High precision detection method of safety helmet based on convolution neural network

Tian-yu LI; Dong LI; Ming-ju CHEN; Hao WU; Yi-cen LIU

doi:10.37188/CJLCD.2020-0309

您当前的位置：

首页 >

文章列表页 >

High precision detection method of safety helmet based on convolution neural network

Image Processing | 更新时间：2021-07-13

- High precision detection method of safety helmet based on convolution neural network
- Chinese Journal of Liquid Crystals and Displays Vol. 36, Issue 7, Pages: 1018-1026(2021)
- 作者机构：
  
  1.四川轻化工大学人工智能四川省重点实验室, 四川宜宾 644000
  2.国网四川省电力公司电力研究院, 四川成都 610000
- 作者简介：
- 基金信息：
  
  Science and Technology Project Funding of State Grid Corporation of China(521997180016);Project of Sichuan Provincial Science and Technology Department(2017JY0338);Project of Sichuan Department of Science and Technology(2019YJ0477);Project of Sichuan Department of Science and Technology(2018GZDZX0043);Project of Sichuan Provincial Science and Technology Department(2018JY0386);Project of Sichuan Provincial Science and Technology Department(2020YFG0178);Artificial intelligence key laboratory of Sichuan province Foundation(2019RYY01);Graduate innovation fund project of Sichuan Light Chemical University(y2020020)
- DOI：10.37188/CJLCD.2020-0309
  CLC： TP391.4;TH691.9
- Received：18 November 2020，
  
  Revised：07 December 2020，
  
  Published：2021-07
- 稿件说明：
移动端阅览
Tian-yu LI, Dong LI, Ming-ju CHEN, et al. High precision detection method of safety helmet based on convolution neural network[J]. Chinese journal of liquid crystals and displays, 2021, 36(7): 1018-1026.
DOI：

Tian-yu LI, Dong LI, Ming-ju CHEN, et al. High precision detection method of safety helmet based on convolution neural network[J]. Chinese journal of liquid crystals and displays, 2021, 36(7): 1018-1026. DOI： 10.37188/CJLCD.2020-0309.

摘要

在复杂的施工环境中，基于机器视觉技术的安全帽佩戴检测算法常常出现漏检、误检，其检测能力有限。为提高安全帽佩戴检测的精度，本文建立了一种基于注意力机制的双向特征金字塔的安全帽检测卷积神经网络。为兼顾卷积神经网络中的浅层位置信息和深层语义信息的表达能力，实现对弱小安全帽目标的检测能力，该网络将跳跃连接和注意力机制CBAM技术引入双向特征融合的特征金字塔网络PANet模块中，构建基于注意力机制的双向特征金字塔模块CPANet。为提高模型的收敛能力，采用了CIoU来代替IoU进行优化锚框回归预测，降低该网络的训练难度。对比实验表明，本文建立的检测网络比YOLOv3、RFBNet、SSD、Faster RCNN的mAP值分别提高了0.82，4.43，23.12，23.96，检测速度达到21 frame/s，实现了施工现场安全帽佩戴实时高精度检测。

Abstract

In a complex construction environment

the helmet wearing recognition algorithm based on machine vision technology often fails and misdetects

and its recognition ability is limited. In order to improve the accuracy of helmet wearing recognition

this paper establishes a helmet recognition convolutional neural network based on the bidirectional feature pyramid of the attention mechanism isproposed. In order to improve the expression ability of shallow position information and deep semantic information in the convolutional neural network

and increase the recognition rate of vague and small helmets

the network introduces the jump connection and the attention mechanism CBAM technology into the bidirectional feature fusion feature pyramid network PANet module

and bidirectional feature pyramid module based on the attention mechanism is constructed. In order to improve the convergence ability of the model

CIoU is used instead of IoU to optimize the anchor frame regression prediction

which reduces the complexity of the network training. The results of comparative experiment show that the mAP value of our proposed recognition network is 0.82

4.43

23.12 and 23.96 higher than that of YOLOv3

RFBNet

SSD

Faster RCNN

respectively

and its detection speed reaches 21 frame/s

thus satisfy with height real-time accuracy of helmet recognition in the construction environment.

关键词

Keywords

references

刘晓慧 , 叶西宁 . 肤色检测和Hu矩在安全帽识别中的应用 . 华东理工大学学报(自然科学版) , 2014 . 40 ( 3 ): 365 - 370 . DOI: 10.3969/j.issn.1006-3080.2014.03.016 http://doi.org/10.3969/j.issn.1006-3080.2014.03.016 .

X H LIU , X N YE . Skin color detection and Hu moments in helmet recognition research . Journal of East China University of Science and Technology (Natural Science Edition) , 2014 . 40 ( 3 ): 365 - 370 . DOI: 10.3969/j.issn.1006-3080.2014.03.016 http://doi.org/10.3969/j.issn.1006-3080.2014.03.016 .

周艳青 , 薛河儒 , 姜新华 , 等 . 基于LBP统计特征的低分辨率安全帽识别 . 计算机系统应用 , 2015 . 24 ( 7 ): 211 - 215 . DOI: 10.3969/j.issn.1003-3254.2015.07.039 http://doi.org/10.3969/j.issn.1003-3254.2015.07.039 .

Y Q ZHOU , H R XUE , X H JIANG , 等 . Low-resolution safety helmet image recognition combining local binary pattern with statistical features . Computer Systems & Applications , 2015 . 24 ( 7 ): 211 - 215 . DOI: 10.3969/j.issn.1003-3254.2015.07.039 http://doi.org/10.3969/j.issn.1003-3254.2015.07.039 .

贾峻苏 , 鲍庆洁 , 唐慧明 . 基于可变形部件模型的安全头盔佩戴检测 . 计算机应用研究 , 2016 . 33 ( 3 ): 953 - 956 . DOI: 10.3969/j.issn.1001-3695.2016.03.072 http://doi.org/10.3969/j.issn.1001-3695.2016.03.072 .

J S JIA , Q J BAO , H M TANG . Method for detecting safety helmet based on deformable part model . Application Research of Computers , 2016 . 33 ( 3 ): 953 - 956 . DOI: 10.3969/j.issn.1001-3695.2016.03.072 http://doi.org/10.3969/j.issn.1001-3695.2016.03.072 .

储岳中 , 黄勇 , 张学锋 , 等 . 基于自注意力的SSD图像目标检测算法 . 华中科技大学学报(自然科学版) , 2020 . 48 ( 9 ): 70 - 75 . https://www.cnki.com.cn/Article/CJFDTOTAL-HZLG202009012.htm https://www.cnki.com.cn/Article/CJFDTOTAL-HZLG202009012.htm .

Y Z CHU , Y HUANG , X F ZHANG , 等 . SSD image target detection algorithm based on self-attention . Journal of Huazhong University of Science and Technology (Nature Science Edition) , 2020 . 48 ( 9 ): 70 - 75 . https://www.cnki.com.cn/Article/CJFDTOTAL-HZLG202009012.htm https://www.cnki.com.cn/Article/CJFDTOTAL-HZLG202009012.htm .

罗元 , 王薄宇 , 陈旭 . 基于深度学习的目标检测技术的研究综述 . 半导体光电 , 2020 . 41 ( 1 ): 1 - 10 . https://www.cnki.com.cn/Article/CJFDTOTAL-BDTG202001001.htm https://www.cnki.com.cn/Article/CJFDTOTAL-BDTG202001001.htm .

Y LUO , B Y WANG , X CHEN . Research progresses of target detection technology based on deep learning . Semiconductor Optoelectronics , 2020 . 41 ( 1 ): 1 - 10 . https://www.cnki.com.cn/Article/CJFDTOTAL-BDTG202001001.htm https://www.cnki.com.cn/Article/CJFDTOTAL-BDTG202001001.htm .

S Q REN , K M HE , R GIRSHICK , 等 . Faster R-CNN: towards real-time object detection with region proposal networks . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 . 39 ( 6 ): 1137 - 1149 . DOI: 10.1109/TPAMI.2016.2577031 http://doi.org/10.1109/TPAMI.2016.2577031 .

徐守坤 , 王雅如 , 顾玉宛 . 基于改进区域卷积神经网络的安全帽佩戴检测 . 计算机工程与设计 , 2020 . 41 ( 5 ): 1385 - 1389 . https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ202005028.htm https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ202005028.htm .

S K XU , Y R WANG , Y W GU . Construction site safety helmet wearing detection based on improved region convolutional neural network . Computer Engineering and Design , 2020 . 41 ( 5 ): 1385 - 1389 . https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ202005028.htm https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ202005028.htm .

REDMON J, DIVVALA S, GIRSHICK R, et al . You only look once: unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Las Vegas, NV, USA: IEEE, 2016: 779-788.

LIU W, ANGUELOV D, ERHAN D, et al . SSD: single shot multibox detector[C]//14 th European Conference on Computer Vision . Amsterdam, The Netherlands: Springer, 2016: 21-37.

REDMON J, FARHAD A. YOLO9000: better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Honolulu, HI, USA: IEEE, 2017: 6517-6525.

LIU S T, HUANG D, WANG Y H. Receptive field block net for accurate and fast object detection[C]//15 th European Conference on Computer Vision . Munich, Germany: Springer, 2018: 404-419.

REDMON J, FARHAD A. YOLOv3: an incremental improvement[C]//2018 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Salt Lake City, UT, USA: IEEE, 2018: 2767-2773.

董永昌 , 单玉刚 , 袁杰 . 基于改进SSD算法的行人检测方法 . 计算机工程与设计 , 2020 . 41 ( 10 ): 2921 - 2926 . https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ202010037.htm https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ202010037.htm .

Y C DONG , Y G SHAN , J YUAN . Pedestrian detection based on improved SSD . Computer Engineering and Design , 2020 . 41 ( 10 ): 2921 - 2926 . https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ202010037.htm https://www.cnki.com.cn/Article/CJFDTOTAL-SJSJ202010037.htm .

陈柳, 陈明举, 薛智爽, 等. 轻量化高精度卷积神经网络的安全帽识别方法[J/OL]. 计算机工程与应用, 1-8[2020-11-25] . http://kns.cnki.net/kcms/detail/11.2127.TP.20201023.1727.009.html http://kns.cnki.net/kcms/detail/11.2127.TP.20201023.1727.009.html .

CHEN L, CHEN M J, XUE Z S, et al . Lightweight and high-precision convolutional neural network for helmet recognition method[J/OL]. Computer Engineering and Applications , 1-8[2020-11-25]. http://kns.cnki.net/kcms/detail/11.2127.TP.20201023.1727.009.html http://kns.cnki.net/kcms/detail/11.2127.TP.20201023.1727.009.html . (in Chinese)

唐悦 , 吴戈 , 朴燕 . 改进的GDT-YOLOV 3目标检测算法 . 液晶与显示 , 2020 . 35 ( 8 ): 852 - 860 . http://cjlcd.lightpublishing.cn/thesisDetails#10.37188/YJYXS20203508.0852&graphicAbstract=0 http://cjlcd.lightpublishing.cn/thesisDetails#10.37188/YJYXS20203508.0852&graphicAbstract=0 .

Y TANG , G WU , Y PIAO . Improved algorithm of GDT-YOLOV 3 image target detection . Chinese Journal of Liquid Crystals and Displays , 2020 . 35 ( 8 ): 852 - 860 . http://cjlcd.lightpublishing.cn/thesisDetails#10.37188/YJYXS20203508.0852&graphicAbstract=0 http://cjlcd.lightpublishing.cn/thesisDetails#10.37188/YJYXS20203508.0852&graphicAbstract=0 .

LIU S, QI L, QIN H F, et al . Path aggregation network for instance segmentation[C]// Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City, UT, USA: IEEE, 2018: 8759-8768.

HUANG G, LIU Z, VAN DER MAATEN L, et al . Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition . Honolulu, HI, USA: IEEE, 2017: 2261-2269.

WOO S, PARK J, LEE J Y, et al . CBAM: convolutional block attention module[C]//2018 15 th European Conference on Computer Vision . Munich, Germany: Springer, 2018: 3-19.

Z H ZHENG , P WANG , W LIU , 等 . Distance-IoU loss: faster and better learning for bounding box regression . Proceedings of the AAAI Conference on Artificial Intelligence , 2020 . 34 ( 7 ): 12993 - 13000 . DOI: 10.1609/aaai.v34i07.6999 http://doi.org/10.1609/aaai.v34i07.6999 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Improved SSD based aircraft remote sensing image target detection

Attention and feature fusion for aircraft target detection in optical remote sensing images

Related Author

Tian-yu LI

Dong LI

Ming-ju CHEN

Hao WU

Yi-ceng LIU

Hao-tong WANG

Zhong-hua GUO

Xu-ting LAN

Related Institution

Electric Power Research Institute， State Grid Sichuan Electric Power Company

Sichuan University of Science & Engineering， Key Laboratory of Artificial Intelligence in Sichuan Province

School of Physics and Electronic and Electrical Engineering, Ningxia University

Ningxia Key Laboratory of Desert Information IntelligentPerception

School of Physics and Electronic and Electrical Engineering， Ningxia University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China 130033 Postal code：130033
Tel：0431-86176059 Email：yjxs@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰