Change point detection (CPD) is the method of detecting sudden changes in timeseries, and its importance is great concerning network traffic. With increased knowledge of occurring changes in data logs due to updates in networking equipment,a deeper understanding is allowed for interactions between the updates and theoperational resource usage. In a data log that reflects the amount of network traffic, there are large variations in the time series because of reasons such as connectioncount or external changes to the system. To circumvent these unwanted variationchanges and assort the deliberate variation changes is a challenge. In this thesis, we utilize data logs retrieved from a network equipment vendor to detect changes, then compare the detected changes to when firmware/signature updates were applied, configuration changes were made, etc. with the goal to achieve a deeper understanding of any interaction between firmware/signature/configuration changes and operational resource usage. Challenges in the data quality and data processing are addressed through data manipulation to counteract anomalies and unwanted variation, as well as experimentation with parameters to achieve the most ideal settings. Results are produced through experiments to test the accuracy of the various change pointdetection methods, and for investigation of various parameter settings. Through trial and error, a satisfactory configuration is achieved and used in large scale log detection experiments. The results from the experiments conclude that additional information about how changes in variation arises is required to derive the desired understanding.

The growth in global population inevitably increases the consumption of natural resources. The need to provide basic services to these growing communities leads to an increase in anthropogenic changes to the natural environment. The resulting transformation of vegetation cover (e.g. deforestation, agricultural expansion, urbanisation) has significant impacts on hydrology, biodiversity, ecosystems and climate. Human settlement expansion is the most common driver of land cover change in South Africa, and is currently mapped on an irregular, ad hoc basis using visual interpretation of aerial photographs or satellite images. This thesis proposes several methods of detecting newly formed human settlements using hyper-temporal, multi-spectral, medium spatial resolution MODIS land surface reflectance satellite imagery. The hyper-temporal images are used to extract time series, which are analysed in an automated fashion using machine learning methods. A post-classification change detection framework was developed to analyse the time series using several feature extraction methods and classifiers. Two novel hyper-temporal feature extraction methods are proposed to characterise the seasonal pattern in the time series. The first feature extraction method extracts Seasonal Fourier features that exploits the difference in temporal spectra inherent to land cover classes. The second feature extraction method extracts state-space vectors derived using an extended Kalman filter. The extended Kalman filter is optimised using a novel criterion which exploits the information inherent in the spatio-temporal domain. The post-classification change detection framework was evaluated on different classifiers; both supervised and unsupervised methods were explored. A change detection accuracy of above 85% with false alarm rate below 10% was attained. The best performing methods were then applied at a provincial scale in the Gauteng and Limpopo provinces to produce regional change maps, indicating settlement expansion. / Thesis (PhD(Eng))--University of Pretoria, 2012. / Electrical, Electronic and Computer Engineering / unrestricted

Native palms, such as the Sabal palmetto, play an important role in maintaining the ecological balance in Florida. As a side-effect of modern globalization, new phytopathogens like Texas Phoenix Palm Decline have been introduced into forest systems that threaten native palms. This presents new challenges for forestry managers and geographers. Advances in remote sensing has assisted the practice of forestry by providing spatial metrics regarding the type, quantity, location, and the state of heath for trees for many years. This study provides spatial details regarding the general palm decline in Florida by taking advantage of the new developments in deep learning constructs coupled with high resolution WorldView-2 multispectral/temporal satellite imagery and LiDAR point cloud data. A novel approach using TensorFlow deep learning classification, multiband spatial statistics and indices, data reduction, and step-wise refinement masking yielded a significant improvement over Random Forest classification in a comparison analysis. The results from the TensorFlow deep learning were then used to develop an Empirical Bayesian Kriging continuous raster as an informative map regarding palm decline zones using Normalized Difference Vegetation Index Change. The significance from this research showed a large portion of the study area exhibiting palm decline and provides a new methodology for deploying TensorFlow learning for multispectral satellite imagery.

The primary objective of this research was to evaluate the potential for monitoring forest change using Landsat ETM and Aster data. This was accomplished by performing eight change detection algorithms: pixel post-classification comparison (PCC), image differencing Normalized Difference Vegetation Index (NDVI), Soil-Adjusted Vegetation Index (SAVI), Transformed Difference Vegetation Index (TDVI), principal component analysis (PCA), multivariate alteration detection (MAD), change vector analysis (CVA) and tasseled cap analysis (TCA). Methods, Post-Classification Comparison and vegetation indices are straightforward techniques and easy to apply. In this study the simplified classification with only 4 forest classes namely close forest, open forest, bare land and grass land was used The overall classification accuracy obtained were 88.4%, 91.9% and 92.1% for the years 2000, 2003 and 2006 respectively. The Tasseled Cap green layer (GTC) composite of the three images was proposed to detect the change in vegetation of the study area. We found that the RBG-TCG worked better than RGBNDVI. For instance, the RBG-TCG detected some areas of changes that RGB-NDVI failed to detect them, moreover RBG-TCG displayed different changed areas with more strong colours. Change vector analysis (CVA) based on Tasseled Cap transformation (TCT) was also applied for detecting and characterizing land cover change. The results support the CVA approach to change detection. The calculated date to date change vectors contained useful information, both in their magnitude and their direction. A powerful tool for time series analysis is the principal components analysis (PCA). This method was tested for change detection in the study area by two ways: Multitemporal PCA and Selective PCA. Both methods found to offer the potential for monitoring forest change detection. A recently proposed approach, the multivariate alteration detection (MAD), in combination with a posterior maximum autocorrelation factor transformation (MAF) was used to demonstrate visualization of vegetation changes in the study area. The MAD transformation provides a way of combining different data types that found to be useful in change detection. Accuracy assessment is an important final step addressed in the study to evaluate the different change detection techniques. A quantitative accuracy assessment at level of change/no change pixels was performed to determine the threshold value with the highest accuracy. Among the various accuracy assessment methods presented the highest accuracy was obtained using the post-classification comparison based on supervised classification of each two time periods (2000 -2003 and 2003-2006), which were 90.6% and 87% consequently.

Magister Scientiae (Biodiversity and Conservation Biology) - MSc (Biodiv and Cons Biol) / Areas of high biodiversity and complex species assemblages are often difficult to manage and to set up meaningful monitoring and evaluations programmes. Mountain Fynbos is such an ecosystem and in the Cape of Good Hope (part of the Table Mountain National Park) plant biodiversity over the last five decades has been in decline. The reasons are difficult to speculate since large herbivores, altered fire regimes and even climate change could be contributors to this decline which has been quantified using fixed quadrats and standard cover-abundance estimates based on a Braun-Blanquet methodology. To provide more detailed data that has more resolution in terms of identifying ecological processes, Fixed-Point Repeat Photography has been presented as a management “solution”. However, photography remains a difficult method to standardize subjects and has certain operational limitations.

Healthy forests and soils are crucial for the very existence of mankind as they provide food, clean water and air, shade and protection against floods and storms. With their photosynthetic carbon storage ability, they mitigate climate change and fertilise and stabilise soils. Unfortunately, deforestation and the loss of fertile soils are the bleak reality and among the world’s most pressing challenges. Over the past decades Kenya has faced severe deforestation, but efforts are being undertaken to reverse deforestation, revegetate degraded land and combat erosion. Satellite remote sensing technology becomes increasingly useful for vegetation monitoring as the data quality improves and the costs decrease. This thesis explores the potential of free open access Sentinel-2 data for vegetation monitoring through Random Forest land cover classification and post-classification change detection on Rusinga Island, Kenya. Different single-date and multi-temporal predictor datasets differentiating respectively between five and four classes were examined to develop the most suitable model. The classification achieved acceptable results when assessed on an independent test dataset (overall accuracy of 90.06% with five classes and 96.89% with four classes), which should however be confirmed on the ground and could potentially be improved with better reference data. In this study, change detection could only be analysed over a time frame of two years, which is too short to produce meaningful results. Nevertheless, the method was proven conceptually and could be applied in the future to monitor land cover changes on Rusinga Island.

Today more and more people are moving to the cities around the world. This puts a lot of strain on the infrastructure as the cities grow in both width and height. To be able to monitor the ongoing change remote sensing is an effective tool and ways to make it even more effective, better and easier to use are constantly sought after. One way to monitor change detection is object based change detection. The idea has been around since the seventies, but it wasn’t until the early 2000 when it was introduced by Blaschke and Strobl(2001) to the market as a solution to the issues with pixel based analysis that it became popular with remote analysts around the world. KTH-SEG is developed at KTH Geoinformatics. It is developed to segment images in order to preform object based analysis; it can also be used for classification. In this thesis object based change detection over an area of Shanghai is carried out. Two different approaches are used; post-classification analysis as well as creating change detection images. The maps are assessed using the maximum likelihood report in the software Geomatica. The segmentation and classification is done using KTH-SEG, training areas and ground truth data polygons are drawn in ArcGIS and pre-processing and other operations is carried out using Geomatica. KTH-SEG offers a number of changeable settings that allows the segmentation to suit the image at hand.  It is easy to use and produces well defined classification maps that are usable for change detection The results are evaluated in order to estimate the efficiency of object based change detection in urban area and KTH-SEG is appraised as a segmentation and classification tool. The results show that the post-classification approach is superior to the change detection images. Whether the poor result of the change detection images is affected by other parameters than the object based approach can’t be determined. / Idag flyttar fler och fler människor in i städer runt om i världen. Det utgör en stor påverkan på den befintliga infra-strukturen då städerna växer på både höjden och bredden. För att kunna bevaka den förändring som sker så används ofta fjärranalys som ett effektivt verktyg. Sätt att utveckla befintliga tekniken försöker man hela tiden hitta nya, enklare och mer effektiva sätt att bevaka förändring finns alltid på horisonten. Objektbaserad förändrings analys är ett sätt att bevaka förändringar. Iden om att använda objekt baserad analys har funnits sedan 70-talet, men det var först i början av 2000-talet, då Blaschke och Strobl(2001) introducerade tekniken som en lösning på de problem man stöter på i pixelbaserad analys, som tekniken blev populär bland fjärranalytiker världen över. KTH-SEG är ett program utvecklat på KTH Geoinformatik avdelning. KTH-SEG är utvecklat för att segmentera bilder inför objektbaserad analys. Dessutom utför programmet klassificering. I det här arbetet utförs objektbaserad förändrings analys över ett område i Shanghai. För att hitta de förändringar som har skett har två tillvägsgångssätt använts: dels har analys av bilder efter klassificeringen gjorts och dels har bilder som i sig själva skall visa den förändring som har skett skapats, så kallade förändringsbilder. Bildernas pålitlighet är utvärderad genom att använda ”maximum likelihood report” i programmet Geomatica.   Segmentering och klassificering är gjort i programmet KTH-SEG, träningsområden och testområden är skapade i ArcGIS och förbehandling av bilder samt andra operationer är gjorda i Geomatica. KTH-SEG erbjuder många valmöjligheter för att påverka segmenteringsresultatet. Den är enkelt att använda och producerar tydliga klassificerade bilder som är användbara för analys. Resultatet utvärderas för att bestämma hur effektivt det är att använda objektbaserad förändrings analys av urbana områden och KTH-SEG utvärderas som ett segmenterings- och klassifikations verktyg. Resultaten visar att förändringsbilder ger ett sämre resultat än bilder som analyseras efter klassifikationen. Huruvida det dåliga resultatet på förändingsbilderna beror på andra omständigheter än tillvägagångssättet med objekt baserad klassifikation kan inte bestämmas. Mycket tyder dock på att det är valet av två bilder från olika satelliter som ger det dåliga resultatet.

Die Fernerkundung ist eine wichtige Quelle für aktuelle und qualitativ hochwertige Geodaten bzw. für die Aktualisierung von vorhandenen Geodaten. Die Entwicklung von neuen flugzeug- und satellitengestützten digitalen Sensoren in den letzten Jahren hat diese Bedeutung noch erhöht. Die Sensoren erschließen aufgrund ihrer verbesserten räumlichen und radiometrischen Auflösung und der vollständig digitalen Verarbeitungskette neue Anwendungsfelder. Klassische Auswerteverfahren stoßen bei der Analyse der Daten häufig an ihre Grenzen. Die in dieser Arbeit vorgestellte multiskalige objektklassen-spezifische Analyse stellt hier ein sehr gut geeignetes Verfahren dar, welches gute Ergebnisse liefert. Die Klassifizierung der Daten erfolgt mittels eines Fuzzy- Klassifizierungsverfahrens, welches Vorteile in der Genauigkeit und Interpretierbarkeit der Ergebnisse liefert. Die thematische Genauigkeit (Datenqualität) der Fuzzy-Klassifizierung ist von entscheidender Bedeutung für die Akzeptanz der Ergebnisse und ihre weitere Nutzung. Hier wurden Methoden zur räumlich differenzierten Ermittlung und Visualisierung der thematischen Genauigkeit entwickelt.Außerdem wurde die Methode der segmentbasierten Fuzzy-Logic Veränderungsanalyse (SFLV) entwickelt. Die Methode ermöglicht die Veränderungsanalyse von sehr bis ultra hoch aufgelösten Fernerkundungsdaten mit einer differenzierten Aussage zu den eingetretenen Veränderungen. Sie basiert auf den Standard Operationen für unscharfe Mengen und nutzt die Ergebnisse der entwickelten Methode zur Analyse hochauflösender Fernerkundungsdaten. Die SFLV liefert einen deutlichen Mehrwert zu dem klassischen Vergleich zweier Klassifizierungsergebnisse, indem sich differenzierte Aussagen über mögliche Veränderungen machen lassen. Die Anwendbarkeit der SFLV wurde erfolgreich an einem kleinen Untersuchungsgebiet auf der Elbinsel Pagensand beispielhaft für Veränderungsanalyse von Biotoptypen auf der Grundlage von HRSC-A Daten aufgezeigt.

Cette thèse présente la méthode de détection de changements MIMOSA (Method for generalIzed Means Ordered Series Analysis). Cette nouvelle méthode permet de détecter automatiquement des changements entre couples ou séries temporelles d’images SAR. En effet, grâce aux moyennes temporelles, le nombre d’images en jeu n’importe plus puisque seulement deux moyennes différentes sont comparées de sorte à détecter les changements (par exemple moyenne géométrique et moyenne quadratique). De ce fait, les grand volumes de données disponibles de nos jours sont exploitables plus facilement puisque l’information utile est «résumée» dans les moyennes. Le seul paramètre de la détection est le taux de fausses alarmes obtenu dans le résultat, ce qui rend son analyse plus intuitive. Les cartes de changements fournies par MIMOSA sont de très bonne qualité en comparaison à celles fournies par d’autres méthodes. De nombreux tests ont été mis en place pour constater la robustesse de la méthode MIMOSA face aux problèmes les plus souvent rencontrés, comme une mauvaise calibration radiométrique, ou encore un mauvais recalage. Une interface graphique a de plus été développée autour de MIMOSA, incorporant de nombreux outils de préparation et traitement des données, ainsi que des outils d’analyse des résultats. / This PhD thesis presents the MIMOSA (Method for generalIzed Means Ordered Series Analysis) change detection methood. This new technique can automatically detect changes between SAR image pairs or within time series. Indeed, thanks to the temporeal means, the number of involved images doesn’t matters because only two different means are compared to detect the changes (for example, the geometric and quadratic means). Thus, large data volumes can be processed easily, since the useful information is condensed within the temporal means. The only change detection parameter is the false alarm rate that will be MIMOSA method are very good compared to other methods. Several tests have been performed in order to quantify the robustness of the method facing the most common problems, like image misregistration or radiometric calibration errors. A graphical user interface has also been developed for MIMOSA, including many useful tools to prepare and process SAR data, but also several analyse tools.

Fine-scale resolution digital elevation models (DEMs) created from data collected using high precision instruments have become ubiquitous in fluvial geomorphology. They permit a diverse range of spatially explicit analyses including hydraulic modeling, habitat modeling and geomorphic change detection. Yet, the intercomparison of survey technologies across a diverse range of wadeable stream habitats has not yet been examined. Additionally, we lack an understanding regarding the precision of DEMs derived from ground-based surveys conducted by different, and inherently subjective, observers. This thesis addresses current knowledge gaps with the objectives i) to intercompare survey techniques for characterizing instream topography, and ii) to characterize observer variability in instream topographic surveys. To address objective i, we used total station (TS), real-time kinematic (rtk) GPS, terrestrial laser scanner (TLS), and infrared airborne laser scanning (ALS) topographic data from six sites of varying complexity in the Lemhi River Basin, Idaho. The accuracy of derived bare earth DEMs was evaluated relative to higher precision TS point data. Significant DEM discrepancies between pairwise techniques were calculated using propagated DEM errors thresholded at a 95% confidence interval. Mean discrepancies between TS and rtkGPS DEMs were relatively low (≤ 0.05 m), yet TS data collection time was up to 2.4 times longer than rtkGPS. ALS DEMs had lower accuracy than TS or rtkGPS DEMs, but ALS aerial coverage and floodplain topographic representation was superior to all other techniques. The TLS bare earth DEM accuracy and precision were lower than other techniques as a result of vegetation returns misinterpreted as ground returns. To address objective ii, we used a case study where seven field crews surveyed the same six sites to quantify the magnitude and effect of observer variability on DEMs interpolated from the survey data. We modeled two geomorphic change scenarios and calculated net erosion and deposition volumes at a 95% confidence interval. We observed several large magnitude elevation discrepancies across crews, however many of these i) tended to be highly localized, ii) were due to systematic errors, iii) did not significantly affect DEM-derived metric precision, and iv) can be corrected post-hoc.