Get started
Work

Modeling, Extracting and Description of Intrinsic Cues of High Resolution Satellite Images: Independent Component Analysis Based Approaches

Year: 2011
Type: dissertation
Abstract: Sub-meter resolution satellite images, capture very detailed information, as for example, shape of buildings, roads, etc. The main purpose of the thesis is to propose descriptors for sub-meter resolution satellite images especially for those who contain geometrical or man-made structures. Independent component analysis (ICA) is a good candidate for this purpose, since previous studies demonstrated that the resulted basis vectors contain some small lines and edges, the important elements in the characterization of geometrical structures. As a basic analysis, a study about the effects of scale size and dimensionality of ICA system on indexing of satellite images is presented and the optimum dimensionality and scale size are found. There are two view points for feature extraction based on ICA. The usual idea is to use the ICA coefficients (ICA sources) and the other is to use the ICA basis vectors related to every image. Based on the first point of view, an ordinary ICA source based approach is proposed for feature extraction. This approach is developed and modified through a topographic ICA system to extract middle level features which leads to a significant improvement in results. Based on the other point of view, two methods are proposed. One of them uses the bag of words idea which considers the basis vectors as visual words. Second method uses the lines properties inside the basis vectors to extract features. Also, using the lines properties idea, another method is developed which directly detects the line segments in the images. Finally, the capabilities of proposed descriptors are compared through a supervised classification based on support vector machine (SVM).
Source: HAL
Language: English
Open Access status: green
OpenAlex ID: W598447940
Cites: 45
Cited by:
Related to: 10