Stereo Visual Odometry


Brief overview


Visual odometry is the process of determining the position and orientation of a mobile robot by using camera images. A stereo camera setup and KITTI grayscale odometry dataset are used in this project. KITTI dataset is one of the most popular datasets and benchmarks for testing visual odometry algorithms. This project aims to use OpenCV functions and apply basic cv principles to process the stereo camera images and build visual odometry using the KITTI dataset.

SIFT Visual Odometry Demo Video [4x]

Disparity Map

disparity_map

Depth Map

Depth_map_limit_50m

SIFT Features

SIFT_Features

SIFT Feature Matching

Feature_Matching

Odometry path

SIFT

sift

ORB

orb

Presentation

Stereo Visual Odometry Presentation.pdf

Write-up

Stereo Visual Odometry - MJ Nel.pdf

GitHub