|
|
Mapping of urban sprawl using remote sensing data
Vostracká, Barbora ; Potůčková, Markéta (advisor) ; Kupková, Lucie (referee)
Mapping of urban sprawl using remote sensing data Abstract Mapping of urban sprawl has been an often discussed topic recently. This work compares remote sensing methods and socio-geographic methods used for tracing urban area changes over a certain period of time, and for mapping of these changes. First the potential of socio-geographic methods for tracing urban area changes is examined, and advantages and disadvantages of these methods are evaluated. Then, in a similar way, remote sensing data and methods which can be used in this field are studied. Based on the example of Praha-západ district is illustrated how CORINE database data can be used for mapping of urban sprawl on the national and regional levels. On the example of Zličín and Hostivice cadastral areas it is shown how to classify high-resolution satellite images and how to interpret aerial images in order to create maps of urban area changes on a local scale. The outcomes of both methods were compared using RSO register data. This work aims to evaluate how suitable remote sensing data and methods are for monitoring and mapping of urban area changes, especially in areas of suburbanization. Keywords: remote sensing, urban areas changes, suburbanization, urban sprawl
|
|
|
Analysis of forest canopy density based on textural features of hight resolution imagery and airborne laser scanning data
Bromová, Petra ; Potůčková, Markéta (advisor) ; Hájek, Filip (referee)
Analysis of forest canopy density based on textural features of high resolution imagery and airborne laser scanning data Abstract The objective of this thesis is to assess the forest canopy density in the Šumava Mountains, Czech Republic. The spruce forests in this area have been suffering from the bark beetle outbreak for almost 20 years resulting in a mixture of dead and young trees, mature forest stands and peat bogs. The canopy density was evaluated using a very high spatial resolution panchromatic imagery and low point density LiDAR, combined with an object oriented approach. The classification based on three GLCM texture measures (contrast, entropy and correlation), which were derived from the image objects, resulted in a kappa index of accuracy of 0.45. Adding the information from the LiDAR data, the accuracy of the classification improved up to 0.95.
|
|
|
Detection of Equilibrium Line Altitude (ELA) Changes from Remote Sensing Data; Case Study from the Cordillera Blanca, Peru
Paraj, Zsolt ; Potůčková, Markéta (advisor) ; Kropáček, Jan (referee)
The aim of this diploma thesis is to monitor glacier change in the Cordillera Blanca in the period from 1987 to 2014. This diploma thesis focuses on three mountains and eleven glaciers in the northern part of the Cordillera Blanca. The input data consist of 29 Landsat scenes (Landsat 4,5,7 and 8) and the ASTER global digital elevation model version 2. Semi-automatic classification algorithm is created based on threshold values detected by spectral analyses of selected land cover types in the Cordillera Blanca. Additionally, the mean snowline (equilibrium line) altitude change is computed for all of the three mountains and eleven glaciers. Besides, glacier change depending on slope and aspect is evaluated. The results of this diploma thesis are presented in maps, tables and charts. The results of the classification are compared with the GLIMS Glacier Database and the field measurements provided by Adam Emmer, MSc. Finally, the advantages and disadvantages of the new Landsat 8 satellite sensor are discussed. Key words: Remote sensing, Landsat, classification, ice and snow detection, ELA, Cordillera Blanca
|
|
|
THE USE OF IMAGE MATCHING METHODS IN GEOMORPHOLOGICAL ANALYSIS
Šiková, Zuzana ; Potůčková, Markéta (advisor) ; Hodač, Jindřich (referee)
The use of optical scanning methods in geomorpho-analysis Abstract Main goal of this thesis is to find out if it is possible to use Structure from motion (SfM) method for analyzing geomorphological objects. Four geomorphological features in three different places within Pilsen-North region was used for testing this method. These objects with very dissimilar dimensions and shapes was scanned for this testing in various light conditions. All used data-sets was entirely created by author of this thesis. The data was initially processed by Agisoft Photoscan Professional Ediditon v1.1.6 and VisualSFM v0.5.26 to create spatial models. These models was afterwards processed in CloudCompare v2.6.1 and MeshLab v1.3.3. This software was used for clipping and merging of 3D models and for converting 3D models in to real dimensions. These real sized spatial models was then contrasted together by creating comparing entities. Outcomes are evaluated in the thesis conclusion. Keywords: Structure from motion (SfM), SIFT, RANSAC
|
|
|
Classification of line features from remote sensing data
Kolankiewiczová, Soňa ; Potůčková, Markéta (advisor) ; Kupková, Lucie (referee)
This work deals with object-based classification of high resolution data. The aim of the thesis (paper, work) is to develope an acceptable classification process of linear features (roads and railways) from high-resolution satellite images. The first part shows different approaches of the linear feature classification and compares theoretic differences between an object-oriented and a pixel-based classification. Linear feature classification was created in the second part. The high-resolution QuickBird satellite images showing Prague surroudings were used for this classification. Using Definiens Developer software and the paper of Nobrega et al. (2006) the segmentation and object-based classification was created on the selected area of the satellite image. Minimum distance method of a pixel-based classification of the same part of image was generated to compare these two methods of classifications. Another classification was created in an another satellite image to verify developed classification process. At the end a visual and statistical accuracy assessment was done to compare an object-oriented and a pixel-based classification . Powered by TCPDF (www.tcpdf.org)
|
|
|
Using Sentinel-1 data for creating a digital terrain model by means of radar interferometry
Karvánek, Matouš ; Potůčková, Markéta (advisor) ; Hlaváčová, Ivana (referee)
Using of Sentinel-1 data for radar interferometry Abstract The diploma thesis deals with extraction of a digital surface model (DSM) using synthetic aperture radar interferometry (InSAR) and Sentinel-1 data in selected locations of the Czech Republic. The InSAR technique, the Sentinel-1 data, their parameters and possibilities of their usage are described in the theoretical part of the thesis. The specification of the model areas and used data follows. The practical part is focused on creating a methodology of deriving a digital surface model and its extracting in the three tested locations. These locations differ from each other in their geomorphological features and land cover. At the end of this part the comparison of the extracted model with the reference model DMP 1G using statistical methods is carried out. At the end of this thesis the results are evaluated and discussed. Key words: InSAR, Sentinel-1, SAR, DSM
|
|
|
Classification of meadow vegetation in the Krkonoše Mts. using aerial hyperspectral data and support vector machines classifier
Hromádková, Lucie ; Kupková, Lucie (advisor) ; Potůčková, Markéta (referee)
Meadow vegetation in the Krkonoše Mountains National Park is classified in this master thesis using aerial hyperspectral data from sensor AISA and Support Vector Machines (SVM) and Neural Networks (NN) classification algorithms. The main goals of the master thesis are to determine the best settings of SVM parameters and to propose an ideal design for a training dataset for this classification algorithm and mapping of the meadows in the Krkonoše mountains. The criterion of the tests will be the result of classification accuracy (confusion matrices and kappa coefficient). The additional goal of the master thesis is to compare performances of both utilized classifiers, especially regarding the amount of training pixels necessary for successful classification of the mountainous meadow vegetation. Classification maps of the area of interest and Python scripts are the main outputs of the master thesis. These outputs will be handed over to the Administration of the Krkonoše Mountains National Park for further utilization in the monitoring and protecting these valuable meadow vegetation communities. Key words: hyperspectral data, AISA, Support Vector Machines, Neural Networks, training dataset, mountainous meadow vegetation
|
|
| |
|
|
Utilization of additional information on the pulse for ALS data classification in rugged terrain
Poláková, Tereza ; Lysák, Jakub (advisor) ; Potůčková, Markéta (referee)
Utilization of additional information of the pulse for ALS data classification in ragged terrain Abstract The diploma thesis deals with airborne laser scanning filtering problem in sandstone landscape which is characterized by ragged terrain and in our country also by dense vegetation that makes difficult to transit laser pulse to terrain that can lead to lower accuracy of created DTM. In the first part the basic filtering algorithm that are systematic divided into several groups are described. The emphasis is also put on theoretic problems which we have to deal with during the filtering of laser scanner data acquired in sandstone landscape. The main goal of the thesis is to suggest changes in one of the existing algorithm to additional information of the pulse (mainly amplitude and width of the pulse) be used, and to test this method over the real data. At the end the results of the method and its implementation are critically evaluated. Keywords: airborne laser scanning, point cloud segmentation, point cloud classification, sandstone landscape, DTM
|
|
|
Classification of road network from airborne laser scanning data and from remote sensing images with high resolution
Kuchařová, Jana ; Potůčková, Markéta (advisor) ; Kupková, Lucie (referee)
Classification of road network from airborne laser scanning data and from remote sensing images with high resolution Abstract Object classification of land cover is currently one of the methods of remote Earth exploration. Road network classification only is unique because it is covered with anthropogenic material and has different characteristics than other elements of the landscape. This work deals with the possibility of using a combination of data from airborne laser scanning and high resolution optical data for detection of the road network in the specific area. The premise is that the use of two different types of data could provide better results, because airborne laser scanning data provide very precise information about the position and height of the point, while satellite data of very high resolution represent the real landscape. Searching for suitable features and classification rules for unambiguous determination of the road network is one of the objectives of the work. Segmentation parameters will also be important for object classification. Another objective is to verify the transferability of classification schemes into the other scene. The results should present a response on whether a procedure can be applied over a different location and also that the use of two types of data can bring...
|
guest ::
RSS feed.