/Monocular-Visual-Odometry

Monocular Visual Odometry on KITTI dataset. Implemented in MATLAB

Primary LanguageMatlab

Monocular-Visual-Odometry

MATLAB code for Monocular Visual Odometry with KITTI dataset. The goal of this approach is to complement the erroneous odometry sensors using the rich information in relations between consecutive images and with the use of minimum hardware, i.e. a monocular vision sensor. In this project we implemented feature detection, feature extraction, and feature matching methods used for each images. Also implemented the pipeline of monocular visual odometry and test our implementation on the KITTI dataset.