An algorithm for recognizing linear objects in aerial photos automatically

A new algorithm for detecting linear infrastructural objects in aerial photos is presented. It is assumed that these objects pass through the whole image: beginning at one side and finishing at the opposite one. It is also assumed that the altitude of shooting and the image scale are invariable. The presented algorithm synthesizes the operation of an edge detector, a ridge detector, and the Hough accumulator into an object-of-interest mask excluding lots of spurious responses, and it completes missing information missed by detectors. First of all the image is preprocessed and anisotropically and repeatedly shrunk along the direction of the linear object and synthesis is performed by finding the shortest paths in a graph. The graph is presented in the form of a mesh, where each mesh node corresponds to a pixel of the shrunk image. At each node on the edges and in ridge lines, its energy is calculated, which is the reliability of this pixel. Then, the path that maximizes the sum of energies at the nodes is determined by considering its curvature. The obtained paths form a mask of linear objects. The algorithm is verified by using aerial photos for different seasons, and it demonstrates proper results (accuracy is ~80%).