is then proposed and used to progressively detect the land cover transitions at each misregistration stage for each image. The impact of misregistration on change detection is then evaluated in terms of the accuracy of change detection using the output from the ellipsoidal change detector.

An introduction to using generalized linear models to enhance satellite-based change detection

Abstract: A popular satellite-based land cover change detection technique is to use the spectral information to set up a binary "change/no-change" mask. For each pixel, if there is a big enough difference between the reflectance values for two images acquired at different times, the area represented by that pixel is considered to have changed. The different change detection methods are different in how they determine a "big enough difference". The analyst is left to choose which function of the reflectance values to use and where to set the "change" threshold. This choice is often subjective and effects the accuracy of the change detection. The authors explore the use of generalized linear models (GLM) as a way to enhance satellite based change detection by helping determine the most appropriate function of the reflectance values to use then apply the modeling to select the threshold. The main idea is that reflectance values from satellite imagery can be incorporated into a GLM to predict the probability of change from one land cover to another and that this method of change detection will provide more information than current change detection methods. A major benefit of using generalized linear models is to determining the significance and most useful combinations of the spectral data for predicting changed areas.

Scene change detection method and scene change detector

Abstract: PROBLEM TO BE SOLVED: To highly accurately detect a scene change by detecting a change between the corresponding respective blocks of a first frame image and a second frame image and judging the change to the corresponding block of a third frame image. SOLUTION: An image fetching means 103 fetches the frame images of every (n) frames, a block output means 104 divides the frame images into the plural blocks and outputs the image data of the blocks and a similarity calculation means 105 calculates similarity between the blocks at the same position of the two frame images. A judgement means 106 processes the similarity outputted from the similarity calculation means 105 and the image data of the blocks outputted from the block output means 104, detects the change to the third frame image and judges whether or not the first frame image and the second frame image is the scene change. When a prescribed evaluated value becomes less than a threshold value, the judgment means 106 outputs signals for expressing the generation of the scene change. COPYRIGHT: (C)1998,JPO

Monitoring of forest changes using unsupervised methods: A case study from boreal forest on mineral soils

Abstract: An unsupervised clustering method was presented for monitoring rapid forest changes such as cuttings, in large areas. The work was based on the hypothesis that most of the important changes in the forest canopy can be detected using space‐born remote sensing information. Multitemporal Landsat TM data covering boreal forest were utilized. The results showed that clustering of changes was not very accurate without prior radiometric calibration. In this study a relative regression calibration was combined with Studentization of the spectral difference features. The change detection accuracy at pixel level was not acceptable, therefore forest stands were used as classification units. It is proposed that if forest stands are not available, spectral segments can be used as observation units for classification. The stand‐level change detection accuracy using the Kernel density linkage clustering method varied from 87.6% with a three‐year interval to 93.1% with a one‐year interval.

Signal subspace fusion of uncalibrated sensors with application in SAR, diagnostic medicine and video processing

Abstract: This paper addresses the problem of fusing the information content of two uncalibrated sensors. This problem arises in registering images of a scene when it is viewed via two different sensory systems, or detecting change in a scene when it is viewed at two different time points by a sensory system, or via two different sensory systems or observation channels. We are concerned with sensory systems which have not only a relative shift, scaling and rotational calibration error, but also an unknown point spread function (that is time-varying for a single sensor, or different for two sensors). By modeling one image in terms of an unknown linear combination of the other image, its powers and their spatially-transformed (shift, rotation and scaling) versions, a signal subspace processing is developed for fusing uncalibrated sensors. The proposed method is shown to be applicable in moving target detection (MTD) using monopulse synthetic aperture radar (SAR) with uncalibrated radars. Results are shown for video, magnetic resonance images of a human brain, moving target detector monopulse SAR, and registration of SAR images of a target obtained via two different radars or at different coordinates by the same radar for automatic target recognition (ATR).