College of Computer Science and Technology(College of Data Science), Taiyuan University of Technology

【目的】针对现有交通标志检测算法中的较大计算量和较高参数量的问题,提出一种改进YOLOv7的轻量化交通标志检测算法。【方法】该算法分为输入、提取特征的骨干网络、融合特征的颈部网络和对目标进行预测的头部网络4个部分。在骨干网络引入大核卷积,增大了有效感受野,提升了骨干网络提取特征的能力;检测颈部融合坐标注意力、随机池化等方法,既能构建通道注意力又能捕捉准确位置,同时提升网络的泛化能力;此外,提出集中综合深度可分离卷积模块,在减少参数量的同时更好地提取图像特征。【结果】实验结果表明,本文算法在CCTSDB2021数据集上的检测精度达到了93.13%,mAP也达到了87.59%,相较于同类型的方法有了较大的提高,该网络在较低的参数量和计算量的情况下实现了较高的精确率,不仅能够精准地捕捉交通标志的位置信息,同时能够准确地对交通标志进行预测。

【Purposes】 Aiming at the problems of large computation and high reference quanti-ty in existing traffic sign detection algorithms, in this paper we proposed a lightweight traffic sign detection algorithm based on improved YOLOv7. 【Methods】 The algorithm is divided into four parts: input, backbone network of feature extraction, neck network of feature fusion, and head network of target prediction. Large kernel convolution was introduced into the backbone net-work, which increases the effective receptive field and improves the ability of feature extraction. The detection of neck fusion coordinate attention, random pooling, and other methods can not only build channel attention and capture accurate position, but also improve the generalization a-bility of the network. In addition, a comprehensive depth-separable convolution module was pro-posed to extract image features by reducing the number of parameters and the radical sign. 【Re-sults】 Experimental results show that the detection accuracy of the proposed algorithm on the CCTSDB2021 data set reaches 93.13%, and mAP also reaches 87.59%, which is a great im-provement with respect to other methods of the same type. The network achieves a high accuracy rate under the condition of low parameter number and calculation amount, which can not only ac-curately capture the location information of traffic signs, but also achieve a high accuracy rate. At the same time, it can accurately predict the traffic signs.

国家自然科学基金资助项目(61703299,62102279)

李禹纬,付锐,刘帆.改进 YOLOv7的轻量化交通标志检测算法[J].太原理工大学学报,2024,55(1):195-203.

LI Yuwei,FU Rui,LIU Fan.A lightweight traffic sign detection algorithm based on improved YOLOv7[J].Journal of Taiyuan University of Technology,2024,55(1):195-203.