基于机器视觉的复杂环境下精确手势识别算法研究

doi:10.16182/j.issn1004731x.joss.21-FZ0668

系统仿真学报 ›› 2021, Vol. 33 ›› Issue (10): 2460-2469.doi: 10.16182/j.issn1004731x.joss.21-FZ0668

基于机器视觉的复杂环境下精确手势识别算法研究

徐胜^1,2, 冯文宇³, 刘志诚³, 涂鑫涛³, 费敏锐⁴, 张堃^3,5,*

1.南通职业大学电子信息工程学院,江苏南通 226007;
2.华东理工常熟研究院有限公司,江苏常熟 215500;
3.南通大学电气工程学院/张謇学院,江苏南通 226007;
4.上海大学机电工程与自动化学院,上海 310053;
5.南通市智能计算与智能控制重点实验室,江苏南通 226007

收稿日期:2021-04-15 修回日期:2021-08-18 出版日期:2021-10-18 发布日期:2021-10-18
通讯作者: 张堃(1983-),男,博士,教授,研究方向为人工智能等。E-mail：zhangkun@ntu.edu.cn
作者简介:徐胜(1980-),男,博士,副教授,研究方向为网络化控制、机器视觉等。E-mail：xsheng1980@163.com
基金资助:
江苏省333工程科研项目(BRA2018218); 江苏省博士后科研资助计划(2020Z389); 南通市基础科学研究项目(JC2021035); 江苏省研究生科研与实践创新计划(SJCX21_1449); 国家级大学生创新创业训练计划(202110304027Z); 省级大学生创新创业训练计划(202110304169H)

Research on Accurate Gesture Recognition Algorithm in Complex Environment Based on Machine Vision

Xu Sheng^1,2, Feng Wenyu³, Liu Zhicheng³, Tu Xintao³, Fei Minrui⁴, Zhang Kun^3,5,*

1. School of Electronic and Information Engineering, Nantong Vocational University, Nantong 226007, China;
2. The East China Science and Technology Research Institute of Changshu Co., Ltd, Changshu 215500, China;
3. School of Electrical Engineering/School of Zhangjian, Nantong University, Nantong 226007 China;
4. School of Mechatronic Engineering and Automation, Shanghai University, Shanghai 310053, China;
5. Nantong Key Laboratory of Intelligent Control and Intelligent Computing, Nantong 226007, China

Received:2021-04-15 Revised:2021-08-18 Online:2021-10-18 Published:2021-10-18

摘要/Abstract

摘要： 针对新冠疫情期间电梯公共按键会导致交叉感染的问题,设计了一种基于机器视觉的无接触式电梯按键控制手势识别算法。为提高手势识别检测精度,结合注意力机制设计了一种Ghost模块,并将YOLOv4中的ResBlock模块改进为Ghost模块,提出改进型YOLOv4算法。经测试,在识别手势的任务中,改进型YOLOv4算法的检测速度较原模型提高了14%,检测精度较原模型提高了0.1%。以改进型YOLOv4算法为核心,设计了一种能应用于电梯按键控制的手势算法,实验数据表明,控制电梯按键的手势识别精度达到98%,可满足公共电梯实施无接触控制的要求。

关键词: 手势识别, YOLOv4, 注意力机制, Ghost模块

Abstract: To address the issue of cross infection caused by elevator public buttons during COVID-19, a software algorithm based on machine vision for non-contact control of public buttons by gesture recognition is designed. In order to improve the accuracy of gesture recognition, an improved YOLOv4 algorithm is proposed. A Ghost module is designed based on attention mechanism, and the ResBlock module in YOLOv4 is improved to Ghost module. The experimental results show that, in the task of gesture recognition, the detection speed is improved by 14% and the detection accuracy is improved by 0.1% compared with the original model. The improved YOLOv4 algorithm is applied to the non-contact elevator buttons control system based on vision. The experimental results show that the detection accuracy reaches 98%, which meets the requirements of non-contact control for public elevators.

Key words: Gesture recognition, YOLOv4, Attentional mechanism, Ghost module

中图分类号:

TP391

徐胜, 冯文宇, 刘志诚, 涂鑫涛, 费敏锐, 张堃. 基于机器视觉的复杂环境下精确手势识别算法研究[J]. 系统仿真学报, 2021, 33(10): 2460-2469.

Xu Sheng, Feng Wenyu, Liu Zhicheng, Tu Xintao, Fei Minrui, Zhang Kun. Research on Accurate Gesture Recognition Algorithm in Complex Environment Based on Machine Vision[J]. Journal of System Simulation, 2021, 33(10): 2460-2469.

参考文献

[1] Liu S Q, Zhang J C, Zhu R.A Wearable Human Motion Tracking Device Using Micro Flow Sensor Incorporating a Micro Accelerometer[J]. IEEE Transactions on Biomedical Engineering (S0018-9294), 2019, 67(4): 940-948.
[2] Wong W K, Juwono F H, Khoo B T T. Multi-features Capacitive Hand Gesture Recognition Sensor: a Machine Learning Approach[J]. IEEE Sensors Journal (S1530-437X), 2021, 21(6): 8441-8450.
[3] Valueva M V, Nagornov N N, Lyakhov P A, et al.Application of the Residue Number System to Reduce Hardware Costs of the Convolutional Neural Network Implementation[J]. Mathematics and Computers in Simulation (S0378-4754), 2020, 177: 232-243.
[4] Cao Z, Hidalgo G, Simon T, et al.OpenPose: Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2019, 43(1): 172-186.
[5] Mao Q C, Sun H M, Liu Y B, et al.Mini-YOLOv3: Real-time Object Detector for Embedded Applications[J]. IEEE Access (S2169-3536), 2019, 7: 133529-133538.
[6] Wu D, Lv S, Jiang M, et al.Using Channel Pruning-based YOLO v4 Deep Learning Algorithm for the Real-time and Accurate Detection of Apple Flowers in Natural Environments[J]. Computers and Electronics in Agriculture (S0168-1699), 2020, 178: 105742.
[7] 朱洪堃, 殷佳炜, 冯文宇, 等. 一种轻量化实时人体姿势检测模型研究与应用[J]. 系统仿真学报, 2020, 32(11): 2155-2165.
Zhu Hongkun, Yin Jiawei, Feng Wenyu, et al.Research and Application of a Lightweight Real-time Human Pose Detection Model[J]. Journal of System Simulation, 2020, 32(11): 2155-2165.
[8] 冯文宇, 朱洪堃, 殷佳炜, 等. 无人CT智能姿态识别算法研究[J]. 仪器仪表学报, 2020, 41(8): 188-195.
Feng Wenyu, Zhu Hongkun, Yin Jiawei, et al.Research on Intelligent Attitude Recognition Algorithm of Unmanned CT[J]. Chinese Journal of Scientific Instrument, 2020, 41(8): 188-195.
[9] Fu L, Feng Y, Wu J, et al.Fast and Accurate Detection of Kiwifruit in Orchard Using Improved YOLOv3-tiny Model[J]. Precision Agriculture (S1385-2256), 2021, 22(3): 754-776.
[10] Bao C, Xie T, Feng W, et al.A Power-Efficient Optimizing Framework FPGA Accelerator Based on Winograd for YOLO[J]. IEEE Access (S2169-3536), 2020, 8: 94307-94317.
[11] Li Y, Li S, Du H, et al.YOLO-ACN: Focusing on Small Target and Occluded Object Detection[J]. IEEE Access (S2169-3536), 2020, 8: 227288-227303.
[12] Zhang X, Zhou X, Lin M, et al.Shufflenet: An extremely Efficient Convolutional Neural Network for Mobile Devices[C]// IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: CVPR, 2018: 6848-6856.
[13] Han K, Wang Y, Tian Q, et al.Ghostnet: More Features from Cheap Operations[C]// IEEE/CVF Conference on Computer Vision and Pattern Recognition. ELECTR NETWORK: CVPR, 2020: 1580-1589.
[14] Hu J, Shen L, Albanie S, et al.Squeeze-and-Excitation Networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence (S0162-8828), 2020, 42(8): 2011-2023.
[15] Fan H, Mei X, Prokhorov D, et al.Multi-level Contextual RNNS with Attention Model for Scene Labeling[J]. IEEE Transactions on Intelligent Transportation Systems (S1524-9050), 2018, 19(11): 3475-3485.
[16] 石敏, 姚瀚钦, 李淳芃, 等. 基于深度Alignment网络的足部测量[J]. 系统仿真学报, 2020, 32(7): 1267-1278.
Shi Min, Yao Hanqin, Li Chunpeng, et al.Foot Measurement Based on Deep Alignment Network[J]. Journal of System Simulation, 2020, 32(7): 1267-1278.
[17] Duan P, Wang T, Cui M, et al.Multi-person Pose Estimation Based on a Deep Convolutional Neural Network[J]. Journal of Visual Communication and Image Representation (S1047-3203), 2019, 62: 245-252.
[18] Shankar V, Roelofs R, Mania H, et al.Evaluating Machine Accuracy on Imagenet[C]// International Conference on Machine Learning. Salt Lake City: PMLR, 2020: 8634-8644.
[19] Suh S, Lee H, Lukowicz P, et al.CEGAN: Classification Enhancement Generative Adversarial Networks for Unraveling Data Imbalance Problems[J]. Neural Networks (S0893-6080), 2021, 133: 69-86.
[20] Sandler M, Howard A, Zhu M, et al.Mobilenetv2: Inverted Residuals and Linear Bottlenecks[C]// IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City: CVPR, 2018: 4510-4520.
[21] Tan M, Le Q.Efficientnet: Rethinking Model Scaling for Convolutional Neural Networks[C]// International Conference on Machine Learning. Long Beach: LCML, 2019: 6105-6114.
[22] Huang G, Liu S, Van D M L, et al. Condensenet: An Efficient Densenet Using Learned Group Convolutions[C]// IEEE Conference on Computer Vision and Pattern Recognition. Houston: Medical Imaging Conference-Image-Guided Procedures, 2018: 2752-2761.

基于机器视觉的复杂环境下精确手势识别算法研究

Research on Accurate Gesture Recognition Algorithm in Complex Environment Based on Machine Vision

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 8

编辑推荐

Metrics

本文评价

[1]	王银, 王飞翔, 孙前来. 多尺度特征融合车辆检测方法[J]. 系统仿真学报, 2022, 34(6): 1219-1229.
[2]	尹诗, 侯国莲, 迟岩, 弓林娟, 胡晓东. 风电机组发电机前轴承健康度预测方法及实现[J]. 系统仿真学报, 2021, 33(6): 1323-1333.
[3]	薛艳萍, 王学松, 武仲科, 王醒策, 周明全. Myo手势识别方法在古建筑漫游系统中的应用[J]. 系统仿真学报, 2019, 31(9): 1907-1915.
[4]	王远明, 张珺, 秦远辉, 柴秀娟. 基于多特征融合的指挥手势识别方法研究[J]. 系统仿真学报, 2019, 31(2): 346-352.
[5]	孔亦思, 胡晓峰, 朱丰, 陶九阳. 战场态势感知中的注意力机制探析[J]. 系统仿真学报, 2017, 29(10): 2233-2241.
[6]	蔡芝蔚, 吴淑燕, 宋俊锋. 基于SVM和组合优化模型的手势识别[J]. 系统仿真学报, 2016, 28(8): 1812-1817.
[7]	毛雁明, 章立亮. 基于Kinect深度信息的手势分割与识别[J]. 系统仿真学报, 2015, 27(4): 830-835.
[8]	王任大, 尹勇, 邢胜伟. 用于手势识别系统的肤色图像后处理方法研究[J]. 系统仿真学报, 2015, 27(10): 2483-2488.