[1]李　军,周科宇,邹　军,等.基于改进YOLOv8n的施工场景下防护装备佩戴检测算法[J].郑州大学学报(工学版),2025,46(03):19-25.[doi:10.13705/j.issn.1671-6833.2025.03.002]
　LI Jun,ZHOU Keyu,ZOU Jun,et al.Protective Equipment Wearing Detection Algorithm in Construction Scenarios Based on YOLOv8n[J].Journal of Zhengzhou University (Engineering Science),2025,46(03):19-25.[doi:10.13705/j.issn.1671-6833.2025.03.002]
点击复制

基于改进YOLOv8n的施工场景下防护装备佩戴检测算法()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
46
期数:
2025年03期
页码:
19-25
栏目:
出版日期:
2025-05-13

文章信息/Info

Title:
Protective Equipment Wearing Detection Algorithm in Construction Scenarios Based on YOLOv8n
文章编号:
1671-6833(2025)03-0019-07
作者:
李　军;  周科宇;  邹　军;  曾文炳
重庆交通大学 机电与车辆工程学院,重庆 400074
Author(s):
LI Jun;  ZHOU Keyu;  ZOU Jun;  ZENG Wenbing
School of Mechatronics and Vehicle Engineering,Chongqing Jiaotong University, Chongqing 400074, China
关键词:
防护装备检测;  BiFPN;  LSCD;  EIoU损失;  C2f-ContextGuided模块;  模型轻量化
Keywords:
protective equipment detection;  BiFPN;  LSCD;  EIoU loss;  C2f-ContextGuided module;  model lightweighting
分类号:
TP391.4
DOI:
10.13705/j.issn.1671-6833.2025.03.002
文献标志码:
A
摘要:
针对在施工场景中现有的防护装备检测算法存在受干扰信息影响、光照不均匀以及被作业设备遮挡等问题,提出了一种改进YOLOv8n的轻量化算法YOLO-LA。首先,将加权双向特征金字塔网络BiFPN引入颈部,通过多路径交互融合,提高底层细节和高级语义信息,增强多尺度特征融合性能,提升模型对复杂场景小目标的检测精度;其次,在基线模型中使用C2f-ContextGuided模块对骨干网络进行改造,ContextGuided模块使用全局上下文信息计算权重向量,并使用其细化局部特征和周围上下文特征的联合特征,从而提高模型的特征提取能力,并降低模型复杂度;再次,提出了一种全新的LSCD轻量化检测头,其使用共享卷积,减少模型的参数量和计算量;最后,用EIoU代替了原来的CIoU,优化边框回归,提高了算法收敛速度和回归精度。实验结果表明:YOLO-LA算法在防护装备佩戴检测中表现优异,相比基线模型YOLOv8n,参数量、计算量和模型内存分别降低了61.5%,43.2%和58.7%,同时mAP@0.5提升了1.4百分点,且FPS值为253帧/s,满足防护装备佩戴检测的实时性、准确性和轻量化要求。
Abstract:
In view of the problems of protective equipment detection, such as information interference, uneven illumination and occlusion in the construction scene, a lightweight algorithm with improved YOLOv8n was proposed, which was called YOLO-LA . Firstly, the weighted bidirectional feature pyramid network BiFPN was introduced into the neck, and the underlying details and high-level semantic information were improved through multi-path interactive fusion, the multi-scale feature fusion performance was enhanced, and the detection accuracy of the model for small targets in complex scenes was improved. Secondly, the C2f-ContextGuided module was used to transform the backbone network in the baseline model, and the global context information was used to calculate the weight vector, to refine the joint features of the local features and the surrounding context features, so as to improve the feature extraction ability of the model and reduce the complexity of the model. Then, a new LSCD lightweight detection head was proposed, which used shared convolution to reduce the number of parameters and computations of the model. Finally, EIoU was used to replace the original CIoU, and the border regression was optimized, and the convergence speed and regression accuracy of the algorithm were improved. Compared with the baseline model YOLOv8n, the number of parameters, the amount of computation, and the size of the model were reduced by 61.5%, 43.2% and 58.7%, respectively, and the mAP@0.5 was increased by 1.4 percentage points, and the FPS was 253 frames/s, which could meet the requirements of real-time, accuracy and lightweight of protective equipment wearing detection.

参考文献/References:

[1]王子豪,方成,李丽萍,等.基于热力图预测的免“锚框”人物目标检测算法[J].计算机工程,2024,50 (10):51-60.

WANG Z H, FANG C, LI L P, et al.Anchor-free person target detection algorithm based on heat map prediction [J].Computer Engineering,2024,50(10):51-60. 
[2]GOU S P, WANG X L, MAO S S, et al. Weakly-supervised semantic feature refinement network for MMW concealed object detection[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2023, 33(3): 1363-1373. 
[3]CAO J, LI P H,ZHANG H, et al. An improved YOLOv4 lightweight traffic sign detection algorithm[J]. IAENG International Journal of Computer Science, 2023,50(3): 825-831. 
[4]许德刚, 王露, 李凡. 深度学习的典型目标检测算法研究综述[J]. 计算机工程与应用, 2021, 57(8): 1025. 
XU D G, WANG L, LI F. Review of typical object detection algorithms fordeep learning[J]. Computer Engineering and Applications, 2021, 57(8): 10-25. 
[5]GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2014: 580-587. 
[6]REN S Q, HE K M, GIRSHICK R, et al. Faster RCNN: towards real-time object detection with region proposalnetworks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149. 
[7]HE K M, GKIOXARI G, DOLLÁR P, et al. Mask RCNN[C]∥2017 IEEE International Conference on Computer Vision ( ICCV). Piscataway: IEEE, 2017: 2980-2988. 
[8]ROY A M, BOSE R, BHADURI J. A fast accurate finegrain object detection model based on YOLOv4 deep neural network[J]. Neural Computing and Applications, 2022,34(5): 3895-3921. 
[9]QIAO S Y, CHEN L C, YUILLE A. DetectoRS: detecting objects with recursive feature pyramid and switchable atrous convolution[C]∥2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2021: 10213-10224. 
[10] BIST R, SUBEDIS B, YANG X, et al. A novel YOLOv6 object detector for monitoring piling behavior of cage-free laying hens[J]. Agriengineering,2023,5(2): 905-923. 
[11]WANG C Y, BOCHKOVSKIY A, LIAO H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-theart for real-time object detectors[C]∥2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2023: 7464-7475. 
[12] ZHOU F B, ZHAO H L, NIE Z. Safety helmet detection based on YOLOv5[C]∥2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA). Piscataway: IEEE, 2021: 6-11. 
[13] ZENG L P, DUAN X L, PAN Y H, et al. Research on the algorithm of helmet-wearing detection based on the optimized yolov4[J]. The Visual Computer:International Journal of Computer Graphics, 2023, 39(5): 2165-2175. 
[14] CHENG R, HE X W, ZHENG Z L, et al. Multi-scale safety helmet detection based on SAS-YOLOv3-tiny[J]. Applied Sciences, 2021, 11(8): 3652. 
[15]程换新, 蒋泽芹, 程力, 等. 基于改进YOLOX-S的安全帽反光衣检测算法[J]. 电子测量技术, 2022, 45 (6): 130-135. 
CHENG H X, JIANG Z Q, CHENG L, et al. Helmet andreflective clothing detection algorithm based on improved YOLOX-S[J]. Electronic Measurement Technology, 2022, 45(6): 130-135. 
[16]郑海洋, 宋纯贺, 武婷婷, 等. 面向绝缘手套佩戴状况检测的小目标检测与匹配算法[J]. 小型微型计算机系统, 2023, 44(9): 1989-1995. 
ZHENG H Y, SONG C H, WU T T, et al. Small target detection and matching algorithm for wearing condition detection of insula-ting gloves[J]. Journal of ChineseComputer Systems, 2023, 44(9): 1989-1995. 
[17] TAN M X, PANG R M, LEQ V. EfficientDet: scalable and efficient object detection[C]∥2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2020: 10781-10790. 
[18] ZHANG Y F, REN W Q, ZHANG Z, et al. Focal and efficient IOU loss for accurate bounding box regression [J]. Neurocomputing, 2022, 506: 146-157. 
[19] GHIASI G, LIN T Y, LE Q V. NAS-FPN: learning scalable feature pyramid architecture for object detection[C] ∥2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway: IEEE, 2019: 7036-7045. 
[20]WU T Y, TANG S, ZHANG R, et al. CGNet: a lightweight context guided network for semantic segmentation [J]. IEEE Transactions on Image Processing,2021,30: 1169-1179. 
[21]WU Y X, HE K M.Group normalization[J]. International Journal of Computer Vision. 2020,128(3):742-755. 
[22] ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 12993-13000.

相似文献/References:

[1]张 震,王晓杰,晋志华,等.基于轻量化 YOLOv5 的交通标志检测[J].郑州大学学报(工学版),2024,45(02):12.[doi:10.13705/j.issn.1671-6833.2023.05.041]
　ZHANG Zhen,WANG Xiaojie,JIN Zhihua,et al.Traffic Sign Detection Based on Lightweight YOLOv5[J].Journal of Zhengzhou University (Engineering Science),2024,45(03):12.[doi:10.13705/j.issn.1671-6833.2023.05.041]

更新日期/Last Update: 2025-05-22