The Power of GMMs: Unsupervised Dirt Spot Detection for Industrial Floor Cleaning Robots
| Autor: | Andreas Grünauer, Georg Halmetschlager-Funek, Johann Prankl, Markus Vincze |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0209 industrial biotechnology
Quality of work Computer science business.industry Online learning 020206 networking & telecommunications Usability Dirt 02 engineering and technology Mixture model GeneralLiterature_MISCELLANEOUS Power (physics) 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering Unsupervised learning Robot Computer vision Artificial intelligence business |
| Zdroj: | Towards Autonomous Robotic Systems ISBN: 9783319641065 TAROS |
| DOI: | 10.1007/978-3-319-64107-2_34 |
| Popis: | Small autonomous florr cleaning robots are the first robots to have entered our homes. These automatic vacuum cleaners have only used ver low-level dirt detection sensors and the vision systems have been constrained to plain-colored and simple-textured floors. However, for industrial applications, where efficiency and the quality of work are paramount, explicit high-level dirt detection is essential. To extend the usability of floor cleaning robots to theses real-world applications, we introduce a more general approach that detects dirt spots on single-colored as well as regularly-textured floors. Dirt detection is approached as a single-class classification problem, using unsupervised online learning of a Gaussian Mixture Model representing the floor pattern. An extensive evaluation shows that our method detects dirt spots on different floor types and that it outperforms state-of-the-art approaches especially for complex floor textures. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|