VISUAL ODOMETRY CORRECTION BASED ON LOOP CLOSURE DETECTION

An essential requirement in the fields of robotics and intelligent transportation systems is to know the position of a mobile robot along the time, as well as the trajectory that it describes by using on-board sensors. In this paper, we propose a novel approach focused on the use of cameras as perception sensors for visual localization in unknown environments. Our system allows to perform a robust visual odometry, where correction algorithms based on loop closure detection are applied for correctly identifying the location of a robot in long-term situations. In order to satisfy the previous conditions, we carry out a methodological improvement of some classic computer vision techniques. In addition, new algorithms are implemented with the aim of compensating the drift produced in the visual odometry calculation along the traversed path. According to this, our main goal is to obtain an accurate estimation of the position, orientation and trajectory followed by an autonomous vehicle. Sequences of images acquired by an on-board stereo camera system are analyzed without any previous knowledge about the real environment. Several results obtained from these sequences are presented to demonstrate the benefits of our proposal.