Hydrocarbon (HC) microseepages can be indicator of possible reservoirs. For that reason, mapping the microseepages has potential to be used in petroleum exploration. This study presents a methodology for mapping HC microseepages and related clay mineral alteration in Gemrik Anticline, Adiyaman. For this purpose samples were collected from the potential seepage zones and tested by geochemical analysis. All samples were found to contain some HC. Then, an ASTER image of the region was obtained and a band combination was generated to map this particular region. To map related clay mineral alteration, firstly reflectance spectra of samples were measured using field spectrometer. Secondly, spectrally-known samples were analyzed in USGS Library to determine the reflectance spectra of the constitutional clay minerals in the samples. Lastly, the reflectance characteristics of selected end v members were represented as ASTER band combinations based on their spectral absorption characteristics and literature information. Crosta Technique was used to determine required principal components to map HC microseepage and related clay mineral alteration. Then, this methodology is applied to the whole ASTER image. Ground truth study showed that more than 65% of the revisited anomalies show similar prospects to that of the referenced anticline regardless of their geochemical content. In order to certify the ASTER band combination for mapping HC microseepages, anomalous and non-anomalous pixels were selected from the resultant HC map and given as training data samples to AdaBoost loop which is an image processing algorithm. It has been found that ASTER band combination offered for mapping HC microseepages is similar to that of AdaBoost Algorithm output.

Two approaches were developed for detecting earthquake damaged buildings from post-event aerial photographs using shadow analysis and perceptual grouping. In the first approach, it is assumed that the vector boundaries of the buildings are not known a priori. Therefore, only the post-event aerial photographs were used to detect the collapsed buildings. The approach relies on an idea that if a building is fully damaged then, it will not generate a closed contour. First, a median filter is applied to remove the noise. Then, the edge pixels are detected through a Canny edge detector and the line segments are extracted from the output edge image using a raster-to-vector conversion process. After that, the line segments are grouped together using a three-level hierarchical perceptual grouping procedure to form a closed contour. The principles used in perceptual grouping include the proximity, the collinearity, the continuity and the perpendicularity. In the second approach, it is assumed that the vector boundaries of the buildings are known a priori. Therefore, this information is used as additional data source to detect the collapsed buildings. First, the edges are detected from the image through a Canny edge detector. Second, the line segments are extracted using a raster-to-vector conversion process. Then, a two-level hierarchical perceptual grouping procedure is used to group these line segments. The boundaries of the buildings are available and stored in a GIS as vector polygons. Therefore, after applying the perceptual grouping procedure, the damage conditions of the buildings are assessed on a building-by-building basis by measuring the agreement between the detected line segments and the vector boundaries.