Applicability of Deep Learned vs Traditional Features for Depth Based Classification
| Autor: | Ingo Kossyk, Mo Li, Zoltan-Csaba Marton, Fabio Bracci |
|---|---|
| Přispěvatelé: | Barneva, R |
| Rok vydání: | 2019 |
| Předmět: |
Scene analysis
Computer science business.industry Deep learning Training data sets Cognitive neuroscience of visual object recognition scene analysis deep learning features Machine learning computer.software_genre object recognition Institut für Robotik und Mechatronik (ab 2013) point cloud descriptor 3D shape descriptor Data set Work (electrical) Margin (machine learning) Sample size determination Artificial intelligence business computer |
| Zdroj: | Computational Modeling of Objects Presented in Images. Fundamentals, Methods, and Applications ISBN: 9783030208042 CompIMAGE |
| DOI: | 10.1007/978-3-030-20805-9_13 |
| Popis: | In robotic applications, highly specific objects such as industrial parts, for example, often need to be recognized. In these cases methods can’t rely on the online availability of large labeled training data sets or pre-trained models. This is especially true for depth data, thus making it challenging for deep learning (DL) approaches. Therefore, this work analyzes the performance of various traditional (global or part-based) and DL features on a restricted depth data set, depending on the tasks complexity. While the sample size is small, we can conclude that pre-trained DL descriptors are the most descriptive, but not by a statistically significant margin and therefore part-based descriptors are still a viable option for small, but difficult 3D data sets. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|