Next Article in Journal
Blind Fractionally Spaced Channel Equalization for Shallow Water PPM Digital Communications Links
Previous Article in Journal
Detection of Simulated Fukushima Daichii Fuel Debris Using a Remotely Operated Vehicle at the Naraha Test Facility
Open AccessArticle

Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data

1
Department Augmented Vision, German Research Center for Artificial Intelligence (DFKI), 67663 Kaiserslautern, Germany
2
Department of Computer Graphics, Max Planck Institute for Informatics, 66123 Saarbrücken, Germany
3
Department of Computer Science, University of Kaiserslautern, 67663 Kaiserslautern, Germany
4
School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), 44000 Islamabad, Pakistan
5
Department of Computer Science, University of Prince Mugrin (UPM), 20012 Madinah, Saudi Arabia
*
Author to whom correspondence should be addressed.
Sensors 2019, 19(20), 4603; https://doi.org/10.3390/s19204603
Received: 23 September 2019 / Revised: 15 October 2019 / Accepted: 15 October 2019 / Published: 22 October 2019
(This article belongs to the Section Physical Sensors)
Recovery of articulated 3D structure from 2D observations is a challenging computer vision problem with many applications. Current learning-based approaches achieve state-of-the-art accuracy on public benchmarks but are restricted to specific types of objects and motions covered by the training datasets. Model-based approaches do not rely on training data but show lower accuracy on these datasets. In this paper, we introduce a model-based method called Structure from Articulated Motion (SfAM), which can recover multiple object and motion types without training on extensive data collections. At the same time, it performs on par with learning-based state-of-the-art approaches on public benchmarks and outperforms previous non-rigid structure from motion (NRSfM) methods. SfAM is built upon a general-purpose NRSfM technique while integrating a soft spatio-temporal constraint on the bone lengths. We use alternating optimization strategy to recover optimal geometry (i.e., bone proportions) together with 3D joint positions by enforcing the bone lengths consistency over a series of frames. SfAM is highly robust to noisy 2D annotations, generalizes to arbitrary objects and does not rely on training data, which is shown in extensive experiments on public benchmarks and real video sequences. We believe that it brings a new perspective on the domain of monocular 3D recovery of articulated structures, including human motion capture. View Full-Text
Keywords: structure from motion; human pose estimation; articulated structure recovery structure from motion; human pose estimation; articulated structure recovery
Show Figures

Figure 1

MDPI and ACS Style

Kovalenko, O.; Golyanik, V.; Malik, J.; Elhayek, A.; Stricker, D. Structure from Articulated Motion: Accurate and Stable Monocular 3D Reconstruction without Training Data. Sensors 2019, 19, 4603.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop