The paper presents a method for patch classification and remoteimage segmentation based on correlated color information. During the trainingphase, a supervised learning algorithm is considered. In the testing phase, weused the classifier built a priori to predict which class an input image samplebelongs to. The tests showed that the most relevant features are contrast, energyand homogeneity extracted from the co-occurrence matrix between H and Scomponents. Compared to gray-level, the chromatic matrices improve the processof texture classification. For experimental results, the images were acquiredby the aid of an unmanned aerial vehicle and represent various types of terrain.Two case studies have shown that the proposed method is more effective thanconsidering separate color channels: flooded area and road segmentation. Also it is shown that the new algorithm provides a faster execution time than the similar one proposed.
Photogrammetry is a well-studied and much-used analysis tool. Typical use cases include area surveillance, flood monitoring and related tasks. Usually, an Unmanned Aerial System (UAS) is used as support for image acquisition from an a priori delimited region in a semi-automated manner (via a mix of ground control and autonomous trajectory tracking). This in turn has led to various algorithms which
handle path trajectory generation under realistic constraints but still many avenues remain open. In this paper, we consider typical costs and constraints (UAS dynamics, total-path length, line inter-distance, turn points, etc.) in order to obtain, via optimization procedures, an optimal trajectory. To this end we make use of polyhedral set operations, flat trajectory generation and other similar tools. Additional work includes the study of non-convex regions and estimation of the number of photographs taken via Ehrhart polynomial computations.