Quantitatively Assessing Roads Extracted from High-Resolution Imagery

Urban mapping has become a challenge for scientists since the launch of high spatial resolution satellites. This paper focuses on the problem of quality when extracting roads from such data. The definition of a judicious reference enabling the establishment of quantitative criteria is proposed. A method is presented and two sets of criteria dedicated to the evaluation of road extraction algorithms are introduced. An example of an application is proposed enhancing the benefits of a rigorous approach of this problem.