Talks and Poster Presentations (with Proceedings-Entry):
A. Grünauer, G. Halmetschlager-Funek, J. Prankl, M. Vincze:
"The Power of GMMs: Unsupervised Dirt Spot Detection for Industrial Floor Cleaning Robots";
Talk: 18th Towards Autonomous Robotic Systems Conference 2017,
- 07-21-2017; in: "18th TAROS Conference 2017",
Small autonomous floor cleaning robots are the first robots to have entered our homes. These automatic vacuum cleaners have only used very 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.
Visual oor inspection, RGBD, GMM, unsupervised learning, industrial cleaning robots
Created from the Publication Database of the Vienna University of Technology.