Automatic Motion Segmentation via a Cumulative Kernel Representation and Spectral Clustering
| Autor: | José Luis Rodríguez-Sotelo, O. T. Sánchez-Manosalvas, Luis Suárez-Zambrano, Omar R. Ona-Rocha, Ana C. Umaquinga-Criollo, Paul D. Rosero-Montalvo, Diego Hernán Peluffo-Ordóñez |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
0209 industrial biotechnology
Multiple kernel learning business.industry Segmentation-based object categorization Computer science Dynamic data Scale-space segmentation Pattern recognition 02 engineering and technology Spectral clustering 020901 industrial engineering & automation Robustness (computer science) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Segmentation Artificial intelligence Cluster analysis business |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783319689340 IDEAL |
| DOI: | 10.1007/978-3-319-68935-7_44 |
| Popis: | Dynamic or time-varying data analysis is of great interest in emerging and challenging research on automation and machine learning topics. In particular, motion segmentation is a key stage in the design of dynamic data analysis systems. Despite several studies have addressed this issue, there still does not exist a final solution highly compatible with subsequent clustering/classification tasks. In this work, we propose a motion segmentation compatible with kernel spectral clustering (KSC), here termed KSC-MS, which is based on multiple kernel learning and variable ranking approaches. Proposed KSC-MS is able to automatically segment movements within a dynamic framework while providing robustness to noisy environments. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|