Search

Hyperspectral imaging has many applications such as Land Use / Land Cover mapping, urban planning, mineral exploration, environmental monitoring, and military surveillance. This research is concerned with the investigation of the improvement of urban land cover mapping using airborne hyperspectral data. Geometric correction and atmospheric correction have been conducted. Quality of rectification has been assessed using DGPS check points. It was found that the total RMS of airborne hyperspectral data was 2.7372m. Minimum Noise Fraction (MNF) transformation and Pixel Purity Index (PPI) have been used for spectral and spatial data reduction. After that feature selection has been carried out. In this research a supervised classification method has been applied using the Spectral Angle Mapper,then, the discrimination of urban feature has been improved using expert system. An expert system classification was developed using the knowledge engineer of ERDAS Imagine 2010 for post classification refinement of initially classified output. The primary motivation behind using the expert system was to reclassify the initial Spectral Angle Mapper classification and reduce errors of omission and commission. Results revealed that the overall accuracy of SAM was 90% and kappa index was 0.89 whereas the expert system gives slightly higher overall accuracy 94.5 percent and a kappa index was 0.93.

Egypt has launched its first Earth remote sensing satellite EgyptSat-1 in 2007. A series of evaluations of the usefulness and limitations of EgyptSat-1 images for different applications are required. This research is concerned with the investigation of the geometric and cartographic potential of EgyptSat-1 image in order to know to what scale EgyptSat-1 image is suitable for map production and map updating. The geometrical accuracy of rectification of EgyptSat-1 based on non-parametric rectification (polynomial approach and rubber sheeting) has been evaluated. Four methods of rectification have been compared: different orders of 2D polynomials (first-order polynomial, second-order polynomial, third-order polynomial) and rubber sheeting method. Different sets of ground control points (observed with differential global positioning system) have been tested. Several experiments were performed to rectify EgyptSat-1 image using the four rectification methods. For each method, different numbers of ground control points (GCPs) were used starting at 15 points, and then the number was reduced each time till the minimum number of GCPs for each method is reached and with three different GCP distributions. Various issues such as the solutions, feasibility, accuracy, and requirements for control information are addressed. The results show that rubber sheeting followed by third-order polynomial then second-order polynomial then first-order polynomial gives the best root mean square error. Actually, a serious mapping should be based on a satisfying by the theory justified mathematical model so that rubber sheeting should not be used for a serious mapping even it shows smaller discrepancies, but for the flat test area, an approximate 2D transformation can be accepted. Also although third-order polynomial is accurate in the proximity of GCPs and shows smaller discrepancies compared to the first- and the second-order polynomials, they can lead to significant errors for regions outside the GCP range and should not be used for a serious mapping. One can be considered the best resulted rectified image that obtained from second-order polynomial followed by the first-order polynomial. It was found in our study area that the minimum number of control points for each method gives accuracy better than a pixel. The first-order polynomial and rubber sheeting are good from the economical cost that they use minimum number of control points (three). It was found that the planimetric accuracy of rectified EgyptSat image met the 1:25,000 mapping standard (National Map Accuracy Standards). Also from the assessment of the information content of the EgyptSat image, it was found that it is consistent with the map scale of 1:25,000. In conclusion by analysis of the results, it is obvious that EgyptSat images are able to produce and update map of scale 1:25,000.

A shoreline is defined as the line of contact between land and water surface. Shoreline extraction/mapping is critical in many coastal zone applications such as safe navigation and coastal environmental protection. Digitizing a feature such as the coastline is a very tedious and time-consuming operation. In this research shoreline mapping at a sub-pixel and pixel levels was evaluated in the northern part of the coastal zone of Egypt (Port Said). Three different image fusion techniques have been used to merge two co-registered data, radar (Radarsat) and optical (Landsat), to improve the classification accuracy. Spatial, spectral, and radiometric qualities of the fused images have been evaluated. The resulted three fused images, the Landsat and Radarsat images, were fed to the fuzzy and the maximum likelihood classifiers where the classification delineated two classes; water and nonwater. The accuracy of the classified images was estimated based on a reference data. After classification, the results have been compared where it was found that image fusion has improved the classification accuracy and the accuracy of the fuzzy classification is better than the maximum likelihood classification in all cases. The best resulted classified image from the ten cases is that obtained from the fused Radarsat-Landsat images using IHS technique that was classified with the fuzzy classifier. Shoreline has been extracted from the (IHS-fuzzy), (SAR-fuzzy), and (Landsat-fuzzy). Experimental results showed that the shoreline extraction accuracy is dramatically improved by the effective image fusion of Landsat and SAR data. The accuracies of the extracted shorelines from (Landsat-fuzzy), (Radarsat-fuzzy), and (IHS-fuzzy) data based on twenty differential GPS check points are estimated to be 5.69, 5.26, and 5.14 m, respectively. The three shorelines extracted/mapped from (Landsat-fuzzy), (Radarsat-fuzzy), (IHS-fuzzy) data were compared to a reference shoreline. The RMS has been computed related to thirty checkpoints on the reference shoreline. The accuracies of the extracted shorelines from (Landsat-fuzzy), (SAR-fuzzy), and (IHS-fuzzy) data are estimated to be 8.3, 7.27, and 6.75 m, respectively. The positional quality of the extracted shorelines (using generalization factor) from (Landsat-fuzzy), (SAR-fuzzy), and (IHS-fuzzy) data are estimated to be 0.977, 0.986, and 0.999, respectively.

Buildings are one of the most important geospatial features for spatial analysis and mapping. Building extraction has been an active research topic in computer vision as well as digital photogrammetry in recent years. Building detection is the process of obtaining the approximate position and shape of a building, while building extraction can be defined as the problem of precisely determining the building outlines, which is one of the critical problems in digital photogrammetry. Building information is extremely important for many applications such as urban planning, telecommunication, three-dimensional city modeling, or extraction of unauthorized buildings over agricultural lands. Three approaches for building detection based on maximum likelihood classification have been compared, firstly, building detection from classification of multispectral satellite image only. The second approach is building detection from classification of multispectral satellite image, while the height information from Light Detection and Ranging (LIDAR) data is applied as an additional channel together with spectral channel. The third approach is building detection based on classification of multispectral satellite image where normalized difference vegetation index (NDVI) and the height information from LIDAR data are applied as additional channels together with spectral channel. The contributions of the individual cues used in the classification have been evaluated. The three approaches were tested using urban blocks containing different sizes, roof color and shapes of buildings. The results show that the third approach is the best for building detection followed by the second approach then the first approach. The third approach appears to be quite successful especially in solving the problem of building detection for those urban blocks that contain closely located buildings as well as in separation of buildings from trees. The third approach results have been improved by developing a building detection module based on integration of classified image, elevation data, and spectral information. A rule-based expert system consists of essentially hypothesis (output; buildings), and variables of a knowledge base were developed in the knowledge engineer of ERDAS Imagine for post-classification refinement of initially classified output building mask. Classification rules were enriched with ancillary data such as the normalized digital surface model and the NDVI. Each rule is a representation of each node in the tree that describes a building class or probability of presence of buildings pixel. Then, the building detection result has been evaluated. It has been found that the use of an expert system, which considers expert knowledge, would further help in the discrimination of the classes and improve classification accuracy of buildings. The overall accuracy of expert classification was 96% and kappa coefficient was 0.95.