Dynamic gesture recognition based on CNN-LSTM-Attention

Jinwei Liu, Baoguo Wei, Mingzhi Cai, Yong Xu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Compared with traditional human-computer interaction techniques, gesture recognition is closer to human expression habits and have some advantages of being efficient and easy to master. Vision-based gesture recognition does not require additional equipment, and is very convenient and relatively low cost. To recognize dynamic gesture in complex background, we build a backbone network based on SSD with dilated convolution, which greatly improves the quality of the detected feature maps, and then we proposes a CNN-LSTM-Attention based dynamic gesture recognition network. The spatial features of dynamic gestures at each moment are first extracted from gesture sequences, then these features are transformed into dynamic gesture spatio-Temporal features by a recurrent neural network with an attention mechanism, and finally fed into a fully connected neural network for gesture recognition. The dynamic gesture recognition network achieves 93.5% recognition rate on Sahand dataset, which exhibits its effectiveness.

Original languageEnglish
Title of host publicationProceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665429184
DOIs
StatePublished - 17 Aug 2021
Event2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021 - Xi�an, China
Duration: 17 Aug 202119 Aug 2021

Publication series

NameProceedings of 2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021

Conference

Conference2021 IEEE International Conference on Signal Processing, Communications and Computing, ICSPCC 2021
Country/TerritoryChina
CityXi�an
Period17/08/2119/08/21

Keywords

  • attention mechanism
  • deep Learning
  • dilated convolution
  • gesture recognition
  • LSTM

Fingerprint

Dive into the research topics of 'Dynamic gesture recognition based on CNN-LSTM-Attention'. Together they form a unique fingerprint.

Cite this