Detection Algorithm of Safety Helmet Wear Based on MobileNet-SSD

doi:10.19678/j.issn.1000-3428.0058733

Abstract

Abstract: The existing methods for checking the wear of safety helmets suffer from complex background and strong interference, and display poor performance on small targets.To address the problem, an improved SSD algorithm is proposed for detecting the wear of safety helmets.The algorithm employs the lightweight MobileNet to construct the MobileNet-SSD algorithm, which improves the detection speed.Then the transfer learning strategy is introduced to address the difficulties in model training.Additionally, as the existing data sets of safety helmets are small-sized, which leads to the underfitting of the network, samples of safety helmets are collected from the actual building work videos to construct a suitable sample set.The experimental results show that the proposed algorithm provides a detection speed that is 10.2 times higher than that of the SSD algorithm with the cost of a minor loss in accuracy.

Key words: detection of safety helmet wear, lightweight SSD algorithm, deep learning, detection precision, detection speed

摘要： 针对真实场景下安全帽佩戴检测面临的背景复杂、干扰性强、待检测目标较小等问题，在SSD算法的基础上，提出改进的MobileNet-SSD算法。通过引入轻量型网络MobileNet并构建MobileNet-SSD算法提高检测速度，采用迁移学习策略克服模型训练困难问题。从施工相关视频中获取真实环境下的安全帽样本构建样本集，以解决当前安全帽数据集规模较小、网络难以充分拟合特征的问题。实验结果表明，MobileNet-SSD算法在损失很小精度的情况下，相较于SSD算法，检测速度提高了10.2倍。

关键词: 安全帽佩戴检测, 轻量型SSD算法, 深度学习, 检测精度, 检测速度

CLC Number:

TP391.41

XU Xianfeng, ZHAO Wanfu, ZOU Haoquan, ZHANG Li, PAN Zhuoyi. Detection Algorithm of Safety Helmet Wear Based on MobileNet-SSD[J]. Computer Engineering, 2021, 47(10): 298-305,313.

徐先峰, 赵万福, 邹浩泉, 张丽, 潘卓毅. 基于MobileNet-SSD的安全帽佩戴检测算法[J]. 计算机工程, 2021, 47(10): 298-305,313.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0058733

http://www.ecice06.com/EN/Y2021/V47/I10/298

Figures/Tables 15

References

[1] 李潇.视频识别在HSE监控平台中的研究与应用[D].上海:华东理工大学, 2014. Li X.Research and application of video recognition in HSE monitoring platform[D].Shanghai:East China University of Science and Technology, 2014.(in Chinese)
[2] 刘云波, 黄华.施工现场安全帽佩戴情况监控技术研究[J].电子科技, 2015(4):75-78. LIU Y B, HUANG H.Research on monitoring technology of wearing safety helmet on construction site[J].Electronic Science and Technology, 2015(4):75-78.(in Chinese)
[3] 冯国臣, 陈艳艳, 陈宁, 等.基于机器视觉的安全帽自动识别技术研究[J].机械设计与制造工程, 2015, 44(10):42-45. FENG G C, CHEN Y Y, CHEN N, et al.Research on automatic identification technology of safety helmet based on machine vision[J].Machine Design and Manufacturing Engineering, 2015, 44(10):42-45.(in Chinese)
[4] 杜思远.变电站人员安全帽佩戴识别算法研究[D].重庆:重庆大学, 2015. DU S Y.Research on the recognition algorithm of substation personnel wearing helmet[D].Chongqing:Chongqing University, 2015.(in Chinese)
[5] 赵永强, 饶元, 董世鹏, 等.深度学习目标检测方法综述[J].中国图象图形学报, 2020, 25(4):629-654. ZHAO Y Q, RAO Y, DONG S P, et al.Overview of deep learning target detection methods[J].Journal of Image and Graphics, 2020, 25(4):629-654.(in Chinese)
[6] 刘颖, 刘红燕, 范九伦, 等.基于深度学习的小目标检测研究与应用综述[J].电子学报, 2020, 48(3):590-601. LIU Y, LIU H Y, FAN J L, et al.Overview of the research and application of small target detection based on deep learning[J].Acta Electronica Sinica, 2020, 48(3):590-601.(in Chinese)
[7] CAO J, SONG C, SONG S, et al.Front vehicle detection algorithm for smart car based on improved SSD model[J].Sensors, 2020, 20(16):46-56.
[8] 李欢, 陈先桥, 施辉, 等.基于SSD的行人头部检测方法[J].计算机工程与设计, 2020, 41(3):827-832. LI H, CHEN X Q, SHI H, et al.Pedestrian head detection method based on SSD[J].Computer Engineering and Design, 2020, 41(3):827-832.(in Chinese)
[9] 史文旭, 谭代伦, 鲍胜利, 等.特征增强SSD算法及其在遥感目标检测中的应用[J].光子学报, 2020, 49(1):154-163. SHI W X, TAN D L, BAO S L, et al.Feature-enhanced SSD algorithm and its application in remote sensing target detection[J].Acta Photonica Sinica, 2020, 49(1):154-163.(in Chinese)
[10] 毛先胤, 刘宇, 马晓红, 等.基于SSD算法的电力巡线机器人障碍物识别[J].自动化与仪器仪表, 2020, 247(1):45-48. MAO X Y, L Y, MA H, et al.Obstacle recognition of power line inspection robot based on SSD algorithm[J].Automation and Instrumentation, 2020, 247(1):45-48.(in Chinese)
[11] PENG D, SUN Z, CHEN Z, et al.Detecting heads using feature refine net and cascaded multi-scale architecture[C]//Proceedings of International Conference on Pattern Recognition.Washington D.C., USA:IEEE Press, 2018:2528-2533.
[12] 徐守坤, 王雅如, 顾玉宛, 等.基于改进Faster RCNN的安全帽佩戴检测研究[J].计算机应用研究, 2020, 37(3):901-905. XU S K, WANG Y R, GU Y W, et al.Research on helmet wearing detection based on improved Faster RCNN[J].Application Research of Computers, 2020, 37(3):901-905.(in Chinese)
[13] 方明, 孙腾腾, 邵桢, 等.基于改进YOLOv2的快速安全帽佩戴情况检测[J].光学精密工程, 2018, 27(5):1197-1205. FANG M, SUN T T, SHAO Z, et al.Fast helmet wearing condition detection based on improved YOLOv2[J].Optics and Precision Engineering, 2018, 27(5):1197-1205.(in Chinese)
[14] 王兵, 李文璟, 唐欢, 等.改进Yolo v3算法及其在安全帽检测中的应用[J].计算机工程与应用, 2020, 56(9):33-40. WANG B, LI W J, TANG H, et al.Improved Yolo v3 algorithm and its application in safety helmet detection[J].Computer Engineering and Applications, 2020, 56(9):33-40.(in Chinese)
[15] LI X, QIN Y, WANG F, et al.Pitaya detection in orchards using the MobileNet-YOLO model[C]//Proceedings of the 39th Chinese Control Conference.Washington D.C., USA:IEEE Press, 2020:6274-6278.
[16] ZHANG D, LÜ J, CHENG Z.An approach focusing on the convolutional layer characteristics of the VGG network for vehicle tracking[J].IEEE Access, 2020, 8:112827-112839.
[17] 郭凯.基于SSD的人脸遮挡实时检测方法研究及系统实现[D].南昌:南昌大学, 2019. GUO K.Research on real-time detection method of face occlusion based on SSD and system implementation[D].Nanchang:Nanchang University, 2019.(in Chinese)
[18] 王明芬.基于视频的安全帽检测和跟踪算法研究[J].信息通信, 2020(1):40-42. WANG M F Research on video-based safety helmet detection and tracking algorithm[J].Information and Communication, 2020(1):40-42.(in Chinese)
[19] FUENTES J D, LOSADA G C, CASILLAS P D, et al.Towards dense people detection with deep learning and depth images[EB/OL].[2020-05-21].https://www.researchgate.net/publication/342944677_Towards_Dense_People_Detection_with_Deep_Learning_and_Depth_images.
[20] 王菲菲, 陈磊, 焦良葆, 等.基于SSD-MobileNet的安全帽检测算法研究[J].信息化研究, 2020, 46(3):34-39. WANG F F, CHEN L, JIAO L B, et al.Research on helmet detection algorithm based on SSD-MobileNet[J].Information Research, 2020, 46(3):34-39.(in Chinese)
[21] SARASWATHI S, MADHESWARAN M.Adaptive supervised multi-resolution approach based modeling of performance improvement in satellite image classification[J].Journal of Ambient Intelligence and Humanized Computing, 2020, 43(2):1-11.
[22] SHOU G L, LIU K, QIAO Y, et al.Automatic defect detection based on improved Faster RCNN for substation equipment[J].Journal of Physics, 2020, 1544(1):12157.
[23] HOWARD A, SANDLER M, CHU G, et al.Searching for mobilenetv3[C]//Proceedings of the IEEE International Conference on Computer Vision.Washington D.C., USA:IEEE Press, 2019:1314-1324.

Please choose a citation manager

Content to export