Automatic main road extraction from high resolution satellite imageries by means of particle swarm optimization applied to a fuzzy-based mean calculation approach

Manual extraction of road network by human operator is an expensive and time-consuming procedure. Alternatively, automation of the extraction process would be a great advancement. For this purpose, an automatic method is proposed to extract roads from high resolution satellite images. In this study, using few samples from road surface, a particle swarm optimization is applied to a fuzzy-based mean calculation system to obtain road mean values in each band of high resolution satellite colour images. Then, the images are segmented using the calculated mean values from the fuzzy system. Optimizing the fuzzy cost function by particle swarm optimization enables the fuzzy approach to be the best mean value of road with sub-grey level precision. Initially, this method was applied to simulated images where the calculated mean values are consistent with the hypothetic mean values. Application of the method to IKONOS satellite images has shown a prospective outcome for automatic road extraction. Mathematical morphology is subsequently used to extract an initial main road centreline from the segmented image. Then, small redundant segments are automatically removed. The quality of the extracted road centreline indicates the effectiveness of the proposed approach.     

Mathematical Modelling and Accuracy Testing of Spot Level 1B Stereopairs

During a project concerned with DEM generation using SPOT stereoscopic imagery, difficulties were experienced when using Level 1B stereopairs for the task. This paper presents a mathematical solution to overcome this problem which has been implemented at the University of Glasgow. Results are included from experimental tests which were carried out over a test field in Jordan using this solution. These tests used five SPOT Level 1B stereopairs together with a single SPOT Level 1A stereopair for comparative purposes. The residual errors at the ground control points and independent check points are given and show that a satisfactory solution was achieved.     

Automatic urban building boundary extraction from high resolution aerial images using an innovative model of active contours

To present a new method for building boundary detection and extraction based on the active contour model, is the main objective of this research. Classical models of this type are associated with several shortcomings; they require extensive initialization, they are sensitive to noise, and adjustment issues often become problematic with complex images. In this research a new model of active contours has been proposed that is optimized for the automatic building extraction. This new active contour model, in comparison to the classical ones, can detect and extract the building boundaries more accurately, and is capable of avoiding detection of the boundaries of features in the neighborhood of buildings such as streets and trees. Finally, the detected building boundaries are generalized to obtain a regular shape for building boundaries. Tests with our proposed model demonstrate excellent accuracy in terms of building boundary extraction. However, due to the radiometric similarity between building roofs and the image background, our system fails to recognize a few buildings.     

Rational function optimization using genetic algorithms

In the absence of either satellite ephemeris information or camera model, rational functions are introduced by many investigators as mathematical model for image to ground coordinate system transformation. The dependency of this method on many ground control points (GCPs), numerical complexity, particularly terms selection, can be regarded as the most known disadvantages of rational functions. This paper presents a mathematical solution to overcome these problems. Genetic algorithms are used as an intelligent method for optimum rational function terms selection. The results from an experimental test carried out over a test field in Iran are presented as utilizing an IKONOS Geo image. Different numbers of GCPs are fed through a variety of genetic algorithms (GAs) with different control parameter settings. Some initial constraints are introduced to make the process stable and fast. The residual errors at independent check points proved that sub-pixel accuracies can be achieved even when only seven and five GCPs are used. GAs could select rational function terms in such a way that numerical problems are avoided without the need to normalize image and ground coordinates.     

Optimal fusion of optical and SAR high-resolution images for semiautomatic building detection

Building detection from different high-resolution aerial and satellite images has been a notable research topic in recent decades. The primary challenges are occlusions, shadows, different roof types, and similar spectral behavior of urban covers. Integration of different data sources is a solution to supplement the input feature space and improve the existing algorithms. Regarding the different nature and unique characteristics of optical and radar images, there are motivations for their fusion. This paper is aimed to identify an optimal fusion of radar and optical images to overcome their individual shortcomings and weaknesses. For this reason, panchromatic, multispectral, and radar images were first classified individually, and their strengths and weaknesses were evaluated. Different feature-level fusions of these data sets were then assessed followed by a decision-level fusion of their results. In both the feature and decision levels of integration, artificial neural networks were applied as the classifiers. Several post-processing methods using normalized different vegetation index, majority filter, and area filter were finally applied to the results. Overall accuracy of 92.8% and building detection accuracy of 89.1% confirmed the ability of the proposed fusion strategy of optical and radar images for building detection purposes.     

Radar interferometry time series analysis of Mashhad subsidence

A large agricultural area located in 20 km north of the city of Mashhad in the north-east of Iran is subject to land subsidence. The subsidence rate was achieved in a couple of sparse points by precise leveling between 1995 and 2005, and continuous GPS measurements obtained from 2005 to 2006. In order to study the temporal behavior of the deformation in high spatial resolution, the small baseline subset (SBAS) algorithm was used to generate the interferometric SAR time series analysis. Time series analysis was performed using 19 interferograms calculated from 12 ENVISAT ASAR data spanning between 2003 and 2006. The time series results exhibited that the area is subsiding continuously without a significant seasonal effect. Mean LOS deformation velocity map obtained from time series analysis demonstrated a considerable subsidence rate up to 24 (cm/yr). In order to evaluate the time series analysis results, continuous GPS measurements as a geodetic approach were applied. The comparisons showed a great agreement between interferometry results and geodetic technique. Moreover, the information of various piezometric wells distributed in the area corresponding to 1995 to 2005 showed a significant decline in water table up to 20 meters. The correlation between the piezometric information and the surface deformation at well’s locations showed that the subsidence occurrence in Mashhad is due to the excess groundwater withdrawal.     

Precision rectification of high resolution satellite imagery without ephemeris data

The huge capability of high resolution satellite imageries (HRSI), that includes spatial, spectral, temporal and radiometric resolutions as well as stereoscopic vision introduces them as a powerful new source for the Photogrammetry, Remote Sensing and GIS communities. High resolution data increases the need for higher accuracy of data modeling. The satellite orbit, position, attitude angles and interior orientation parameters have to be adjusted in the geometrical model to achieve optimal accuracy with the use of a minimum number of Ground Control Points (GCPs). But most high resolution satellite vendors do not intend to publish their sensor models and ephemeris data. There is consequently a need for a range of alternative, practical approaches for extracting accurate 2D and 3D terrain information from HRSI. The flexibility and good accuracy of the alternative models demonstrated with KFA-1000 and the well-known SPOT level 1A images. A block of eight KFA-1000 space photos in two strips with 60% longitudinal overlap and 15% lateral sidelap and SPOT image with rational function, DLT, 2D projective, polynomials, affine, conformal, multiquadric and finite element methods were used in the test. The test areas cover parts of South and West of Iran. Considering the quality of GCPs, the best result was found with the DLT method with a RMSE of 8.44 m for the KFA-1000 space photos.     

Comparison of Pixel and Object Oriented Based Classification of Hyperspectral Pansharpened Images

In this paper pixel-based and object-oriented classifications were investigated for land-cover mapping in an urban area. Since the image fusion methods are playing a useful role in supplying classification different fusion approaches such as Gram-Schmidt Transform (GS), Principal Component Transform (PC), Haar wavelet, and À Trous Wavelet Transform (ATWT) algorithms have been used and the fused image with the best quality has been assessed on its respected classification. A Hyperion image and IRS-PAN image covering a region near Tehran, Iran have been used to demonstrate the enhancement and accuracy assessment of fused image over the initial images. The evaluation results of fused images showed that the Haar wavelet approach has good quality in preserving spectral information as well as spatial information. Classification results were compared to evaluate the effectiveness of the two classification approaches. Result of the pan-sharpened image classifications displayed that the object-oriented procedure presented more accurate outcomes (90.47 %) than those obtained by pixel-based classification method (77.33 %).     

Semi Automatic Road Extraction by Fusion of High Resolution Optical and Radar Images

Two new methods for fusion of high-resolution optical and radar satellite images have been proposed to extract roads in high quality in this paper. Two fusion methods, including neural network and knowledge-based fusion are introduced. The first proposed method consists of two stages: (i) separate road detection using each dataset and (ii) fusion of the results obtained using a neural network. In this method, the neural networks are separately applied on high-resolution IKONOS and TerraSAR-X images for road detection, using a variety of texture parameters. The outputs of two neural networks, as well as the spectral features of optical image, are used in a third neural network as inputs. The second method is a knowledge-based fusion using thresholds of narrow roads and vegetation gray levels. First roads are extracted from each source separately. The outputs are then compared and advantages and disadvantages of each data source are investigated . The results obtained from accuracy assessment show the efficiency of the proposed methods. Furthermore, the comparison of the results showed the superiority of the first algorithm.