586 Hits in 4.6 sec

Traffic Police Gesture Recognition Based on Gesture Skeleton Extractor and Multichannel Dilated Graph Convolution Network

Xin Xiong, Haoyuan Wu, Weidong Min, Jianqiang Xu, Qiyan Fu, Chunjiang Peng
2021 Electronics  
Traffic police gesture recognition is important in automatic driving.  ...  To alleviate the aforementioned issues, a traffic police gesture recognition method based on a gesture skeleton extractor (GSE) and a multichannel dilated graph convolution network (MD-GCN) is proposed  ...  Acknowledgments: We gratefully acknowledge the assistance of Neurocomputing, 390, He J, Zhang C, He X, Dong R, Visual Recognition of traffic police gestures with convolutional pose machine and handcrafted  ... 
doi:10.3390/electronics10050551 fatcat:q5zbhbzjsnfotpjuh6dyhmuw2i

Dynamic Gesture Recognition Algorithm Based on 3D Convolutional Neural Network

Yuting Liu, Du Jiang, Haojie Duan, Ying Sun, Gongfa Li, Bo Tao, Juntong Yun, Ying Liu, Baojia Chen, Syed Hassan Ahmed
2021 Computational Intelligence and Neuroscience  
The temporal and spatial features are extracted by convolution of the video containing gesture.  ...  The experiments show that the recognition accuracy of the proposed 3D convolutional neural network combined with attention mechanism reaches 72.4% on EgoGesture dataset, which is improved greatly compared  ...  In the dynamic gesture recognition, LSTM uses the common convolutional network to extract the features, serializes the spatial features extracted by the previous network through LSTM, and then classifies  ... 
doi:10.1155/2021/4828102 pmid:34447430 pmcid:PMC8384521 fatcat:bb5m3n3znncwnfjsuhc33pzcxm

A Deep Learning Framework for Recognizing both Static and Dynamic Gestures [article]

Osama Mazhar, Sofiane Ramdani, Andrea Cherubini
2021 arXiv   pre-print
The Convolutional Neural Network in StaDNet is fine-tuned on a background-substituted hand gestures dataset.  ...  We employ a pose-driven spatial attention strategy, which guides our proposed Static and Dynamic gestures Network - StaDNet.  ...  In [34] , the authors studied redundancy and attention in ConvLSTM by deriving its several variants for gesture recognition.  ... 
arXiv:2006.06321v2 fatcat:bgruduvbzbedtibcy2gylsgk6e

CGAP2: Context and gap aware predictive pose framework for early detection of gestures [article]

Nishant Bhattacharya, Suresh Sundaram
2020 arXiv   pre-print
In this paper, we propose a novel context and gap aware pose prediction framework(CGAP2), which predicts future pose data for anticipatory recognition of gestures in an online fashion.  ...  With a growing interest in autonomous vehicles' operation, there is an equally increasing need for efficient anticipatory gesture recognition systems for human-vehicle interaction.  ...  [35] introduce attention based convolutional LSTMs and ascertain how they barely contribute to spatio-temporal feature fusion based on which they derive a new LSTM cell.  ... 
arXiv:2011.09216v1 fatcat:aaqeyu3nfnakdkt2zackjs7pmu

A Deep Learning Framework for Recognizing Both Static and Dynamic Gestures

Osama Mazhar, Sofiane Ramdani, Andrea Cherubini
2021 Sensors  
The Convolutional Neural Network (CNN) in StaDNet is fine-tuned on a background-substituted hand gestures dataset.  ...  We employ a pose-driven spatial attention strategy, which guides our proposed Static and Dynamic gestures Network—StaDNet.  ...  In [47] , the authors studied redundancy and attention in ConvLSTM by deriving its several variants for gesture recognition.  ... 
doi:10.3390/s21062227 pmid:33806741 fatcat:bicbi5kswbfwplpw7mh23x3bli

DrawInAir: A Lightweight Gestural Interface Based on Fingertip Regression [chapter]

Gaurav Garg, Srinidhi Hegde, Ramakrishna Perla, Varun Jain, Lovekesh Vig, Ramya Hebbalaguppe
2019 Lecture Notes in Computer Science  
The major challenge in training egocentric gesture recognition models is in obtaining sufficient labeled data for end-to-end learning.  ...  (Bi-LSTM), for a real-time pointing hand gesture classification.  ...  In our scenario, since the fingertip location is known, training an attention model appears redundant.  ... 
doi:10.1007/978-3-030-11024-6_15 fatcat:jxm3gp2werh6poognecdy4xqh4

GestARLite: An On-Device Pointing Finger Based Gestural Interface for Smartphones and Video See-Through Head-Mounts [article]

Varun Jain, Gaurav Garg, Ramakrishna Perla, Ramya Hebbalaguppe
2019 arXiv   pre-print
by a Bi-LSTM model for gesture classification.  ...  To this end, we propose a novel lightweight hand gesture recognition framework that works in First Person View for wearable devices.  ...  (ii) 2 gesture patterns (Rectangle and Circle) for RoI highlighting in user's FoV and for zoom-in and zoom-out operations.  ... 
arXiv:1904.09843v1 fatcat:uay76kwlhne4hg5mulutcnpizy

RGB-D-based Human Motion Recognition with Deep Learning: A Survey [article]

Pichao Wang and Wanqing Li and Philip Ogunbona and Jun Wan and Sergio Escalera
2018 arXiv   pre-print
In particular, convolutional neural networks (CNN) have achieved great success for image-based tasks, and recurrent neural networks (RNN) are renowned for sequence-based problems.  ...  Human motion recognition is one of the most important branches of human-centered research activities. In recent years, motion recognition based on RGB-D data has attracted much attention.  ...  Figure from [22] . an end-to-end trainable neural network architecture incorporating temporal convolutions and bidirectional LSTM for gesture recognition.  ... 
arXiv:1711.08362v2 fatcat:cugugpqeffcshnwwto4z2aw4ti

Deep Learning for Action and Gesture Recognition in Image Sequences: A Survey [chapter]

Maryam Asadi-Aghbolaghi, Albert Clapés, Marco Bellantonio, Hugo Jair Escalante, Víctor Ponce-López, Xavier Baró, Isabelle Guyon, Shohreh Kasaei, Sergio Escalera
2017 Gesture Recognition  
A survey on deep learning based approaches for action and gesture recognition in image sequences.  ...  This chapter is a survey of current deep learning based methodologies for action and gesture recognition in sequences of images.  ...  Acknowledgments This work has been partially supported by the Spanish projects TIN2015-66951-C2-2-R and TIN2016-74946-P (MINECO/FEDER, UE) and CERCA Programme / Generalitat de Catalunya.  ... 
doi:10.1007/978-3-319-57021-1_19 fatcat:d2m5oyomsjhkbfpunhefho6ayq

Sign Language Recognition Analysis using Multimodal Data [article]

Al Amin Hosain, Panneer Selvam Santhalingam, Parth Pathak, Jana Kosecka, Huzefa Rangwala
2019 arXiv   pre-print
In this work, we investigate the feasibility of using skeletal and RGB video data for sign language recognition using a combination of different deep learning architectures.  ...  With the advancement of depth sensors, skeletal data is used for applications like video analysis and activity recognition.  ...  Compared to RGB methods, skeletal data has received little attention in ASL recognition.  ... 
arXiv:1909.11232v1 fatcat:owkrqtzc6ngrna5bdtsru26gqq

Evaluation Of Hidden Markov Models Using Deep CNN Features In Isolated Sign Recognition [article]

Anil Osman Tur, Hacer Yalim Keles
2020 arXiv   pre-print
This problem has recently been studied widely using deep Convolutional Neural Network (CNN) based features and Long Short-Term Memory (LSTM) based deep sequence models.  ...  Isolated sign recognition from video streams is a challenging problem due to the multi-modal nature of the signs, where both local and global hand features and face gestures needs to be attended simultaneously  ...  Acknowledgement The research presented is part of a project funded by The Scientific and Technological Research Council of Turkey (TÜBİTAK) under the grant number 217E022. %bibliographystyleieeetr  ... 
arXiv:2006.11183v1 fatcat:wrzgzsonmjfrfn5qfatp3s2tju

Short-Term Temporal Convolutional Networks for Dynamic Hand Gesture Recognition [article]

Yi Zhang, Chong Wang, Ye Zheng, Jieyu Zhao, Yuqi Li, Xijiong Xie
2019 arXiv   pre-print
In this paper, we present a multimodal gesture recognition method based on 3D densely convolutional networks (3D-DenseNets) and improved temporal convolutional networks (TCNs).  ...  The purpose of gesture recognition is to recognize meaningful movements of human bodies, and gesture recognition is an important issue in computer vision.  ...  For instance, convolutional LSTM [26] was introduced for spatio-temporal feature maps. 2S-RNN(RGB and Depth) [27] was used for continuous gesture recognition.  ... 
arXiv:2001.05833v1 fatcat:yuthfbzzzfddzhe5xa63pv4onq

Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition [article]

Benjia Zhou, Yunan Li, Jun Wan
2021 arXiv   pre-print
In this paper, we propose a regional attention with architecture-rebuilt 3D network (RAAR3DNet) for gesture recognition.  ...  Human gesture recognition has drawn much attention in the area of computer vision.  ...  for gesture recognition.  ... 
arXiv:2102.05348v2 fatcat:tx2w52q2e5ehvbl3qlzmzyjqmq

Chinese Traffic Police Gesture Recognition Based on Graph Convolutional Network in Natural Scene

Kang Liu, Ying Zheng, Junyi Yang, Hong Bao, Haoming Zeng
2021 Applied Sciences  
nodes and a temporal attention mechanism (TAS) to extract features in the temporal dimension.  ...  For an automated driving system to be robust, it needs to recognize not only fixed signals such as traffic signs and traffic lights, but also gestures used by traffic police.  ...  Partitioning strategies for constructing convolution operations. Figure 8 . 8 Figure 8. Channel attention module. Figure 9 . 9 Figure 9. Spatial attention module.  ... 
doi:10.3390/app112411951 fatcat:id5hbay5ofcizfsktrwzvzgurq

Multi-Task and Multi-Modal Learning for RGB Dynamic Gesture Recognition

Dinghao Fan, Hengjie Lu, Shugong Xu, Shan Cao
2021 IEEE Sensors Journal  
Our framework is trained to learn a representation for multi-task learning: gesture segmentation and gesture recognition.  ...  Gesture recognition is getting more and more popular due to various application possibilities in human-machine interaction.  ...  INTRODUCTION R ECENT advances in computer vision and pattern recognition have made gesture recognition an accessible and important interaction tool for various applications including human-computer interaction  ... 
doi:10.1109/jsen.2021.3123443 fatcat:4biyoph3xbe6dksji53pzpcc6i
« Previous Showing results 1 — 15 out of 586 results