The human motion database: A cognitive and parametric sampling of human motion

Guerra-Filho, Gutemberg; Biswas, Arnab

doi:10.1109/fg.2011.5771381

Cited by 19 publications

(18 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HDM05 [7] provides a dataset of 1457 human whole-body motion clips with a total run length of around 50 minutes, which have been created by segmenting a continuous motion sequence demonstrated by five different non-professional actors. The Human Motion Database [8] provides five different datasets that have been acquired by using a systematic sampling methodology to select motions to be collected and additionally provides a survey of some existing motion databases in the cited article. In the Edinburgh CGVU Interaction Database [9], human whole-body motion for manipulation and object interaction tasks is captured using magnetic and RGB-D sensors.…”

Section: Related Workmentioning

confidence: 99%

“…We therefore decided early on that the annotation visualization must be interactive instead of using a rendered video of the motion from a fixed perspective. We used the Web Graphics Library (WebGL) 7 and the three.js framework, 8 which builds on WebGL, to implement an interactive 3D visualizer directly in the user's web browser without the need to install additional software. This allows the user to select an appropriate perspective that help him or her with the annotation process by rotating and zooming the virtual camera freely.…”

Section: A User Interfacementioning

confidence: 99%

See 1 more Smart Citation

The KIT Motion-Language Dataset

2016

View full text Add to dashboard Cite

Linking human motion and natural language is of great interest for the generation of semantic representations of human activities as well as for the generation of robot activities based on natural language input. However, although there have been years of research in this area, no standardized and openly available data set exists to support the development and evaluation of such systems. We, therefore, propose the Karlsruhe Institute of Technology (KIT) Motion-Language Dataset, which is large, open, and extensible. We aggregate data from multiple motion capture databases and include them in our data set using a unified representation that is independent of the capture system or marker set, making it easy to work with the data regardless of its origin. To obtain motion annotations in natural language, we apply a crowd-sourcing approach and a web-based tool that was specifically build for this purpose, the Motion Annotation Tool. We thoroughly document the annotation process itself and discuss gamification methods that we used to keep annotators motivated. We further propose a novel method, perplexity-based selection, which systematically selects motions for further annotation that are either under-represented in our data set or that have erroneous annotations. We show that our method mitigates the two aforementioned problems and ensures a systematic annotation process. We provide an in-depth analysis of the structure and contents of our resulting data set, which, as of October 10, 2016, contains 3911 motions with a total duration of 11.23 hours and 6278 annotations in natural language that contain 52,903 words. We believe this makes our data set an excellent choice that enables more transparent and comparable research in this important area.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: A User Interfacementioning

confidence: 99%

The KIT Motion-Language Dataset

2016

View full text Add to dashboard Cite

show abstract

“…Both of the nonmotion data sources could be turned into animations. The motion data sources that we use are behavioral markup language actions from SmartBody, a subset of the CMU Motion Capture Database, and The ICS Action Database . Our action recognition source is The Human Motion Database , and our plain text actions are from The American Time Use Survey …”

Section: Experimentationmentioning

confidence: 99%

ALET: Agents Learning their Environment through Text

Balint

Allbeck

2017

Computer Animation & Virtual

View full text Add to dashboard Cite

For intelligent virtual humans to interact in a rich environment, connections between the usable actions and objects must be defined. For scenarios consisting of hundreds of object types and many actions, having a simulation author create these connections by hand becomes and difficult. This limitation causes the simulation to have only a few object connections, whereas the rest of the objects are static and cannot be acted upon. Automated methods to connect objects to actions are promising but incomplete as they still miss key interactions and are unable to determine important characteristics of each action such as the manner of the action. We present Agents Learning their Environment through Text (ALET) to connect graphical objects to actions and provide an understanding of the actions. Observing that text contains descriptions of actions and connections to objects, ALET leverages large text corpora, and knowledge bases to provide candidate connections and descriptions for the actions and objects available in a simulation. The candidate connections and descriptions populate a representation that describes the graphical models and animations. We test ALET against other semantic generation methods, and find it more accurately determines object roles in actions, as well as determines semantic information about the action. KEYWORDS autonomous actors, intelligent virtual humans, semantic virtual environmentsComput Anim Virtual Worlds. 2017;28:e1759.wileyonlinelibrary.com/journal/cav

show abstract

“…Another suitable route for pHRI is the imitation learning approach, justified by a wide variety of computational algorithms that have been recently developed [see an exhaustive overview in Schaal et al (2003)]. This approach yields to the teacher-student concept and consists in (i) collecting movements of a human agent (i.e., the teacher in the imitation process), gathered by motion capture techniques and clustered in motion databases (Guerra-Filho and Biswas 2011;Kuehne et al 2011;Mandery et al 2015;Wojtusch and Stryk 2015); (ii) classifying motions as a set of primitive actions (i.e., motion primitives) for model abstraction (Kulic et al 2008); (iii) mapping human models into a robot platform, i.e., the student in the imitation process. The retargeting implies the development of robot control algorithms capable of learning motion models from these primitives (Amor et al 2014;Terlemez et al 2014;Mandery et al 2016) in order to emulate human-like movements.…”

Section: Introductionmentioning

confidence: 99%

Towards real-time whole-body human dynamics estimation through probabilistic sensor fusion algorithms

et al. 2018

View full text Add to dashboard Cite

Physical human-robot interaction is receiving a growing attention from the scientific community. One of the main challenges is to understand the principles governing the mutual behaviour during collaborative interactions between humans. In this context, the knowledge of human whole-body motion and forces plays a pivotal role. Current state of the art methods, however, do not allow one for reliable estimations of the human dynamics during physical human-robot interaction. This paper builds upon our former work on human dynamics estimation by proposing a probabilistic framework and an estimation tool for online monitoring of the human dynamics during human-robot collaboration tasks. The soundness of the proposed approach is verified in human-robot collaboration experiments and the results show that our probabilistic framework is able to estimate the human dynamic, thereby laying the foundation for more complex collaboration scenarios.

show abstract

The human motion database: A cognitive and parametric sampling of human motion

Cited by 19 publications

References 7 publications

The KIT Motion-Language Dataset

The KIT Motion-Language Dataset

ALET: Agents Learning their Environment through Text

Towards real-time whole-body human dynamics estimation through probabilistic sensor fusion algorithms

Contact Info

Product

Resources

About