程书帅,王霄,李伟,等.基于改进YOLOv4的轻量级目标检测算法研究[J]. 微电子学与计算机,2023,40(6):1-8. doi: 10.19304/J.ISSN1000-7180.2022.0447
引用本文: 程书帅,王霄,李伟,等.基于改进YOLOv4的轻量级目标检测算法研究[J]. 微电子学与计算机,2023,40(6):1-8. doi: 10.19304/J.ISSN1000-7180.2022.0447
CHENG S S,WANG X,LI W,et al. Research on lightweight target detection algorithm based on improved YOLOv4[J]. Microelectronics & Computer,2023,40(6):1-8. doi: 10.19304/J.ISSN1000-7180.2022.0447
Citation: CHENG S S,WANG X,LI W,et al. Research on lightweight target detection algorithm based on improved YOLOv4[J]. Microelectronics & Computer,2023,40(6):1-8. doi: 10.19304/J.ISSN1000-7180.2022.0447

基于改进YOLOv4的轻量级目标检测算法研究

Research on lightweight target detection algorithm based on improved YOLOv4

  • 摘要: 针对YOLOv4目标检测算法在一些应用场景的参数多、网络复杂、精度低等问题,提出一种改进的轻量级的目标检测算法GD-YOLO. 首先,通过使用轻量级网络GhostNet替换掉YOLOv4的主干特征提取网络CSPDarknet,GhostNet网络极大降低了算法的参数量及计算量,使得算法更加轻量化;其次,提出双重注意力机制(DATM),其不仅增强模型对空间和通道上的特征进行加强,而且其结构参数量小,使用在对主干网络提取出来的三个有效特征层添加双重注意力机制,让模型对特征提取更加有效;最后,新增ACON激活函数代替原有的GhostNet网络中的ReLU激活函数,进一步提高算法检测精度. 在VOC2007+2012数据集上的实验结果表明,GD-YOLO算法的平均准确率(mAP)达到84.28%,与YOLOv4算法相比提升了4个百分点,与YOLOv5算法相比低了大约1个百分点;从模型参数量方面,与YOLOv4算法相比减少了11 M,与YOLOv5相比减少3 M. 所提GD-YOLO算法相对于YOLOv4不仅减少了模型参数量,而且也保存了较高的平均准确率,表明该算法是更具有轻量化及高准确率的.

     

    Abstract: Aiming at the problems of YOLOv4 target detection algorithm in some application scenarios with too many parameters, complex network and low accuracy, an improved lightweight target detection algorithm GD-YOLO was proposed. Firstly, the main feature extraction network of YOLOv4, CSPDarknet, is replaced by the lightweight network GhostNet, which greatly reduces the number of parameters and computation of the algorithm and makes the algorithm more lightweight. Secondly, the double attention mechanism (DATM) is proposed, which not only strengthens the spatial and channel features of the model, but also has a small number of structural parameters. The double attention mechanism is added to the three effective feature layers extracted from the backbone network to make the model more effective for feature extraction. Finally, ACON activation function was added to replace ReLU activation function in GhostNet network to further improve the detection accuracy of the algorithm. Experimental results on VOC2007+2012 data set show that the GD-YOLO algorithm has an average accuracy (mAP) of 84.28%, which is 4 percentage points higher than YOLOv4 algorithm and about 1 percentage point lower than YOLOv5 algorithm. Compared with YOLOv4 algorithm, the number of model parameters is reduced by 11M, and 3M compared with YOLOv5 algorithm. Compared with YOLOv4, the proposed GD-YOLO algorithm not only reduces the number of model parameters, but also preserves a higher average accuracy, indicating that the algorithm is more lightweight and has higher accuracy.

     

/

返回文章
返回