Simultaneous localization, mapping and deblurring
Authors:
- 1 November 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1203-1210
Abstract
Handling motion blur is one of important issues in visual SLAM. For a fast-moving camera, motion blur is an unavoidable effect and it can degrade the results of localization and reconstruction severely. In this paper, we present a unified algorithm to handle motion blur for visual SLAM, including the blur-robust data association method and the fast deblurring method. In our framework, camera motion and 3-D point structures are reconstructed by SLAM, and the information from SLAM makes the estimation of motion blur quite easy and effective. Reversely, estimating motion blur enables robust data association and drift-free localization of SLAM with blurred images. The blurred images are recovered by fast deconvolution using SLAM data, and more features are extracted and registered to the map so that the SLAM procedure can be continued even with the blurred images. In this way, visual SLAM and deblurring are solved simultaneously, and improve each other's results significantly.Keywords
This publication has 12 references indexed in Scilit:
- Non-uniform deblurring for shaken images2010
- Monocular SLAM with locally planar landmarks via geometric rao-blackwellized particle filtering on Lie groups2010
- ESM-Blur: Handling & rendering blur in 3D tracking and augmentation2009
- A visual odometry framework robust to motion blur2009
- High-quality motion deblurring from a single imageACM Transactions on Graphics, 2008
- Parallel Tracking and Mapping for Small AR Workspaces2007
- Single Image Motion Deblurring Using Transparency2007
- Removing camera shake from a single photograph2006
- Lucas-Kanade 20 Years On: A Unifying FrameworkInternational Journal of Computer Vision, 2004
- An iterative technique for the rectification of observed distributionsThe Astronomical Journal, 1974