FPGA-based Implementation of Hand Gesture Recognition Using Convolutional Neural Network

Tongtong Zhang; Weiguo Zhou; Xin Jiang; Yunhui Liu

doi:10.1109/CBS.2018.8612238

FPGA-based Implementation of Hand Gesture Recognition Using Convolutional Neural Network

Tongtong Zhang
, Weiguo Zhou
, Xin Jiang
, Yunhui Liu

Harbin Institute of Technology Shenzhen
Chinese University of Hong Kong

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Scopus citations

Abstract

Convolutional Neural Network (CNN) is a deep learning algorithm which is widely used in image processing and pattern recognition due to its robustness to feature invariance. However, it is also computation-intensive that results in a bad real-time performance. Field Programmable Gate Arrays (FPGA) has good performance in energy-efficiency, flexibility of parallel processing and pipelined operations. Thus it is expected to be used for accelerating deep learning algorithm. In this research, a FPGA based system is developed to realize the real-time Hand Gesture Recognition. We train a designed CNN model with caffe framework and obtain the model's parameters on PC. Bilinear interpolation algorithm is used to adjust the size of the image captured by camera. Then we use FPGA to implement the inference process of Hand Gesture Recognition with obtained parameters by designing an accelerator using Xilinx SDx tools.

Original language	English
Title of host publication	2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	133-138
Number of pages	6
ISBN (Electronic)	9781538673553
DOIs	https://doi.org/10.1109/CBS.2018.8612238
State	Published - 2 Jul 2018
Externally published	Yes
Event	2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018 - Shenzhen, China Duration: 25 Oct 2018 → 27 Oct 2018

Publication series

Name	2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018

Conference

Conference	2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018
Country/Territory	China
City	Shenzhen
Period	25/10/18 → 27/10/18

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

Access to Document

10.1109/CBS.2018.8612238

Cite this

Zhang, T., Zhou, W., Jiang, X., & Liu, Y. (2018). FPGA-based Implementation of Hand Gesture Recognition Using Convolutional Neural Network. In 2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018 (pp. 133-138). Article 8612238 (2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CBS.2018.8612238

@inproceedings{2b5e4355554c47f1be18cdb9603ac8a3,

title = "FPGA-based Implementation of Hand Gesture Recognition Using Convolutional Neural Network",

abstract = "Convolutional Neural Network (CNN) is a deep learning algorithm which is widely used in image processing and pattern recognition due to its robustness to feature invariance. However, it is also computation-intensive that results in a bad real-time performance. Field Programmable Gate Arrays (FPGA) has good performance in energy-efficiency, flexibility of parallel processing and pipelined operations. Thus it is expected to be used for accelerating deep learning algorithm. In this research, a FPGA based system is developed to realize the real-time Hand Gesture Recognition. We train a designed CNN model with caffe framework and obtain the model's parameters on PC. Bilinear interpolation algorithm is used to adjust the size of the image captured by camera. Then we use FPGA to implement the inference process of Hand Gesture Recognition with obtained parameters by designing an accelerator using Xilinx SDx tools.",

author = "Tongtong Zhang and Weiguo Zhou and Xin Jiang and Yunhui Liu",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018 ; Conference date: 25-10-2018 Through 27-10-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/CBS.2018.8612238",

language = "英语",

series = "2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "133--138",

booktitle = "2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018",

address = "美国",

}

Zhang, T, Zhou, W, Jiang, X & Liu, Y 2018, FPGA-based Implementation of Hand Gesture Recognition Using Convolutional Neural Network. in 2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018., 8612238, 2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018, Institute of Electrical and Electronics Engineers Inc., pp. 133-138, 2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018, Shenzhen, China, 25/10/18. https://doi.org/10.1109/CBS.2018.8612238

FPGA-based Implementation of Hand Gesture Recognition Using Convolutional Neural Network. / Zhang, Tongtong; Zhou, Weiguo; Jiang, Xin et al.
2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 133-138 8612238 (2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - FPGA-based Implementation of Hand Gesture Recognition Using Convolutional Neural Network

AU - Zhang, Tongtong

AU - Zhou, Weiguo

AU - Jiang, Xin

AU - Liu, Yunhui

PY - 2018/7/2

Y1 - 2018/7/2

N2 - Convolutional Neural Network (CNN) is a deep learning algorithm which is widely used in image processing and pattern recognition due to its robustness to feature invariance. However, it is also computation-intensive that results in a bad real-time performance. Field Programmable Gate Arrays (FPGA) has good performance in energy-efficiency, flexibility of parallel processing and pipelined operations. Thus it is expected to be used for accelerating deep learning algorithm. In this research, a FPGA based system is developed to realize the real-time Hand Gesture Recognition. We train a designed CNN model with caffe framework and obtain the model's parameters on PC. Bilinear interpolation algorithm is used to adjust the size of the image captured by camera. Then we use FPGA to implement the inference process of Hand Gesture Recognition with obtained parameters by designing an accelerator using Xilinx SDx tools.

AB - Convolutional Neural Network (CNN) is a deep learning algorithm which is widely used in image processing and pattern recognition due to its robustness to feature invariance. However, it is also computation-intensive that results in a bad real-time performance. Field Programmable Gate Arrays (FPGA) has good performance in energy-efficiency, flexibility of parallel processing and pipelined operations. Thus it is expected to be used for accelerating deep learning algorithm. In this research, a FPGA based system is developed to realize the real-time Hand Gesture Recognition. We train a designed CNN model with caffe framework and obtain the model's parameters on PC. Bilinear interpolation algorithm is used to adjust the size of the image captured by camera. Then we use FPGA to implement the inference process of Hand Gesture Recognition with obtained parameters by designing an accelerator using Xilinx SDx tools.

UR - https://www.scopus.com/pages/publications/85062099469

U2 - 10.1109/CBS.2018.8612238

DO - 10.1109/CBS.2018.8612238

M3 - 会议稿件

AN - SCOPUS:85062099469

T3 - 2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018

SP - 133

EP - 138

BT - 2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018

Y2 - 25 October 2018 through 27 October 2018

ER -

Zhang T, Zhou W, Jiang X, Liu Y. FPGA-based Implementation of Hand Gesture Recognition Using Convolutional Neural Network. In 2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 133-138. 8612238. (2018 IEEE International Conference on Cyborg and Bionic Systems, CBS 2018). doi: 10.1109/CBS.2018.8612238

FPGA-based Implementation of Hand Gesture Recognition Using Convolutional Neural Network

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this