Vision, GPS and Translation and Orientation Data from a Car: for testing and evaluation of stereo visual odometry and SLAM algorithms

The dataset was gathered to inform development of a low-cost robotic sensor platform, capable of performing accurate estimation of robotic position for Simultaneous Localisation and Mapping or SLAM tasks. The data was gathered from a car driven in a 9.5km circuit around the University of Queensland's St Lucia campus on the 15/12/2010. Travelling at speeds of up to 60km/h, the driven circuit traverses local roads and encounters a number of varying scenarios including roadworks, speed bumps, bright scenes, a number of loop closure events, multi-lane roads and roundabouts. The data consists of visual data from a calibrated stereo pair, translation and orientation information as a ground truth from an XSens Mti-g INS GPS and additional information from a USB NMEA GPS. The full set of images is available as separated 1.95GB RAR files, while a smaller subset of 100 images in both raw and debayered/undistorted formats is also available. MD5 checksums are provided on large files to ensure integrity of downloaded data.