Robotics: Science and Systems VIII

Visual Route Recognition with a Handful of Bits

Michael Milford


In this paper we use a sequence-based visual localization algorithm to reveal surprising answers to the question, how much visual information is actually needed to conduct effective navigation? The algorithm actively searches for the best local image matches within a sliding window of short route segments or sub-routes, and matches sub-routes by searching for coherent sequences of local image matches. In contrast to many existing techniques, the technique requires no pre-training or camera parameter calibration. We compare the algorithm's performance to the state-of-the-art FAB-MAP 2.0 algorithm on a 70 km benchmark dataset. Performance matches or exceeds the state of the art feature-based localization technique using images as small as 4 pixels, fields of view reduced by a factor of 250, and pixel bit depths reduced to 2 bits. We present further results demonstrating the system localizing in an office environment with near 100



    AUTHOR    = {Michael Milford}, 
    TITLE     = {Visual Route Recognition with a Handful of Bits}, 
    BOOKTITLE = {Proceedings of Robotics: Science and Systems}, 
    YEAR      = {2012}, 
    ADDRESS   = {Sydney, Australia}, 
    MONTH     = {July},
    DOI       = {10.15607/RSS.2012.VIII.038}