Robust direct visual odometry using mutual information
- 1 October 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9-14
Abstract
Robust vision-based state estimation in real-world indoor and outdoor environments is a challenging problem due to the combination of drastic lighting changes and limited dynamic range of commodity cameras. This limitation is at odds with the fundamental constancy of illumination assumption made in image-intensity based tracking methodologies. We present and experimentally validate a Mutual Information (MI) based dense rigid body tracking algorithm that is demonstrably robust to drastic illumination changes, and compare the performance of this algorithm to a canonical Sum of Squared Differences based Lucas-Kanade tracking formulation. Further, we propose a novel approach that combines the robustness benefits of information-based measures and the speed of traditional intensity based Lucas-Kanade tracking for robust state estimation in real-time.Keywords
This publication has 17 references indexed in Scilit:
- Direct model based visual tracking and pose estimation using mutual informationImage and Vision Computing, 2014
- DTAM: Dense tracking and mapping in real-time2011
- Accurate real-time tracking using mutual information2010
- Parallel Tracking and Mapping for Small AR Workspaces2007
- Robust motion estimation under varying illuminationImage and Vision Computing, 2005
- Estimating mutual informationPhysical Review E, 2004
- Lucas-Kanade 20 Years On: A Unifying FrameworkInternational Journal of Computer Vision, 2004
- Mutual-information-based registration of medical images: a surveyIEEE Transactions on Medical Imaging, 2003
- A generalized brightness change model for computing optical flow2002
- The statistics of natural imagesNetwork: Computation in Neural Systems, 1994