This letter introduces a new approach for the automated detection of circular oil tanks from single panchromatic satellite images. The new approach considers the symmetric nature of the circular oil depots, and it computes the radial symmetry in a unique way. We propose an automated thresholding method to focus on circular regions and a new measure, circle support ratio, to verify detected circles. Experiments are performed on GeoEye-1 test scenes, and the results reveal that the new approach is capable of detecting oil tanks with high success. The performance of our approach is also compared with leading techniques from the literature and has provided comparable or superior results.

The research on automatic road detection from satellite images started in the mid-70s [1]. Nowadays, there are many algorithms about non-supervised and semi-supervised road extraction. While some methods only use weak geometric information in combination with radiometric and spectral characteristics of the roads, more advanced local and global geometric properties such as smooth continuation, maximum curvature or network formation started to appear in recent algorithms.

Visually extracted 2D and 3D information have their own advantages and disadvantages that complement each other. Therefore, it is important to be able to switch between the different dimensions according to the requirements of the problem and use them together to combine the reliability of 2D information with the richness of 3D information. In this article, we use 2D and 3D information in a feature-based vision system and demonstrate their complementary properties on different applications (namely: depth prediction, scene interpretation, grasping from vision and object learning).