Computer Engineering and Applications ›› 2024, Vol. 60 ›› Issue (6): 230-237.DOI: 10.3778/j.issn.1002-8331.2210-0353

• Graphics and Image Processing • Previous Articles     Next Articles

Small Target-Oriented Multi-Space Hierarchical Helmet Detection

LI Jiaxin, HU Yang, HUANG Xiezhou, LI Hongjun   

  1. 1.School of Information Science and Technology, Nantong University, Nantong, Jiangsu 226019, China
    2.Chang Chien College, Nantong University, Nantong, Jiangsu 226019, China
    3.State Key Laboratory for Novel Software Technology at Nanjing University, Nanjing 210093, China
  • Online:2024-03-15 Published:2024-03-15

面向小目标的多空间层次安全帽检测

李嘉信,胡杨,黄协舟,李洪均   

  1. 1.南通大学 信息科学技术学院,江苏 南通 226019
    2.南通大学 张謇学院,江苏 南通 226019
    3.南京大学 计算机软件新技术国家重点实验室,南京 210093

Abstract: As there are factors affecting the detection effect such as small targets and distances in the target video, it is difficult to capture small targets. A multi-spatial hierarchical helmet wearing detection algorithm for small targets is proposed in the article, which will be personalized and improved on the basis of Yolov5s network model. Firstly, a multi-spatial attention module is designed to consider the effects of spatial features from different perspectives and fuse them to enhance the spatial location relationships of salient features. Secondly, features at multiple spatial scales are fused while combining multiple features in the feature extraction process to adapt to the capture of targets at different spatial levels and improve the detection of small targets. Thirdly, data augmentation is used to improve the generalizability of the dataset to adapt the training targets to more diverse scenarios. Finally, the loss function is optimized to enhance the regression capability and improve the training effect. The experimental results show that the proposed algorithm achieves an average accuracy of 91.5%, significantly reducing the number of missed detections. In addition, the proposed algorithm has been deployed to real construction sites and has shown superior performance in detecting small targets, which is of great value for application.

Key words: helmet detection, Yolov5s, multi-spatial attention module, data augmentation, multi-spatial scale fusion

摘要: 由于目标视频中存在目标小、距离远等影响检测效果的因素,对小目标的捕捉难度较大,提出一种面向小目标的多空间层次安全帽佩戴检测算法,该算法将在Yolov5s的网络模型基础上进行个性化改进。设计一种多空间注意力模块,从不同角度考虑空间特征的效果并加以融合,加强显著性特征的空间位置关系;融合多空间尺度的特征,同时结合特征提取过程中的多种特征,适应对不同空间层次目标的捕捉,提高对小目标的检测能力;利用数据增强提高数据集的泛用性,使训练目标适应更多样的情景;优化损失函数,增强回归能力,提高训练效果。实验结果表明,所提算法的平均准确率达到91.5%,明显地减少了漏检情况。除此之外,将其部署到实际施工现场,展现了出对小目标优越的检测性能,具有极大的应用价值。

关键词: 安全帽检测, Yolov5s, 多空间注意力模块, 数据增强, 多空间尺度融合