Publikation
Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal Fully-Convolutional Networks
Noshaba Cheema; Somayeh Hosseini; Janis Sprenger; Erik Herrmann; Han Du; Klaus Fischer; Philipp Slusallek
In: Paolo Cignoni; Eder Miguel (Hrsg.). Eurographics 2019 - Short Papers. Eurographics (EG-2019), The 40th Annual Conference of the European Association for Computer Graphics, May 6-10, Genoa, Italy, Pages 69-72, The Eurographics Association, 2019.
Zusammenfassung
Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, natural looking motions, most data-driven approaches require considerable efforts of pre-processing, including motion segmentation and annotation. Existing (semi-) automatic solutions either require hand-crafted features for motion segmentation or do not produce the semantic annotations required for motion synthesis and building large-scale motion databases. In addition, human labeled annotation data suffers from inter- and intra-labeler inconsistencies by design. We propose a semi-automatic framework for semantic segmentation of motion capture data based on supervised machine learning techniques. It first transforms a motion capture sequence into a ''motion image'' and applies a convolutional neural network for image segmentation. Dilated temporal convolutions enable the extraction of temporal information from a large receptive field. Our model outperforms two state-of-the-art models for action segmentation, as well as a popular network for sequence modeling. Most of all, our method is very robust under noisy and inaccurate training labels and thus can handle human errors during the labeling process.
Projekte
- DISTRO - Distributed 3D Object Design
- Hybr-iT - Hybride und intelligente Mensch-Roboter-Kollaboration - Hybride Teams in wandlungsfähigen, cyber-physischen Produktionsumgebungen
- REACT - Autonomes Fahren: Modellierungs-, Lern- und Simulationsumgebung für das Fußgängerverhalten in kritischen Verkehrssituationen