TY - CONF T1 - Unaided stereo vision based pose estimation A1 - Warren, Michael A1 - McKinnon, D. A1 - He, H. A1 - Upcroft, Ben ED - Wyeth, Gordon ED - Upcroft, Ben Y1 - 2010/// KW - Stereo vision KW - visual odometry KW - field robotics KW - computer vision KW - dataset PB - Australian Robotics and Automation Association JF - Australasian Conference on Robotics and Automation CY - Brisbane UR - http://eprints.qut.edu.au/39881/ L1 - file:///E:/Files/c39881.pdf N2 - This paper presents the development of a low- cost sensor platform for use in ground-based vi- sual pose estimation and scene mapping tasks. We seek to develop a technical solution using low-cost vision hardware that allows us to accu- rately estimate robot position for SLAM tasks. We present results from the application of a vi- sion based pose estimation technique to simul- taneously determine camera poses and scene structure. The results are generated from a dataset gathered traversing a local road at the St Lucia Campus of the University of Queens- land. We show the accuracy of the pose esti- mation over a 1.6km trajectory in relation to GPS ground truth. ER -