Supervisor's review for the bachelor's thesis of the 4th year student of the Department of Informatics of the Mathematics and Mechanics Department Shevchenko V.A.  Development of methodology for comparing visual odometry approaches using open datasets Bachelor's work of Shevchenko V.A. is devoted to the problem of determining the displacement of an object by changing the image with a camera fixed on it. The task is relevant, since the definition of object displacement is used in various tasks of navigation, path planning, automatic control, collision avoidance in the field of robotics and self-controlled vehicles. At the same time, visual methods using a single camera have the best accuracy to equipment ratio.  The aim of the work was to review the existing methods of visual odometry for a single camera, existing open databases, develop a comparison methodology, compare different algorithms.  The following results are achieved in the work: • The algorithms DSO, LSD-SLAM, SVO are considered; • Open databases KITTI, Apollo Scape, Tum Mono; • Metrics are proposed for comparison based on local and accumulated errors; • Comparison of algorithms on the considered databases; The best accuracy was demonstrated by the DSO algorithm.  The results are of great practical importance for the choice of the visual odometry method for solving navigation problems in robotics and the development of unmanned vehicles.  The work has also disadvantages: • errors are not normalized to the length of the trajectory, the error size is not commensurable for different test sequences; • The SVO algorithm could not be started • the text of the thesis note has some stylistic shortcomings.  Despite the shortcomings, given the valuable practical results of the work, I believe that the bachelor's thesis of Shevchenko V.A. deserves an evaluation - "EXCELLENT".  PhD., senior lecturer of Department of Informatics Faculty of Mathematics and Mechanics of St. Petersburg State University Salischev S.I. 05/15/2018