A real-time recognition method of static gesture based on DSSD (original) (raw)

Abstract

Gesture recognition is of great significance for human-machine interaction and it has broad application prospects. In order to improve the detection accuracy and speed, a real-time recognition method of static gesture based on Deconvolutional Single Shot Detector (DSSD) is proposed in this paper. We have improved the original DSSD network and the deconvolution module, used the K-means clustering algorithm to select the aspect ratios of the prior boxes to improve the detection accuracy. The detection accuracy of small data set is improved by introducing transfer learning method, and the influences of three different base networks on the DSSD network model are discussed. In order to verify the effectiveness of the proposed method, we compared it with the gesture recognition methods based on SSD300, SSD321, YOLOV2 and DES in ASL dataset. The experimental results show that the proposed method has a recognition rate of 94.8%, which is 2.7%, 2.1% and 2.8%higher than SSD300, SSD321 and YOLOv2, respectively. The detection rate is close to the method of Single-Shot Object Detection with Enriched Semantics (DES), while still maintaining a reasonable detection speed of 27 FPS. In addition, since DSSD fuse the semantic information of each feature extraction layer, the proposed method also has good detection ability for small gesture objects.

Access this article

Log in via an institution

Subscribe and save

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Dai J, Li Y, He K (2016). R-FCN: object detection via region-based fully ConvolutionalNetworks. 2017 IEEE conference on computer vision and pattern recognition (CVPR)
  2. Fu CY, Liu W, Ranga A, Tyagi A, Berg AC (2017) DSSD : deconvolutional single shot detector. arXiv preprint arXiv:1701.06659
  3. He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. Proceedings of the 2016 IEEE conference on computer vision and pattern recognition (CVPR), Las Vegas: IEEE, pp:770–778
  4. Krizhevsky A, Sutskever I, Hinton GE (2012). Image net classification with deep convolutional neural networks. Proceedings of international conference on neural information processing systems. Curran associates Inc, pp: 1097–1105.
  5. Lin T Y, Dollar P, Girshick R (2017). Feature pyramid networks for object detection 2017 IEEE conference on computer vision and pattern recognition (CVPR).
  6. Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY et al (2016)SSD: single shot MultiBox detector. European conference on computer vision (ECCV)
  7. Ma GW, Xu ZH, Zhang W, Li SC (2015) An enriched k-means clustering method for grouping fractures with meliorated initial centers. Arab J Geosci 8(4):1881–1893
    Article Google Scholar
  8. Peng Z, Bingbing N, Cong G (2018) Scale-transferrable object detection. 2018 IEEE conference on computer vision and pattern recognition (CVPR)
  9. Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, Real-Time Object Detection IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  10. Shrivastava A, Sukthankar R, Malik J (2017). Beyond Skip Connections: Top-Down Modulation for Object Detection. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  11. Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. Computer Science
  12. Zhang S, Wen L, Bian X (2018) Single-shot refinement neural network for object detection. 2018 IEEE conference on computer vision and pattern recognition (CVPR)
  13. Zhang Z, Qiao S, Xie C (2018). Single-Shot Object Detection with Enriched Semantics. 2018 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Download references

Author information

Authors and Affiliations

  1. School of Computer and Information, Hefei University of Technology, No.193, Tunxi Road, HeFei, Anhui, People’s Republic of China
    Yong Zhang, Wenjun Zhou, Yujie Wang & Linjia Xu

Authors

  1. Yong Zhang
  2. Wenjun Zhou
  3. Yujie Wang
  4. Linjia Xu

Corresponding author

Correspondence toYong Zhang.

Ethics declarations

Conflict of interest

Author Yong Zhang declares that he has no conflict of interest. Author Wenjun Zhou declares that he has no conflict of interest. Author Yujie Wang declares that she has no conflict of interest. Author LinjiaXu declares that he has no conflict of interest.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

About this article

Cite this article

Zhang, Y., Zhou, W., Wang, Y. et al. A real-time recognition method of static gesture based on DSSD.Multimed Tools Appl 79, 17445–17461 (2020). https://doi.org/10.1007/s11042-020-08725-9

Download citation

Keywords