改进YOLOv7的煤岩图像检测算法
Coal rock image detection algorithm based on improved YOLOv7
赵艳芹 1邓虎诚1
作者信息
- 1. 黑龙江科技大学 计算机与信息工程学院,哈尔滨 150022
- 折叠
摘要
针对现阶段煤岩图像检测识别中精度和模型规模难以平衡的问题,提出了一种通过替换部分普通卷积模块来改进YOLOv7 网络结构的煤岩图像检测算法.通过引入卷积核为7 的卷积模块ConvNeXt来替换普通的3×3 大小卷积模块,提升煤炭特征获得效果.利用SimAM注意力机制,替换1×1 大小卷积模块,给出MP_SAM模块,使算法提取更丰富的目标信息,运用αIoU优化损失函数,使之更适用于清晰度不够高的煤岩图像,增强算法的泛化能力.结果表明,与YOLOv7 算法相比,该算法的准确率提升了 3.9%,mAP 提升了 1.5%,模型整体 FLOPs 减少了0.7 G,通过更小的模型,获得了更好的检测结果.
Abstract
This paper proposes a coal rock image detection algorithm for improving YOLOv7 network structure by replacing some ordinary convolution modules,which is designed to address the problem that is hard to balance the accuracy and model scale in current coal rock image detection.The study is accom-plished by introducing ConvNeXt with a convolution kernel by 7 to replace the ordinary convolution mod-ule with the size 3×3 for improving the coal characteristics and obtaining the effect;using SimAM atten-tion mechanism to replace convolutional modules with the size 1×1 for creating MP_SAM modules to ena-ble the algorithm to extract more target information;optimizing the loss function by using αIoU to make it more suitable for coal rock images with insufficient clarity,and enhance the generalization ability of the algorithm.The experimental results show that,compared with YOLOv7 algorithm,the accuracy of the al-gorithm increases by 3.9%,the mAP increases by 1.5%,the overall FLOPs of the model are reduced by 0.7 G,and the detection results are better obtained by using the smaller model.
关键词
煤岩检测/YOLOv7/SimAM/ConvNeXt/αIoUKey words
coal rock detection/YOLOv7/SimAM/ConvNeXt/αIoU引用本文复制引用
基金项目
黑龙江省省属高等学校基本科研业务费项目(2022-KYYWF-0565)
出版年
2024
国家科技期刊平台
NSTL
万方数据