Results 1 - 10
of
11
Tracking the Articulated Motion of Two Strongly Interacting Hands
"... We propose a method that relies on markerless visual observations to track the full articulation of two hands that interact with each-other in a complex, unconstrained manner. We formulate this as an optimization problem whose 54dimensional parameter space represents all possible configurations of t ..."
Abstract
-
Cited by 31 (4 self)
- Add to MetaCart
(Show Context)
We propose a method that relies on markerless visual observations to track the full articulation of two hands that interact with each-other in a complex, unconstrained manner. We formulate this as an optimization problem whose 54dimensional parameter space represents all possible configurations of two hands, each represented as a kinematic structure with 26 Degrees of Freedom (DoFs). To solve this problem, we employ Particle Swarm Optimization (PSO), an evolutionary, stochastic optimization method with the objective of finding the two-hands configuration that best explains observations provided by an RGB-D sensor. To the best of our knowledge, the proposed method is the first to attempt and achieve the articulated motion tracking of two strongly interacting hands. Extensive quantitative and qualitative experiments with simulated and real world image sequences demonstrate that an accurate and efficient solution of this problem is indeed feasible. 1.
Hands in action: real-time 3D reconstruction of hands in interaction with objects
- In IEEE ICRA
, 2010
"... Abstract-This paper presents a method for vision based estimation of the pose of human hands in interaction with objects. Despite the fact that most robotics applications of human hand tracking involve grasping and manipulation of objects, the majority of methods in the literature assume a free han ..."
Abstract
-
Cited by 21 (6 self)
- Add to MetaCart
(Show Context)
Abstract-This paper presents a method for vision based estimation of the pose of human hands in interaction with objects. Despite the fact that most robotics applications of human hand tracking involve grasping and manipulation of objects, the majority of methods in the literature assume a free hand, isolated from the surrounding environment. Our hand tracking method is non-parametric, performing a nearest neighbor search in a large database (100000 entries) of hand poses with and without grasped objects. The system operates in real time, it is robust to self occlusions, object occlusions and segmentation errors, and provides full hand pose reconstruction from markerless video. Temporal consistency in hand pose is taken into account, without explicitly tracking the hand in the high dimensional pose space.
Non-Parametric Hand Pose Estimation with Object Context
, 2013
"... This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. ..."
Abstract
-
Cited by 4 (0 self)
- Add to MetaCart
(Show Context)
This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain. ACCEPTED MANUSCRIPT
Gravity Optimised Particle Filter for Hand Tracking
"... Copyright and reuse: The Warwick Research Archive Portal (WRAP) makes this work by researchers of the University of Warwick available open access under the following conditions. Copyright © and all moral rights to the version of the paper presented here belong to the individual author(s) and/or othe ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Copyright and reuse: The Warwick Research Archive Portal (WRAP) makes this work by researchers of the University of Warwick available open access under the following conditions. Copyright © and all moral rights to the version of the paper presented here belong to the individual author(s) and/or other copyright owners. To the extent reasonable and practicable the material made available in WRAP has been checked for eligibility before being made available. Copies of full items can be used for personal research or study, educational, or not-for-profit purposes without prior permission or charge. Provided that the authors, title and full bibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content is not changed in any way. Publisher’s statement: “NOTICE: this is the author’s version of a work that was accepted for publication in Pattern Recognition. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in
Capturing Hand Motion with an RGB-D Sensor, Fusing a Generative Model with Salient Points **Supplementary Material**
"... For the pose estimation we resort to the widely used Linear Blend Skinning model [4], consisting of a triangular mesh, an underlying kinematic skeleton and a set of skinning weights. A personalized model for a single subject was created with the following rigging process: A detailed triangular mesh ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
For the pose estimation we resort to the widely used Linear Blend Skinning model [4], consisting of a triangular mesh, an underlying kinematic skeleton and a set of skinning weights. A personalized model for a single subject was created with the following rigging process: A detailed triangular mesh of both hands of the subject was created using a commercial 3D scanning solution1. The scanning setup consisted of 5 camera-pods2 placed in proximity to the scanned hand, covering several viewpoints. A 3D mesh was reconstructed with the camera-system’s proprietary software (multi-view stereo), which was further denoised and processed (e.g. hole filling) manually using Meshlab3. The final result was a watertight mesh for each hand consisting of approximately 10.000 vertices. A skeletal structure was manually fitted in each mesh using a custom OpenGL tool and the corresponding skinning weights for each vertex were computed using the open-source4 “Pinocchio ” soft-ware [2]. In our experiments, a single hand consists of 31 revolute joints, i.e. 37 DoF (including 6 DoF for the global rigid motion that models the wrist). Thus, for sequences with two interacting hands we have to estimate all 74 DoF. Figure 1 depicts the mesh, the skeleton and the DoF for the right hand. 2
THING: Introducing a Tablet-based Interaction Technique for Controlling 3D Hand Models
"... Figure 1: THING enables the control of 3D hand models (in blue) by sliding fingers along sliders arranged in a morphologically-consistent pattern on the tablet’s screen. This creates a strong correspondence between user’s input and pose of the controlled hand. Here, the user closes the virtual hand ..."
Abstract
- Add to MetaCart
(Show Context)
Figure 1: THING enables the control of 3D hand models (in blue) by sliding fingers along sliders arranged in a morphologically-consistent pattern on the tablet’s screen. This creates a strong correspondence between user’s input and pose of the controlled hand. Here, the user closes the virtual hand and then points the index finger. The hands of virtual characters are highly complex 3D mod-els that can be tedious and time-consuming to animate with current methods. This paper introduces THING, a novel tablet-based approach that leverages multi-touch interaction for a quick and precise control of a 3D hand’s pose. The flexion/extension and abduction/adduction of the virtual fin-gers can be controlled for each finger individually or for several fingers in parallel through sliding motions on the tablet’s surface. We designed two variants of THING: (1) MobileTHING, which maps the spatial location and orienta-tion of the tablet to that of the virtual hand, and (2) Desk-topTHING, which combines multi-touch controls of fingers with traditional mouse controls for the hand’s global position and orientation. We compared the usability of THING against mouse-only controls and a data glove in two controlled exper-iments. Results show that DesktopTHING was significantly preferred by users while providing performance similar to data gloves. Together, these results could pave the way to the introduction of novel hybrid user interfaces based on tablets and computer mice in future animation pipelines.
Probabilistic detection of pointing directions for human-robot interaction
"... Abstract—Deictic gestures – pointing at things in human-human collaborative tasks – constitute a pervasive, non-verbal way of communication, used e.g. to direct attention towards objects of interest. In a human-robot interactive scenario, in order to delegate tasks from a human to a robot, one of th ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—Deictic gestures – pointing at things in human-human collaborative tasks – constitute a pervasive, non-verbal way of communication, used e.g. to direct attention towards objects of interest. In a human-robot interactive scenario, in order to delegate tasks from a human to a robot, one of the key requirements is to recognize and estimate the pose of the pointing gesture. Standard approaches rely on full-body or partial-body postures to detect the pointing direction. We present a probabilistic, appearance-based object detection framework to detect pointing gestures and robustly estimate the pointing direction. Our method estimates the pointing direction without assuming any human kinematic model. We propose a functional model for pointing which incorporates two types of pointing, finger pointing and tool pointing using an object in hand. We evaluate our method on a new dataset with 9 participants pointing at 10 objects. I.
Article Depth Camera-Based 3D Hand Gesture Controls with Immersive Tactile Feedback for Natural Mid-Air Gesture Interactions
"... sensors ..."
unknown title
"... Abstract—We present a method for articulated hand tracking that relies on visual input acquired by a calibrated multi-camera system. A state-of-the-art result on this problem has been presented in [12]. In that work, hand tracking is formulated as the minimization of an objective function that quant ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract—We present a method for articulated hand tracking that relies on visual input acquired by a calibrated multi-camera system. A state-of-the-art result on this problem has been presented in [12]. In that work, hand tracking is formulated as the minimization of an objective function that quantifies the discrepancy between a hand pose hypothesis and the observations. The objective function treats the observations from each camera view in an independent way. We follow the same general opti-mization framework but we choose to employ the visual hull [10] as the main observation cue, which results from the integration of information from all available views prior to optimization. We investigate the behavior of the resulting method in extensive experiments and in comparison with that of [12]. The obtained results demonstrate that for low levels of noise contamination, regardless of the number of cameras, the two methods perform comparably. The situation changes when noisy observations or as few as two cameras with short baselines are employed. In these cases, the proposed method is more accurate than that of [12]. Thus, the proposed method is preferable in real-world scenarios with noisy observations obtained from easy-to-deploy, stereo camera setups. I.
