Hand pose estimation with CNN-RNN

被引:0
|
作者
Hu, Zhongxu [1 ]
Hu, Youmin [1 ]
Wu, Bo [1 ]
Liu, Jie [1 ]
机构
[1] Huazhong Univ Sci & Technol, Sch Mech Sci & Engn, Wuhan, Hubei, Peoples R China
基金
国家重点研发计划;
关键词
Hand pose estimation; multi-frame; CNN-RNN;
D O I
10.1109/EECS.2017.91
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Hand pose estimation plays an important role in human-computer interaction. The traditional way is to deal with a single frame image. We know that the gesture is continuous, so the adjacent frames must be highly correlated. Therefore, the input of model of this paper was changed from single frame image to multi-frame images in order to use the condition that the adjacent frames have relevance. So the structure of CNN-RNN was used in this paper. We discussed the effect of using the RNN module in the model. Finally, we demonstrated that our approach significantly outperforms state-of-the-art techniques in the NYU dataset.
引用
收藏
页码:458 / 463
页数:6
相关论文
共 50 条
  • [1] Yield estimation of winter wheat in China based on CNN-RNN network
    He X.
    Luo H.
    Qiao M.
    Tian Z.
    Zhou G.
    Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2021, 37 (17): : 124 - 132
  • [2] Spatio-Temporal Approach using CNN-RNN in Hand Gesture Recognition
    Gunawan, Mochammad Rifky
    Djamal, Esmeralda Contessa
    2021 4TH INTERNATIONAL CONFERENCE ON COMPUTER AND INFORMATICS ENGINEERING (IC2IE 2021), 2021, : 385 - 389
  • [3] A dual CNN-RNN for multiple people tracking
    Babaee, Maryam
    Li, Zimu
    Rigoll, Gerhard
    NEUROCOMPUTING, 2019, 368 : 69 - 83
  • [4] A CNN-RNN Framework for Crop Yield Prediction
    Khaki, Saeed
    Wang, Lizhi
    Archontoulis, Sotirios V.
    FRONTIERS IN PLANT SCIENCE, 2020, 10
  • [5] Characters Recognition based on CNN-RNN architecture and Metaheuristic
    Keddous, F.
    Nguyen, H-N
    Nakib, A.
    2021 IEEE INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW), 2021, : 500 - 507
  • [6] A CNN-RNN unified framework for intrapartum cardiotocograph classification
    Liang, Huanwen
    Lu, Yu
    COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2023, 229
  • [7] CNN-RNN based method for license plate recognition
    Shivakumara, Palaiahnakote
    Tang, Dongqi
    Asadzadehkaljahi, Maryam
    Lu, Tong
    Pal, Umapada
    Anisi, Mohammad Hossein
    CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2018, 3 (03) : 169 - 175
  • [8] Improving CNN-RNN Hybrid Networks for Handwriting Recognition
    Dutta, Kartik
    Krishnan, Praveen
    Mathew, Minesh
    Jawahar, C. V.
    PROCEEDINGS 2018 16TH INTERNATIONAL CONFERENCE ON FRONTIERS IN HANDWRITING RECOGNITION (ICFHR), 2018, : 80 - 85
  • [9] A Hierarchical CNN-RNN Approach for Visual Emotion Classification
    Li, Liang
    Zhu, Xinge
    Hao, Yiming
    Wang, Shuhui
    Gao, Xingyu
    Huang, Qingming
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2019, 15 (03)
  • [10] Human Abnormality Classification Using Combined CNN-RNN Approach
    Kabir, Mohsin
    Safir, Farisa Benta
    Shahen, Saifullah
    Maua, Jannatul
    Awlad, Iffat Ara Binte
    Mridha, M. F.
    2020 IEEE 17TH INTERNATIONAL CONFERENCE ON SMART COMMUNITIES: IMPROVING QUALITY OF LIFE USING ICT, IOT AND AI (IEEEHONET 2020), 2020, : 204 - 208