Illumination change robustness in direct visual SLAM
| Autor: | Thomas Schops, Seonwook Park, Marc Pollefeys |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
business.industry
Computer science ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020207 software engineering 02 engineering and technology Simultaneous localization and mapping Real image Visualization Odometry Robustness (computer science) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Artificial intelligence Visual odometry business |
| Zdroj: | ICRA |
| DOI: | 10.1109/icra.2017.7989525 |
| Popis: | Direct visual odometry and Simultaneous Localization and Mapping (SLAM) methods determine camera poses by means of direct image alignment. This optimizes a photometric cost term based on the Lucas-Kanade method. Many recent works use the brightness constancy assumption in the alignment cost formulation and therefore cannot cope with significant illumination changes. Such changes are especially likely to occur for loop closures in SLAM. Alternatives exist which attempt to match images more robustly. In our paper, we perform a systematic evaluation of real-time capable methods. We determine their accuracy and robustness in the context of odometry and of loop closures, both on real images as well as synthetic datasets with simulated lighting changes. We find that for real images, a Census-based method outperforms the others. We make our new datasets available online3. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|