X-means: Extending K-means with Efficient Estimation of the Number of Clusters
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Extracting Cylinders in Full 3D Data Using a Random Sampling Method and the Gaussian Image
VMV '01 Proceedings of the Vision Modeling and Visualization Conference 2001
Adaptive Behavior
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
On the algorithmic implementation of multiclass kernel-based vector machines
The Journal of Machine Learning Research
One-Shot Learning of Object Categories
IEEE Transactions on Pattern Analysis and Machine Intelligence
Evaluation of Features Detectors and Descriptors based on 3D Objects
International Journal of Computer Vision
Interactive segmentation for manipulation in unstructured environments
ICRA'09 Proceedings of the 2009 IEEE international conference on Robotics and Automation
Humanoid motion planning for dual-arm manipulation and re-grasping tasks
IROS'09 Proceedings of the 2009 IEEE/RSJ international conference on Intelligent robots and systems
A tale of two object recognition methods for mobile robots
ICVS'08 Proceedings of the 6th international conference on Computer vision systems
Segmentation and modeling of visually symmetric objects by robot actions
International Journal of Robotics Research
Manipulator and object tracking for in-hand 3D object modeling
International Journal of Robotics Research
Exploiting low-level image segmentation for object recognition
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Direct solutions for computing cylinders from minimal sets of 3d points
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Hi-index | 0.00 |
Humans can effortlessly perceive an object they encounter for the first time in a possibly cluttered scene and memorize its appearance for later recognition. Such performance is still difficult to achieve with artificial vision systems because it is not clear how to define the concept of objectness in its full generality. In this paper we propose a paradigm that integrates the robot's manipulation and sensing capabilities to detect a new, previously unknown object and learn its visual appearance. By making use of the robot's manipulation capabilities and force sensing, we introduce additional information that can be utilized to reliably separate unknown objects from the background. Once an object has been identified, the robot can continuously manipulate it to accumulate more information about it and learn its complete visual appearance. We demonstrate the feasibility of the proposed approach by applying it to the problem of autonomous learning of visual representations for viewpoint-independent object recognition on a humanoid robot.