Filters








802 Hits in 7.0 sec

Fast and Accurate 3D Hand Pose Estimation via Recurrent Neural Network for Capturing Hand Articulations [article]

Cheol-hwan Yoo, Seo-won Ji, Yong-goo Shin, Seung-wook Kim, and Sung-jea Ko
2020 arXiv   pre-print
3D hand pose estimation from a single depth image plays an important role in computer vision and human-computer interaction.  ...  In this paper, we propose a hierarchically-structured convolutional recurrent neural network (HCRNN) with six branches that estimate the 3D position of the palm and five fingers independently.  ...  Recently, most 3D hand pose estimation methods have been based on convolutional neural networks (CNNs) with a single depth image.  ... 
arXiv:1911.07424v2 fatcat:fakgzjn7o5gh3dimk7gmro2eqe

Fast and Accurate 3D Hand Pose Estimation via Recurrent Neural Network for Capturing Hand Articulations

Cheol-Hwan Yoo, Seo-Won Ji, Yong-Goo Shin, Seung-Wook Kim, Sung-Jea Ko
2020 IEEE Access  
INDEX TERMS 3D hand pose estimation, recurrent neural network, hand articulations.  ...  3D hand pose estimation from a single depth image plays an important role in computer vision and human-computer interaction.  ...  CONCLUSION To design a practical architecture for 3D hand pose estimation, we considered the articulated structure of the hand and proposed an efficient regression network, namely termed HCRNN.  ... 
doi:10.1109/access.2020.3001637 fatcat:7dou6dqnsbhxtlgalfhnhgrlre

Survey on depth and RGB image-based 3D hand shape and pose estimation

Lin Huang, Boshen Zhang, Zhilin Guo, Yang Xiao, Zhiguo Cao, Junsong Yuan
2021 Virtual Reality & Intelligent Hardware  
With the availability of large-scale annotated hand datasets and the rapid developments of deep neural networks (DNNs), numerous DNN-based data-driven methods have been proposed for accurate and rapid  ...  hand shape and pose estimation.  ...  networks for 3D hand pose estimation.  ... 
doi:10.1016/j.vrih.2021.05.002 fatcat:4tbhftt3ira6fporaqlscqhsse

H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions

Bugra Tekin, Federica Bogo, Marc Pollefeys
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Given a single RGB image, our model jointly estimates the 3D hand and object poses, models their interactions, and recognizes the object and action classes with a single feed-forward pass through a neural  ...  The complete model takes as input a sequence of frames and outputs per-frame 3D hand and object pose predictions along with the estimates of object and action categories for the entire sequence.  ...  We compare the results of our Hand + Object network to those of the networks trained only for hand pose estimation and only for object pose estimation in Table 3 .  ... 
doi:10.1109/cvpr.2019.00464 dblp:conf/cvpr/TekinBP19 fatcat:xz7iop75wvdybmqbtyaprvhwru

A Multi-scale Approach to Gesture Detection and Recognition

Natalia Neverova, Christian Wolf, Giulio Paci, Giacomo Sommavilla, Graham W. Taylor, Florian Nebout
2013 2013 IEEE International Conference on Computer Vision Workshops  
Finally, we employ a Recurrent Neural Network for modeling large-scale temporal dependencies, data fusion and ultimately gesture classification.  ...  In our system, each gesture is decomposed into large-scale body motion and local subtle movements such as hand articulation.  ...  a recurrent neural network (RNN) for capturing temporal dependencies and integrating over a time span corresponding to the average duration of a gesture.  ... 
doi:10.1109/iccvw.2013.69 dblp:conf/iccvw/Neverova0PSTN13 fatcat:lerju4ym75bmjjinrwp74iaedi

A Unified Deep Framework for Joint 3D Pose Estimation and Action Recognition from a Single RGB Camera

Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Sergio A Velastin, And Pablo Zegers
2020 Sensors  
A two-stream deep neural network is then designed and trained to map detected 2D keypoints into 3D poses.  ...  3D poses via an image-based intermediate representation and performing action recognition.  ...  A fast and accurate approach of 3D pose estimation from only RGB input is highly desirable.  ... 
doi:10.3390/s20071825 pmid:32218350 pmcid:PMC7180926 fatcat:ilbvk55rcvhx7k2wkvgdgu4fjm

A Survey on 3D Hand Skeleton and Pose Estimation by Convolutional Neural Network

Van-Hung Le, Hung-Cuong Nguyen
2020 Advances in Science, Technology and Engineering Systems  
In this paper, we surveyed studies in which Convolutional Neural Networks (CNNs) were used to estimate the 3D hand pose from data obtained from the cameras (e.g., RGB camera, depth(D) camera, RGB-D camera  ...  Restoring, estimating the fully 3D hand skeleton and pose from the image data of the captured sensors/cameras applied in many applications of computer vision and robotics: human-computer interaction; gesture  ...  The title is "Using the Lie algebra, Lie group to improve the skeleton hand presentation".  ... 
doi:10.25046/aj050418 fatcat:tzpjnmpwtjbh7m6ld3nucyvxia

V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map [article]

Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee
2018 arXiv   pre-print
of keypoints, such as hand or human body joints, via 2D convolutional neural networks (CNNs).  ...  Our system outperforms previous methods in almost all publicly available 3D hand and human pose estimation datasets and placed first in the HANDS 2017 frame-based 3D hand pose estimation challenge.  ...  [16] proposed the viewpointinvariant pose estimation method using CNN and multiple rounds of a recurrent neural network.  ... 
arXiv:1711.07399v3 fatcat:jtp3hizwunglbcn3erid2pavaa

V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map

Ju Yong Chang, Gyeongsik Moon, Kyoung Mu Lee
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
of keypoints, such as hand or human body joints, via 2D convolutional neural networks (CNNs).  ...  Our system outperforms previous methods in almost all publicly available 3D hand and human pose estimation datasets and placed first in the HANDS 2017 frame-based 3D hand pose estimation challenge.  ...  Acknowledgments This work was supported by the Visual Turing Test project (IITP-2017-0-01780) from the Ministry of Science and ICT of Korea.  ... 
doi:10.1109/cvpr.2018.00533 dblp:conf/cvpr/MoonCL18 fatcat:m6kskcckxjhehmuu54l256tsaq

Recent Advances of Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective

Wu Liu, Tao Mei
2022 ACM Computing Surveys  
Especially, we provide insightful analyses for the intrinsic connections and methods evolution from 2D to 3D pose estimation.  ...  Recently, benefiting from the deep learning technologies, a significant amount of research efforts have advanced the monocular human pose estimation both in 2D and 3D areas.  ...  [198] develop a multi-stage convolution network to recurrently optimize the estimated 3D pose.  ... 
doi:10.1145/3524497 fatcat:4pbvntngrnfp7lqhcpjmy7p2fq

Review of constraints on vision-based gesture recognition for human–computer interaction

Biplab Ketan Chakraborty, Debajit Sarma, M.K. Bhuyan, Karl F MacDorman
2018 IET Computer Vision  
The ability of computers to recognize hand gestures visually is essential for progress in human-computer interaction.  ...  of the hand.  ...  Erol et al. [38] (2007) A review of hand pose estimation methods and capturing of the real 3D hand motion in HCI.  ... 
doi:10.1049/iet-cvi.2017.0052 fatcat:fs2l3o27vveqjlanldjmziuudi

Recent Advances in Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective [article]

Wu Liu, Qian Bao, Yu Sun, Tao Mei
2021 arXiv   pre-print
Recently, benefited from the deep learning technologies, a significant amount of research efforts have greatly advanced the monocular human pose estimation both in 2D and 3D areas.  ...  2D and 3D, and the complex multi-person scenarios.  ...  [151] develop a multi-stage convolution network to recurrently optimize the estimated 3D pose.  ... 
arXiv:2104.11536v1 fatcat:tdag2jq2vjdrjekwukm5nu7l6a

Leaving Flatland: Advances in 3D behavioral measurement [article]

Jesse D. Marshall, Tianqing Li, Joshua H. Wu, Timothy W. Dunn
2021 arXiv   pre-print
Existing 3D measurement techniques draw on specialized hardware, such as motion capture or depth cameras, as well as deep multi-view and monocular computer vision.  ...  natural, occlusive environments. 3D behavioral measurement enables unique applications in phenotyping, investigating the neural basis of behavior, and designing artificial agents capable of imitating animal  ...  Finally, task-optimized recurrent neural networks have proven to be an important model of the motor system, in particular for 3D arm reaching [122, 123] .  ... 
arXiv:2112.01987v1 fatcat:z5dqj47s3fbt3d4t75bnsp2l6q

Recent Advances in 3D Object and Hand Pose Estimation [article]

Vincent Lepetit
2020 arXiv   pre-print
3D object and hand pose estimation have huge potentials for Augmented Reality, to enable tangible interfaces, natural interfaces, and blurring the boundaries between the real and virtual worlds.  ...  In this chapter, we present the recent developments for 3D object and hand pose estimation using cameras, and discuss their abilities and limitations and the possible future development of the field.  ...  Moreover, the predicted 3D locations are provided to a recurrent neural network, to propagate this information over time and recognize the action performed by the hand.  ... 
arXiv:2006.05927v1 fatcat:ttroutu7ljgzvf4joqexpz6rai

DeepTIO: A Deep Thermal-Inertial Odometry with Visual Hallucination [article]

Muhamad Risqi U. Saputra, Pedro P.B. de Gusmao, Chris Xiaoxuan Lu, Yasin Almalioglu, Stefano Rosa, Changhao Chen, Johan Wahlström, Wei Wang, Andrew Markham, Niki Trigoni
2020 arXiv   pre-print
To overcome this issue, we propose a Deep Neural Network model for thermal-inertial odometry (DeepTIO) by incorporating a visual hallucination network to provide the thermal network with complementary  ...  However, in visually-denied scenarios (e.g. heavy smoke or darkness), pose estimates degrade or even fail.  ...  to model long-term camera pose dependencies using a Recurrent Neural Network (RNN).  ... 
arXiv:1909.07231v2 fatcat:w4jtfllubvfsbl6a6lq3qnjxe4
« Previous Showing results 1 — 15 out of 802 results