3D Hand Trajectory Segmentation by Curvatures and Hand Orientation for Classification through a Probabilistic Approach

Diego R. Faria, Jorge Dias

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this work we present the segmentation and classification of 3D hand trajectory. Curvatures features are acquired by (r, θ, h) and the hand orientation is acquired by approximating the hand plane in 3D space. The 3D positions of the hand movement are acquired by markers of a magnetic tracking system [6]. Observing humans movements we perform a learning phase using histogram techniques. Based on the learning phase is possible classify reach-to-grasp movements applying Bayes rule to recognize the way that a human grasps an object by continuous classification based on multiplicative updates of beliefs. We are classifying the hand trajectory by its curvatures and by hand orientation along the trajectory individually. Both results are compared after some trials to verify the best classification between these two kinds of segmentation. Using entropy as confidence level, we can give weights for each kind of classification to combine both, acquiring a new classification for results comparison. Using these techniques we developed an application to estimate and classify two possible types of grasping by the reach-to-grasp movements performed by humans. These reported steps are important to understand some human behaviors before the object manipulation and can be used to endow a robot with autonomous capabilities (e.g. reaching objects for handling).
Original languageEnglish
Title of host publication2009 IEEE/RSJ International Conference on Intelligent Robots and Systems
PublisherIEEE
Pages1284-1289
Number of pages6
DOIs
Publication statusPublished - 15 Dec 2009
EventIEEE/RSJ International Conference on Intelligent Robots and Systems, 2009. - St. Louis, United States
Duration: 10 Oct 200915 Oct 2009

Conference

ConferenceIEEE/RSJ International Conference on Intelligent Robots and Systems, 2009.
Abbreviated titleIROS 2009.
CountryUnited States
CitySt. Louis
Period10/10/0915/10/09

Fingerprint

Trajectories
Entropy
Robots

Cite this

Faria, D. R., & Dias, J. (2009). 3D Hand Trajectory Segmentation by Curvatures and Hand Orientation for Classification through a Probabilistic Approach. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 1284-1289). IEEE. https://doi.org/10.1109/IROS.2009.5354792
Faria, Diego R. ; Dias, Jorge. / 3D Hand Trajectory Segmentation by Curvatures and Hand Orientation for Classification through a Probabilistic Approach. 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 2009. pp. 1284-1289
@inproceedings{fb532474e044439b8562c706175d536e,
title = "3D Hand Trajectory Segmentation by Curvatures and Hand Orientation for Classification through a Probabilistic Approach",
abstract = "In this work we present the segmentation and classification of 3D hand trajectory. Curvatures features are acquired by (r, θ, h) and the hand orientation is acquired by approximating the hand plane in 3D space. The 3D positions of the hand movement are acquired by markers of a magnetic tracking system [6]. Observing humans movements we perform a learning phase using histogram techniques. Based on the learning phase is possible classify reach-to-grasp movements applying Bayes rule to recognize the way that a human grasps an object by continuous classification based on multiplicative updates of beliefs. We are classifying the hand trajectory by its curvatures and by hand orientation along the trajectory individually. Both results are compared after some trials to verify the best classification between these two kinds of segmentation. Using entropy as confidence level, we can give weights for each kind of classification to combine both, acquiring a new classification for results comparison. Using these techniques we developed an application to estimate and classify two possible types of grasping by the reach-to-grasp movements performed by humans. These reported steps are important to understand some human behaviors before the object manipulation and can be used to endow a robot with autonomous capabilities (e.g. reaching objects for handling).",
author = "Faria, {Diego R.} and Jorge Dias",
year = "2009",
month = "12",
day = "15",
doi = "10.1109/IROS.2009.5354792",
language = "English",
pages = "1284--1289",
booktitle = "2009 IEEE/RSJ International Conference on Intelligent Robots and Systems",
publisher = "IEEE",
address = "United States",

}

Faria, DR & Dias, J 2009, 3D Hand Trajectory Segmentation by Curvatures and Hand Orientation for Classification through a Probabilistic Approach. in 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, pp. 1284-1289, IEEE/RSJ International Conference on Intelligent Robots and Systems, 2009. , St. Louis, United States, 10/10/09. https://doi.org/10.1109/IROS.2009.5354792

3D Hand Trajectory Segmentation by Curvatures and Hand Orientation for Classification through a Probabilistic Approach. / Faria, Diego R.; Dias, Jorge.

2009 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE, 2009. p. 1284-1289.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - 3D Hand Trajectory Segmentation by Curvatures and Hand Orientation for Classification through a Probabilistic Approach

AU - Faria, Diego R.

AU - Dias, Jorge

PY - 2009/12/15

Y1 - 2009/12/15

N2 - In this work we present the segmentation and classification of 3D hand trajectory. Curvatures features are acquired by (r, θ, h) and the hand orientation is acquired by approximating the hand plane in 3D space. The 3D positions of the hand movement are acquired by markers of a magnetic tracking system [6]. Observing humans movements we perform a learning phase using histogram techniques. Based on the learning phase is possible classify reach-to-grasp movements applying Bayes rule to recognize the way that a human grasps an object by continuous classification based on multiplicative updates of beliefs. We are classifying the hand trajectory by its curvatures and by hand orientation along the trajectory individually. Both results are compared after some trials to verify the best classification between these two kinds of segmentation. Using entropy as confidence level, we can give weights for each kind of classification to combine both, acquiring a new classification for results comparison. Using these techniques we developed an application to estimate and classify two possible types of grasping by the reach-to-grasp movements performed by humans. These reported steps are important to understand some human behaviors before the object manipulation and can be used to endow a robot with autonomous capabilities (e.g. reaching objects for handling).

AB - In this work we present the segmentation and classification of 3D hand trajectory. Curvatures features are acquired by (r, θ, h) and the hand orientation is acquired by approximating the hand plane in 3D space. The 3D positions of the hand movement are acquired by markers of a magnetic tracking system [6]. Observing humans movements we perform a learning phase using histogram techniques. Based on the learning phase is possible classify reach-to-grasp movements applying Bayes rule to recognize the way that a human grasps an object by continuous classification based on multiplicative updates of beliefs. We are classifying the hand trajectory by its curvatures and by hand orientation along the trajectory individually. Both results are compared after some trials to verify the best classification between these two kinds of segmentation. Using entropy as confidence level, we can give weights for each kind of classification to combine both, acquiring a new classification for results comparison. Using these techniques we developed an application to estimate and classify two possible types of grasping by the reach-to-grasp movements performed by humans. These reported steps are important to understand some human behaviors before the object manipulation and can be used to endow a robot with autonomous capabilities (e.g. reaching objects for handling).

UR - http://ieeexplore.ieee.org/document/5354792/

U2 - 10.1109/IROS.2009.5354792

DO - 10.1109/IROS.2009.5354792

M3 - Conference contribution

SP - 1284

EP - 1289

BT - 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems

PB - IEEE

ER -

Faria DR, Dias J. 3D Hand Trajectory Segmentation by Curvatures and Hand Orientation for Classification through a Probabilistic Approach. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems. IEEE. 2009. p. 1284-1289 https://doi.org/10.1109/IROS.2009.5354792