%0 Journal Article
%T 改进YOLOv7的地下工程衬砌表观病害检测算法<br>The Apparent Disease Detection Algorithm of Underground Engineering Lining of YOLOv7 Was Improved
%A 石朱林
%A 陶为戈
%A 孙志刚
%J Artificial Intelligence and Robotics Research
%P 290-299
%@ 2326-3423
%D 2024
%I Hans Publishing
%R 10.12677/airr.2024.132031
%X 针对地下工程衬砌表观病害检测精度低的问题，给出了一种改进YOLOv7的衬砌表观病害检测算法。该算法首先在主干网络输出位置各自加入CBAM注意力机制，用于加强主干网络对关键区域的特征提取能力；其次将无参数注意力机制SimAM引入到SPPCSPC模块中，并裁剪掉冗余的一层CBS模块，在增强主干网络对密集小目标的特征提取能力的同时，缩减计算量和参数规模；最后使用自制数据集训练算法模型，与原算法相比本算法的<i>P</i>、<i>R</i>以及<i>mAP</i>0.5分别提升了12.7、5.4和8.6个百分点。实验结果表明本文改进方法有效地提升了算法对衬砌表观病害的检测性能。<br />
Aiming at the low detection accuracy of underground engineering lining apparent disease, an improved YOLOv7 algorithm for lining apparent disease detection is presented. Firstly, CBAM attention mechanism is added to each output position of the backbone network to enhance the feature extraction capability of the backbone network for key regions. Secondly, the non-parametric attention mechanism SimAM is introduced into SPPCSPC module, and the redundant CBS module is cut out, which enhances the feature extraction ability of the backbone network for dense small targets, and reduces the computation and parameter scale. Finally, the algorithm model is trained with self-made data set. Compared with the original algorithm, the <i>P</i>, <i>R</i> and <i>mAP</i>0.5 of the proposed algorithm are improved by 12.7, 5.4 and 8.6 percentage points respectively. The results show that the improved method can effectively improve the detection performance of the algorithm on the apparent diseases of the lining.
%K YOLOv7，SPPFCSPC，衬砌病害，注意力机制<br>YOLOv7
%K SPPFCSPC
%K Lining Disease
%K Attention Mechanism
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=87358