Road network extraction from high-resolution multi spectral satellite images

Download
2012
Karaman, Ersin
In this thesis, an automatic road extraction algorithm for multi-spectral images is developed. The developed model extracts elongated structures from images by using edge detection, segmentation and clustering techniques. The study also extracts non-road regions like vegetative fields, bare soils and water bodies to obtain more accurate road map. The model is constructed in a modular approach that aims to extract roads with different characteristics. Each module output is combined to create a road score map. The developed algorithm is tested on 8-band WorldView-2 satellite images. It is observed that, the proposed road extraction algorithm yields 47 % precision and 70 % recall. The approach is also tested on the lower spectral resolution images with four-band, RGB and gray level. It is observed that the additional four bands provide an improvement of 12 % for precision and 3 % for recall. Road type analysis is also in the scope of this study. Roads are classified into asphalt, concrete and unpaved using Gaussian Mixture Models. Other linear objects such as railroads and water canals may also be extracted by this process. An algorithm that classifies drive roads and railroads for very high resolution images is also investigated. It is based on the Fourier descriptors that identify the presence of railroad sleepers. Water canals are also extracted in multi-spectral images by using spectral ratios that employ the near infrared bands. Structural properties are used to distinguish water canals from other water bodies in the image.

Suggestions

Development of free and open source software for flow mapping integrated to geographic information systems
Güllüoğlu, Naim Cem; Işık, Oğuz; Karahanoğlu, Nurkan; Department of Geodetic and Geographical Information Technologies (2014)
Mapping of spatial interaction data is an ongoing challenge for cartographers. In many Geographic Information Systems (GIS) software there is no off-the-shelf functionality for processing and visualizing spatial interactions or geographical flows. Considering the development efforts that have been made in the last few decades to discover the potential of GIS almost in every aspect, handling and visualization of spatial interaction data under GIS remain underutilized. The main objective of this study is to d...
Alignment of uncalibrated images for multi-view classification
Arık, Sercan Ömer; Vural, Elif; Frossard, Pascal (2011-12-29)
Efficient solutions for the classification of multi-view images can be built on graph-based algorithms when little information is known about the scene or cameras. Such methods typically require a pairwise similarity measure between images, where a common choice is the Euclidean distance. However, the accuracy of the Euclidean distance as a similarity measure is restricted to cases where images are captured from nearby viewpoints. In settings with large transformations and viewpoint changes, alignment of im...
Superpixel based image sequence representation and motion estimation
İnce, Kutalmış Gökalp; Alatan, Abdullah Aydın; Demirekler, Mübeccel; Department of Electrical and Electronics Engineering (2017)
In this study a superpixel based representation of image sequences is proposed. For superpixel extraction, a novel gradient ascent approach, in which spatial and spectral statistics are utilized to obtain an optimal Bayesian classifier for pixel to superpixel label assignment, is proposed. Utilization of the spectral and spatial statistics reduce the dependency on user selected global parameters, while increasing the robustness and adaptability. Proposed Local Adaptive Superpixels (LASP) approach exploits he...
PROGRESSIVE COMPRESSION OF DIGITAL ELEVATION DATA USING MESHES
Kose, Kivanc; Yılmaz, Erdal; ÇETİN, AHMET ENİS (2009-07-17)
In this paper a new Digital Elevation Map (DEM) image compression algorithm is proposed. DEM image can be threated as a grayscale image, whose pixel values are the elevation values of the map points. The grayscale DEM image is compressed using an adaptive wavelet based image compression algorithm. The method, which is an extension of the progressive mesh compression takes advantage of the multiresolution property of the wavelets while coding the map images. This makes it possible to decode different resolut...
An integrated approach to computational vision - The edge strength function and the nested symmetries
Tarı, Zehra Sibel (1999-01-01)
A new development in local symmetry extraction and its connections to segmentation functionals and the fronts propagating with curvature-dependent speed are examined. The basic tool is a new distance function that attains its maximum value at the shape boundary and decays rapidly away from there. It is shown that the Hessian of the distance function captures perceptual information that can be extracted easily, efficiently, and robustly in the form of nested local shape symmetries at multiple scales. The mos...
Citation Formats
E. Karaman, “Road network extraction from high-resolution multi spectral satellite images,” Ph.D. - Doctoral Program, Middle East Technical University, 2012.