Name
Abstract | ||
|---|---|---|
Tracking arbitrary objects in natural environments is a challenging task in visual computing. A central problem is the need to adapt to changing appearances under strong transformation and occlusion. We propose a tracking framework that utilises the strength of Convolutional Neural Networks to create a robust and adaptive model of the object from training data produced during tracking. An incremental update mechanism provides increased performance and reduces the computational costs for training during tracking, allowing for robust real-time tracking with state-of-the-art performance. Together with optimisations for deploying the framework on humanoid robots and distributed devices, this shows its viability for research in developmental robotics on questions around infant cognition or active exploration. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1016/j.neucom.2018.10.086 | Neurocomputing |
Keywords | Field | DocType |
Object tracking,Convolutional neural networks,Developmental robotics | Training set,Visual computing,Computer vision,Convolutional neural network,Developmental robotics,Video tracking,Artificial intelligence,Robot,Cognition,Mathematics,Machine learning,Humanoid robot | Journal |
Volume | ISSN | Citations |
342 | 0925-2312 | 0 |
PageRank | References | Authors |
0.34 | 13 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Stefan Heinrich | 1 | 28 | 5.50 |
| Peer Springstübe | 2 | 0 | 0.34 |
| Tobias Knöppler | 3 | 0 | 0.34 |
| Matthias Kerzel | 4 | 32 | 7.67 |
| Stefan Wermter | 5 | 1100 | 151.62 |