改进YOLOX的夜间安全帽检测算法

doi:10.3778/j.issn.1002-8331.2305-0087

摘要/Abstract

摘要： 安全帽检测是保障建筑施工现场安全的一个有效手段。为保证暗光条件下图像分辨度，塔机吊钩摄像头夜间经常需采集灰度图像。由于摄像头晃动和人员走动，安全帽目标区域还经常会出现模糊现象。为解决模糊灰度图像中目标特征丢失所导致的检测精度下降问题，以YOLOX为基准模型，提出一种用于夜间安全帽检测的特征增强和回归权重自适应YOLOX（feature enhancement and regression weight adaptive，FERWA-YOLOX）算法。算法在输入层增加了融合不同大小感受野的多尺度残差（multi-scale residuals，MSR）模块，在同层网络中融合更多局部特征，降低目标局部模糊带来的影响；在解耦头的分类分支增加并行池化通道注意力（parallel pooling channel attention，PPCA）模块，弥补因目标颜色特征丢失所导致的网络分类能力的下降；设计了一种带双惩罚项的损失函数（double penalty items-Siou，DPI-Siou），自适应地降低形状固定目标的形状损失和模糊目标在回归时的权重，提高网络的检测精度。实验结果表明，FERWA-YOLOX较原YOLOX算法，mAP提升了4.88个百分点，参数量仅提升0.5?MB，且满足夜间实时检测需求。

关键词: 夜间目标检测, 安全帽检测, 感受野, 通道注意力, 损失函数

Abstract: Helmet detection is an effective means to ensure the safety of construction sites. In order to ensure the image resolution under dark light conditions, the tower crane hook camera often needs to collect grayscale images at night. Additionally, helmet target areas are often blurred due to camera shake and people moving around. In order to solve the problem of detection accuracy drop caused by the loss of target features in fuzzy grayscale images, using YOLOX as the baseline model, a feature enhancement and regression weight adaptive YOLOX (FERWA-YOLOX) algorithm for night helmet detection is proposed. The algorithm adds a multi-scale residual (MSR) module that fuses different sizes of receptive fields to the input layer, integrate more local features in the same layer network to reduce the impact of local blurring of the target. The algorithm also adds a parallel pooling channel attention (PPCA) module to the classification branch of the decoupling head, makes up for the decline in network classification ability caused by the loss of target color features. A loss function with double penalty items (DPI-Siou) is designed to adaptively reduce the shape loss of fixed-shape objects and the weight of fuzzy objects in regression, and improve the detection accuracy of the network. The experimental results show that, compared with the original YOLOX algorithm, the mAP of FERWA-YOLOX has increased by 4. 88 percentage points, and the parameter volume has only increased by 0.5 MB, which meets the needs of real-time detection at night.

Key words: target detection at night, safety helmet testing, receptive field, channel attention, loss function

韩贵金, 王瑞萱, 徐午言, 李君. 改进YOLOX的夜间安全帽检测算法[J]. 计算机工程与应用, 2024, 60(15): 180-188.

HAN Guijin, WANG Ruixuan, XU Wuyan, LI Jun. Improved YOLOX Night Helmet Detection Algorithm[J]. Computer Engineering and Applications, 2024, 60(15): 180-188.

参考文献

[1] 刘晓慧, 叶西宁. 肤色检测和Hu矩在安全帽识别中的应用[J]. 华东理工大学学报 (自然科学版), 2014, 40(3): 365-370.
LIU X H, YE X N. Skin color detection and Hu moments in helmet recognition research[J]. Journal of East China University of Science and Technology (Natural Science Edition), 2014, 40(3): 365-370.
[2] HAO W A, JZA B. An intelligent vision-based approach for helmet identification for work safety-ScienceDirect[J]. Computers in Industry, 2018, 100: 267-277.
[3] 宋晓凤, 吴云军, 刘冰冰, 等. 改进YOLOv5s算法的安全帽佩戴检测[J]. 计算机工程与应用, 2023, 59(2): 194-201.
SONG X F, WU Y J, LIU B B, et al. Improved YOLOv5s algorithm for helmet wearing detection[J]. Computer Engineering and Applications, 2023, 59(2): 194-201.
[4] FU D S, GAO L, HU T, et al. Research on safety helmet detection algorithm of power workers based on improved YOLOv5[J]. Journal of Physics (Conference Series), 2022, 2171: 012006.
[5] 谢国波, 唐晶晶, 林志毅, 等. 复杂场景下的改进YOLOv4安全帽检测算法[J]. 激光与光电子学进展, 2023, 60(12): 129-137.
XIE G B, TANG J J, LIN Z Y, et al. Improved YOLOv4 helmet detection algorithm under complex scenarios[J]. Laser & Optoelectronics Progress, 2023, 60(12): 129-137.
[6] YOHANANDAN S, SONG A, DYER A G, et al. Saliency preservation in low-resolution grayscale images[C]//European Conference on Computer Vision. Cham: Springer, 2018.
[7] 刘明康, 王宏民, 李琦, 等. 增强型灰度图像空间实现虹膜活体检测[J]. 中国图象图形学报, 2020, 25(7): 1421-1435.
LIU M K, WANG H M, LI Q, et al. Enhanced gray-level image space for iris liveness detection[J]. Journal of Image and Graphics, 2020, 25(7): 1421-1435.
[8] 刘金花. 基于卷积神经网络的模糊图像微小目标检测方法[J]. 信息记录材料, 2022, 23(6): 243-245.
LIU J H. A convolutional neural network-based method for detecting tiny targets in fuzzy images[J]. Information Recording Materials, 2022, 23(6): 243-245.
[9] TIAN Z, SHEN C, CHEN H, et al. FCOS: fully convolutional one-stage object detection[C]//Proceedings of the IEEE International Conference on Computer Vision, 2019: 9627-9636.
[10] GE Z, LIU S, WANG F, et al. YOLOX: exceeding YOLO series in 2021[J]. arXiv:2107.08430, 2021.
[11] 刘向增, 徐雪灵, 刘如意, 等. 面向图像匹配的局部特征提取研究进展[J]. 计算机技术与发展, 2022, 32(2): 1-13.
LIU X Z, XU X L, LIU R Y, et al. Research progress of local feature extraction for image matching[J]. Computer Technology and Development, 2022, 32(2): 1-13.
[12] SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015.
[13] EVERINGHAM M, VAN GOOL L, WILLIAMS C K, et al. The pascal visual object classes (VOC) challenge[J]. International Journal of Computer Vision, 2010: 303-338.
[14] HU J, SHEN L, SUN G, et al. Squeeze-and-excitation networks[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018.
[15] LIN M, CHEN Q, YAN S C. Network in network[J]. IEEE Transactions on Information Theory, 1999, 45(2): 399-406.
[16] REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019: 658-666.
[17] GEVORGYAN Z. SIoU loss: more powerful learning for bounding box regression[J]. Computer Vision and Pattern Recognition, 2020, 30(8): 1742-1754.