Name
Abstract | ||
|---|---|---|
We propose a semi-direct monocular visual odometry algorithm that is precise, robust, and faster than current state-of-the-art methods. The semi-direct approach eliminates the need of costly feature extraction and robust matching techniques for motion estimation. Our algorithm operates directly on pixel intensities, which results in subpixel precision at high frame-rates. A probabilistic mapping method that explicitly models outlier measurements is used to estimate 3D points, which results in fewer outliers and more reliable points. Precise and high frame-rate motion estimation brings increased robustness in scenes of little, repetitive, and high-frequency texture. The algorithm is applied to micro-aerial-vehicle state-estimation in GPS-denied environments and runs at 55 frames per second on the onboard embedded computer and at more than 300 frames per second on a consumer laptop. We call our approach SVO (Semi-direct Visual Odometry) and release our implementation as open-source software. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ICRA.2014.6906584 | Robotics and Automation |
Keywords | Field | DocType |
autonomous aerial vehicles,control engineering computing,distance measurement,embedded systems,motion estimation,probability,robot vision,stereo image processing,3D points,GPS-denied environments,SVO,consumer laptop,fast semidirect monocular visual odometry,high frame-rate motion estimation,micro-aerial-vehicle state-estimation,onboard embedded computer,open-source software,outlier measurements,pixel intensities,probabilistic mapping method,subpixel precision | Computer vision,Visual odometry,Odometry,Robustness (computer science),Feature extraction,Pixel,Artificial intelligence,Frame rate,Engineering,Subpixel rendering,Motion estimation | Conference |
Volume | Issue | ISSN |
2014 | 1 | 1050-4729 |
Citations | PageRank | References |
278 | 8.23 | 28 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Christian Forster | 1 | 697 | 29.01 |
| Matia Pizzoli | 2 | 446 | 19.74 |
| Davide Scaramuzza | 3 | 2704 | 154.51 |