Header logo is


2019


no image
Hierarchical Task-Parameterized Learning from Demonstration for Collaborative Object Movement

Hu, S., Kuchenbecker, K. J.

Applied Bionics and Biomechanics, (9765383), December 2019 (article)

Abstract
Learning from demonstration (LfD) enables a robot to emulate natural human movement instead of merely executing preprogrammed behaviors. This article presents a hierarchical LfD structure of task-parameterized models for object movement tasks, which are ubiquitous in everyday life and could benefit from robotic support. Our approach uses the task-parameterized Gaussian mixture model (TP-GMM) algorithm to encode sets of demonstrations in separate models that each correspond to a different task situation. The robot then maximizes its expected performance in a new situation by either selecting a good existing model or requesting new demonstrations. Compared to a standard implementation that encodes all demonstrations together for all test situations, the proposed approach offers four advantages. First, a simply defined distance function can be used to estimate test performance by calculating the similarity between a test situation and the existing models. Second, the proposed approach can improve generalization, e.g., better satisfying the demonstrated task constraints and speeding up task execution. Third, because the hierarchical structure encodes each demonstrated situation individually, a wider range of task situations can be modeled in the same framework without deteriorating performance. Last, adding or removing demonstrations incurs low computational load, and thus, the robot’s skill library can be built incrementally. We first instantiate the proposed approach in a simulated task to validate these advantages. We then show that the advantages transfer to real hardware for a task where naive participants collaborated with a Willow Garage PR2 robot to move a handheld object. For most tested scenarios, our hierarchical method achieved significantly better task performance and subjective ratings than both a passive model with only gravity compensation and a single TP-GMM encoding all demonstrations.

hi

DOI [BibTex]


Decoding subcategories of human bodies from both body- and face-responsive cortical regions
Decoding subcategories of human bodies from both body- and face-responsive cortical regions

Foster, C., Zhao, M., Romero, J., Black, M. J., Mohler, B. J., Bartels, A., Bülthoff, I.

NeuroImage, 202(15):116085, November 2019 (article)

Abstract
Our visual system can easily categorize objects (e.g. faces vs. bodies) and further differentiate them into subcategories (e.g. male vs. female). This ability is particularly important for objects of social significance, such as human faces and bodies. While many studies have demonstrated category selectivity to faces and bodies in the brain, how subcategories of faces and bodies are represented remains unclear. Here, we investigated how the brain encodes two prominent subcategories shared by both faces and bodies, sex and weight, and whether neural responses to these subcategories rely on low-level visual, high-level visual or semantic similarity. We recorded brain activity with fMRI while participants viewed faces and bodies that varied in sex, weight, and image size. The results showed that the sex of bodies can be decoded from both body- and face-responsive brain areas, with the former exhibiting more consistent size-invariant decoding than the latter. Body weight could also be decoded in face-responsive areas and in distributed body-responsive areas, and this decoding was also invariant to image size. The weight of faces could be decoded from the fusiform body area (FBA), and weight could be decoded across face and body stimuli in the extrastriate body area (EBA) and a distributed body-responsive area. The sex of well-controlled faces (e.g. excluding hairstyles) could not be decoded from face- or body-responsive regions. These results demonstrate that both face- and body-responsive brain regions encode information that can distinguish the sex and weight of bodies. Moreover, the neural patterns corresponding to sex and weight were invariant to image size and could sometimes generalize across face and body stimuli, suggesting that such subcategorical information is encoded with a high-level visual or semantic code.

ps

paper pdf DOI [BibTex]

paper pdf DOI [BibTex]


Active Perception based Formation Control for Multiple Aerial Vehicles
Active Perception based Formation Control for Multiple Aerial Vehicles

Tallamraju, R., Price, E., Ludwig, R., Karlapalem, K., Bülthoff, H. H., Black, M. J., Ahmad, A.

IEEE Robotics and Automation Letters, Robotics and Automation Letters, 4(4):4491-4498, IEEE, October 2019 (article)

Abstract
We present a novel robotic front-end for autonomous aerial motion-capture (mocap) in outdoor environments. In previous work, we presented an approach for cooperative detection and tracking (CDT) of a subject using multiple micro-aerial vehicles (MAVs). However, it did not ensure optimal view-point configurations of the MAVs to minimize the uncertainty in the person's cooperatively tracked 3D position estimate. In this article, we introduce an active approach for CDT. In contrast to cooperatively tracking only the 3D positions of the person, the MAVs can actively compute optimal local motion plans, resulting in optimal view-point configurations, which minimize the uncertainty in the tracked estimate. We achieve this by decoupling the goal of active tracking into a quadratic objective and non-convex constraints corresponding to angular configurations of the MAVs w.r.t. the person. We derive this decoupling using Gaussian observation model assumptions within the CDT algorithm. We preserve convexity in optimization by embedding all the non-convex constraints, including those for dynamic obstacle avoidance, as external control inputs in the MPC dynamics. Multiple real robot experiments and comparisons involving 3 MAVs in several challenging scenarios are presented.

ps

pdf DOI Project Page [BibTex]

pdf DOI Project Page [BibTex]


no image
Decoding the Viewpoint and Identity of Faces and Bodies

Foster, C., Zhao, M., Bolkart, T., Black, M., Bartels, A., Bülthoff, I.

Journal of Vision, 19(10): 54c, pages: 54-55, Arvo Journals, September 2019 (article)

Abstract
(2019). . , 19(10): 25.13, 54-55. doi: Zitierlink: http://hdl.handle.net/21.11116/0000-0003-7493-4

ps

link (url) DOI [BibTex]

link (url) DOI [BibTex]


no image
Low-Hysteresis and Low-Interference Soft Tactile Sensor Using a Conductive Coated Porous Elastomer and a Structure for Interference Reduction

Park, K., Kim, S., Lee, H., Park, I., Kim, J.

Sensors and Actuators A: Physical, 295, pages: 541-550, August 2019 (article)

Abstract
The need for soft whole-body tactile sensors is emerging. Piezoresistive materials are advantageous in terms of making large tactile sensors, but the hysteresis of piezoresistive materials is a major drawback. The hysteresis of a piezoresistive material should be attenuated to make a practical piezoresistive soft tactile sensor. In this paper, we introduce a low-hysteresis and low-interference soft tactile sensor using a conductive coated porous elastomer and a structure to reduce interference (grooves). The developed sensor exhibits low hysteresis because the transduction mechanism of the sensor is dominated by the contact between the conductive coated surface. In a cyclic loading experiment with different loading frequencies, the mechanical and piezoresistive hysteresis values of the sensor are less than 21.7% and 6.8%, respectively. The initial resistance change is found to be within 4% after the first loading cycle. To reduce the interference among the sensing points, we also propose a structure where the grooves are inserted between the adjacent electrodes. This structure is implemented during the molding process, which is adopted to extend the porous tactile sensor to large-scale and facile fabrication. The effects of the structure are investigated with respect to the normalized design parameters ΘD, ΘW, and ΘT in a simulation, and the result is validated for samples with the same design parameters. An indentation experiment also shows that the structure designed for interference reduction effectively attenuates the interference of the sensor array, indicating that the spatial resolution of the sensor array is improved. As a result, the sensor can exhibit low hysteresis and low interference simultaneously. This research can be used for many applications, such as robotic skin, grippers, and wearable devices.

hi

DOI [BibTex]

DOI [BibTex]


no image
Physical activity in non-ambulatory toddlers with cerebral palsy

M.Orlando, J., Pierce, S., Mohan, M., Skorup, J., Paremski, A., Bochnak, M., Prosser, L. A.

Research in Developmental Disabilities, 90, pages: 51-58, July 2019 (article)

Abstract
Background: Children with cerebral palsy are less likely to be physically active than their peers, however there is limited evidence regarding self-initiated physical activity in toddlers who are not able, or who may never be able, to walk. Aims: The aim of this study was to measure self-initiated physical activity and its relationship to gross motor function and participation in non-ambulatory toddlers with cerebral palsy. Methods and procedures: Participants were between the ages of 1–3 years. Physical activity during independent floor-play at home was recorded using a wearable tri-axial accelerometer worn on the child’s thigh. The Gross Motor Function Measure-66 and the Child Engagement in Daily Life, a parent-reported questionnaire of participation, were administered. Outcomes and results: Data were analyzed from the twenty participants who recorded at least 90 min of floor-play (mean: 229 min), resulting in 4598 total floor-play minutes. The relationship between physical activity and gross motor function was not statistically significant (r = 0.20; p = 0.39), nor were the relationships between physical activity and participation (r = 0.05−0.09; p = 0.71−0.84). Conclusions and implications: The results suggest physical activity during floor-play is not related to gross motor function or participation in non-ambulatory toddlers with cerebral palsy. Clinicians and researchers should independently measure physical activity, gross motor function, and participation.

hi

DOI [BibTex]

DOI [BibTex]


Implementation of a 6-{DOF} Parallel Continuum Manipulator for Delivering Fingertip Tactile Cues
Implementation of a 6-DOF Parallel Continuum Manipulator for Delivering Fingertip Tactile Cues

Young, E. M., Kuchenbecker, K. J.

IEEE Transactions on Haptics, 12(3):295-306, June 2019 (article)

Abstract
Existing fingertip haptic devices can deliver different subsets of tactile cues in a compact package, but we have not yet seen a wearable six-degree-of-freedom (6-DOF) display. This paper presents the Fuppeteer (short for Fingertip Puppeteer), a device that is capable of controlling the position and orientation of a flat platform, such that any combination of normal and shear force can be delivered at any location on any human fingertip. We build on our previous work of designing a parallel continuum manipulator for fingertip haptics by presenting a motorized version in which six flexible Nitinol wires are actuated via independent roller mechanisms and proportional-derivative controllers. We evaluate the settling time and end-effector vibrations observed during system responses to step inputs. After creating a six-dimensional lookup table and adjusting simulated inputs using measured Jacobians, we show that the device can make contact with all parts of the fingertip with a mean error of 1.42 mm. Finally, we present results from a human-subject study. A total of 24 users discerned 9 evenly distributed contact locations with an average accuracy of 80.5%. Translational and rotational shear cues were identified reasonably well near the center of the fingertip and more poorly around the edges.

hi

DOI Project Page [BibTex]


no image
How Does It Feel to Clap Hands with a Robot?

Fitter, N. T., Kuchenbecker, K. J.

International Journal of Social Robotics, 12(1):113-127, April 2019 (article)

Abstract
Future robots may need lighthearted physical interaction capabilities to connect with people in meaningful ways. To begin exploring how users perceive playful human–robot hand-to-hand interaction, we conducted a study with 20 participants. Each user played simple hand-clapping games with the Rethink Robotics Baxter Research Robot during a 1-h-long session involving 24 randomly ordered conditions that varied in facial reactivity, physical reactivity, arm stiffness, and clapping tempo. Survey data and experiment recordings demonstrate that this interaction is viable: all users successfully completed the experiment and mentioned enjoying at least one game without prompting. Hand-clapping tempo was highly salient to users, and human-like robot errors were more widely accepted than mechanical errors. Furthermore, perceptions of Baxter varied in the following statistically significant ways: facial reactivity increased the robot’s perceived pleasantness and energeticness; physical reactivity decreased pleasantness, energeticness, and dominance; higher arm stiffness increased safety and decreased dominance; and faster tempo increased energeticness and increased dominance. These findings can motivate and guide roboticists who want to design social–physical human–robot interactions.

hi

DOI [BibTex]

DOI [BibTex]


 Perceptual Effects of Inconsistency in Human Animations
Perceptual Effects of Inconsistency in Human Animations

Kenny, S., Mahmood, N., Honda, C., Black, M. J., Troje, N. F.

ACM Trans. Appl. Percept., 16(1):2:1-2:18, Febuary 2019 (article)

Abstract
The individual shape of the human body, including the geometry of its articulated structure and the distribution of weight over that structure, influences the kinematics of a person’s movements. How sensitive is the visual system to inconsistencies between shape and motion introduced by retargeting motion from one person onto the shape of another? We used optical motion capture to record five pairs of male performers with large differences in body weight, while they pushed, lifted, and threw objects. From these data, we estimated both the kinematics of the actions as well as the performer’s individual body shape. To obtain consistent and inconsistent stimuli, we created animated avatars by combining the shape and motion estimates from either a single performer or from different performers. Using these stimuli we conducted three experiments in an immersive virtual reality environment. First, a group of participants detected which of two stimuli was inconsistent. Performance was very low, and results were only marginally significant. Next, a second group of participants rated perceived attractiveness, eeriness, and humanness of consistent and inconsistent stimuli, but these judgements of animation characteristics were not affected by consistency of the stimuli. Finally, a third group of participants rated properties of the objects rather than of the performers. Here, we found strong influences of shape-motion inconsistency on perceived weight and thrown distance of objects. This suggests that the visual system relies on its knowledge of shape and motion and that these components are assimilated into an altered perception of the action outcome. We propose that the visual system attempts to resist inconsistent interpretations of human animations. Actions involving object manipulations present an opportunity for the visual system to reinterpret the introduced inconsistencies as a change in the dynamics of an object rather than as an unexpected combination of body shape and body motion.

ps

publisher pdf DOI [BibTex]

publisher pdf DOI [BibTex]


no image
Self and Body Part Localization in Virtual Reality: Comparing a Headset and a Large-Screen Immersive Display

van der Veer, A. H., Longo, M. R., Alsmith, A. J. T., Wong, H. Y., Mohler, B. J.

Frontiers in Robotics and AI, 6(33), 2019 (article)

ps

DOI [BibTex]

DOI [BibTex]


The Virtual Caliper: Rapid Creation of Metrically Accurate Avatars from {3D} Measurements
The Virtual Caliper: Rapid Creation of Metrically Accurate Avatars from 3D Measurements

Pujades, S., Mohler, B., Thaler, A., Tesch, J., Mahmood, N., Hesse, N., Bülthoff, H. H., Black, M. J.

IEEE Transactions on Visualization and Computer Graphics, 25(5):1887-1897, IEEE, 2019 (article)

Abstract
Creating metrically accurate avatars is important for many applications such as virtual clothing try-on, ergonomics, medicine, immersive social media, telepresence, and gaming. Creating avatars that precisely represent a particular individual is challenging however, due to the need for expensive 3D scanners, privacy issues with photographs or videos, and difficulty in making accurate tailoring measurements. We overcome these challenges by creating “The Virtual Caliper”, which uses VR game controllers to make simple measurements. First, we establish what body measurements users can reliably make on their own body. We find several distance measurements to be good candidates and then verify that these are linearly related to 3D body shape as represented by the SMPL body model. The Virtual Caliper enables novice users to accurately measure themselves and create an avatar with their own body shape. We evaluate the metric accuracy relative to ground truth 3D body scan data, compare the method quantitatively to other avatar creation tools, and perform extensive perceptual studies. We also provide a software application to the community that enables novices to rapidly create avatars in fewer than five minutes. Not only is our approach more rapid than existing methods, it exports a metrically accurate 3D avatar model that is rigged and skinned.

ps

Project Page IEEE Open Access IEEE Open Access PDF DOI [BibTex]

Project Page IEEE Open Access IEEE Open Access PDF DOI [BibTex]

2013


Branch\&Rank for Efficient Object Detection
Branch&Rank for Efficient Object Detection

Lehmann, A., Gehler, P., VanGool, L.

International Journal of Computer Vision, Springer, December 2013 (article)

Abstract
Ranking hypothesis sets is a powerful concept for efficient object detection. In this work, we propose a branch&rank scheme that detects objects with often less than 100 ranking operations. This efficiency enables the use of strong and also costly classifiers like non-linear SVMs with RBF-TeX kernels. We thereby relieve an inherent limitation of branch&bound methods as bounds are often not tight enough to be effective in practice. Our approach features three key components: a ranking function that operates on sets of hypotheses and a grouping of these into different tasks. Detection efficiency results from adaptively sub-dividing the object search space into decreasingly smaller sets. This is inherited from branch&bound, while the ranking function supersedes a tight bound which is often unavailable (except for rather limited function classes). The grouping makes the system effective: it separates image classification from object recognition, yet combines them in a single formulation, phrased as a structured SVM problem. A novel aspect of branch&rank is that a better ranking function is expected to decrease the number of classifier calls during detection. We use the VOC’07 dataset to demonstrate the algorithmic properties of branch&rank.

ps

pdf link (url) [BibTex]

2013


pdf link (url) [BibTex]


Extracting Postural Synergies for Robotic Grasping
Extracting Postural Synergies for Robotic Grasping

Romero, J., Feix, T., Ek, C., Kjellstrom, H., Kragic, D.

Robotics, IEEE Transactions on, 29(6):1342-1352, December 2013 (article)

ps

[BibTex]

[BibTex]


Markov Random Field Modeling, Inference & Learning in Computer Vision & Image Understanding: A Survey
Markov Random Field Modeling, Inference & Learning in Computer Vision & Image Understanding: A Survey

Wang, C., Komodakis, N., Paragios, N.

Computer Vision and Image Understanding (CVIU), 117(11):1610-1627, November 2013 (article)

Abstract
In this paper, we present a comprehensive survey of Markov Random Fields (MRFs) in computer vision and image understanding, with respect to the modeling, the inference and the learning. While MRFs were introduced into the computer vision field about two decades ago, they started to become a ubiquitous tool for solving visual perception problems around the turn of the millennium following the emergence of efficient inference methods. During the past decade, a variety of MRF models as well as inference and learning methods have been developed for addressing numerous low, mid and high-level vision problems. While most of the literature concerns pairwise MRFs, in recent years we have also witnessed significant progress in higher-order MRFs, which substantially enhances the expressiveness of graph-based models and expands the domain of solvable problems. This survey provides a compact and informative summary of the major literature in this research topic.

ps

Publishers site pdf [BibTex]

Publishers site pdf [BibTex]


Vision meets Robotics: The {KITTI} Dataset
Vision meets Robotics: The KITTI Dataset

Geiger, A., Lenz, P., Stiller, C., Urtasun, R.

International Journal of Robotics Research, 32(11):1231 - 1237 , Sage Publishing, September 2013 (article)

Abstract
We present a novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research. In total, we recorded 6 hours of traffic scenarios at 10-100 Hz using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras, a Velodyne 3D laser scanner and a high-precision GPS/IMU inertial navigation system. The scenarios are diverse, capturing real-world traffic situations and range from freeways over rural areas to inner-city scenes with many static and dynamic objects. Our data is calibrated, synchronized and timestamped, and we provide the rectified and raw image sequences. Our dataset also contains object labels in the form of 3D tracklets and we provide online benchmarks for stereo, optical flow, object detection and other tasks. This paper describes our recording platform, the data format and the utilities that we provide.

avg ps

pdf DOI [BibTex]

pdf DOI [BibTex]


Unscented Kalman Filtering on Riemannian Manifolds
Unscented Kalman Filtering on Riemannian Manifolds

Soren Hauberg, Francois Lauze, Kim S. Pedersen

Journal of Mathematical Imaging and Vision, 46(1):103-120, Springer Netherlands, May 2013 (article)

ps

Publishers site PDF [BibTex]

Publishers site PDF [BibTex]


Quasi-Newton Methods: A New Direction
Quasi-Newton Methods: A New Direction

Hennig, P., Kiefel, M.

Journal of Machine Learning Research, 14(1):843-865, March 2013 (article)

Abstract
Four decades after their invention, quasi-Newton methods are still state of the art in unconstrained numerical optimization. Although not usually interpreted thus, these are learning algorithms that fit a local quadratic approximation to the objective function. We show that many, including the most popular, quasi-Newton methods can be interpreted as approximations of Bayesian linear regression under varying prior assumptions. This new notion elucidates some shortcomings of classical algorithms, and lights the way to a novel nonparametric quasi-Newton method, which is able to make more efficient use of available information at computational cost similar to its predecessors.

ei ps pn

website+code pdf link (url) [BibTex]

website+code pdf link (url) [BibTex]


Random Forests for Real Time {3D} Face Analysis
Random Forests for Real Time 3D Face Analysis

Fanelli, G., Dantone, M., Gall, J., Fossati, A., van Gool, L.

International Journal of Computer Vision, 101(3):437-458, Springer, 2013 (article)

Abstract
We present a random forest-based framework for real time head pose estimation from depth images and extend it to localize a set of facial features in 3D. Our algorithm takes a voting approach, where each patch extracted from the depth image can directly cast a vote for the head pose or each of the facial features. Our system proves capable of handling large rotations, partial occlusions, and the noisy depth data acquired using commercial sensors. Moreover, the algorithm works on each frame independently and achieves real time performance without resorting to parallel computations on a GPU. We present extensive experiments on publicly available, challenging datasets and present a new annotated head pose database recorded using a Microsoft Kinect.

ps

data and code publisher's site pdf DOI Project Page [BibTex]

data and code publisher's site pdf DOI Project Page [BibTex]


Markerless Motion Capture of Multiple Characters Using Multi-view Image Segmentation
Markerless Motion Capture of Multiple Characters Using Multi-view Image Segmentation

Liu, Y., Gall, J., Stoll, C., Dai, Q., Seidel, H., Theobalt, C.

Transactions on Pattern Analysis and Machine Intelligence, 35(11):2720-2735, 2013 (article)

Abstract
Capturing the skeleton motion and detailed time-varying surface geometry of multiple, closely interacting peoples is a very challenging task, even in a multicamera setup, due to frequent occlusions and ambiguities in feature-to-person assignments. To address this task, we propose a framework that exploits multiview image segmentation. To this end, a probabilistic shape and appearance model is employed to segment the input images and to assign each pixel uniquely to one person. Given the articulated template models of each person and the labeled pixels, a combined optimization scheme, which splits the skeleton pose optimization problem into a local one and a lower dimensional global one, is applied one by one to each individual, followed with surface estimation to capture detailed nonrigid deformations. We show on various sequences that our approach can capture the 3D motion of humans accurately even if they move rapidly, if they wear wide apparel, and if they are engaged in challenging multiperson motions, including dancing, wrestling, and hugging.

ps

data and video pdf DOI Project Page [BibTex]

data and video pdf DOI Project Page [BibTex]


Viewpoint and pose in body-form adaptation
Viewpoint and pose in body-form adaptation

Sekunova, A., Black, M., Parkinson, L., Barton, J. J. S.

Perception, 42(2):176-186, 2013 (article)

Abstract
Faces and bodies are complex structures, perception of which can play important roles in person identification and inference of emotional state. Face representations have been explored using behavioural adaptation: in particular, studies have shown that face aftereffects show relatively broad tuning for viewpoint, consistent with origin in a high-level structural descriptor far removed from the retinal image. Our goals were to determine first, if body aftereffects also showed a degree of viewpoint invariance, and second if they also showed pose invariance, given that changes in pose create even more dramatic changes in the 2-D retinal image. We used a 3-D model of the human body to generate headless body images, whose parameters could be varied to generate different body forms, viewpoints, and poses. In the first experiment, subjects adapted to varying viewpoints of either slim or heavy bodies in a neutral stance, followed by test stimuli that were all front-facing. In the second experiment, we used the same front-facing bodies in neutral stance as test stimuli, but compared adaptation from bodies in the same neutral stance to adaptation with the same bodies in different poses. We found that body aftereffects were obtained over substantial viewpoint changes, with no significant decline in aftereffect magnitude with increasing viewpoint difference between adapting and test images. Aftereffects also showed transfer across one change in pose but not across another. We conclude that body representations may have more viewpoint invariance than faces, and demonstrate at least some transfer across pose, consistent with a high-level structural description. Keywords: aftereffect, shape, face, representation

ps

pdf from publisher abstract pdf link (url) Project Page [BibTex]

pdf from publisher abstract pdf link (url) Project Page [BibTex]


Non-parametric hand pose estimation with object context
Non-parametric hand pose estimation with object context

Romero, J., Kjellström, H., Ek, C. H., Kragic, D.

Image and Vision Computing , 31(8):555 - 564, 2013 (article)

Abstract
In the spirit of recent work on contextual recognition and estimation, we present a method for estimating the pose of human hands, employing information about the shape of the object in the hand. Despite the fact that most 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. Occlusion of the hand from grasped objects does in fact often pose a severe challenge to the estimation of hand pose. In the presented method, object occlusion is not only compensated for, it contributes to the pose estimation in a contextual fashion; this without an explicit model of object shape. Our hand tracking method is non-parametric, performing a nearest neighbor search in a large database (.. entries) of hand poses with and without grasped objects. The system that operates in real time, is robust to self occlusions, object occlusions and segmentation errors, and provides full hand pose reconstruction from monocular video. Temporal consistency in hand pose is taken into account, without explicitly tracking the hand in the high-dim pose space. Experiments show the non-parametric method to outperform other state of the art regression methods, while operating at a significantly lower computational cost than comparable model-based hand tracking methods.

ps

Publisher site pdf link (url) [BibTex]

Publisher site pdf link (url) [BibTex]