基于改进YOLOX的垃圾分类检测方法  

Garbage Classification and Detection Method Based on Improved YOLOX

作　　者：欧阳飞 吴旭[1] 向东升 OUYANG Fei;WU Xu;XIANG Dong-sheng(Department of Computer and Network Security(Oxford Brookes University),Chengdu University of Technology,Chengdu 610059,China)

机构地区：[1]成都理工大学计算机与网络安全学院(牛津布鲁克斯大学),四川成都610059

出　　处：《计算机与现代化》2023年第8期68-73,共6页Computer and Modernization

摘　　要：垃圾分类回收可以改善环境污染问题,保护居民的生活环境,保证生态可持续发展,然而传统的人工垃圾分类方法效率低、主观性强,本文提出一种基于改进YOLOX的垃圾分类检测方法,用于提高垃圾分类的效率和准确率。通过自制垃圾分类数据集训练YOLOX网络,实现垃圾的检测和分类。为了取得更好的检测效果,在网络中引入ECA注意力机制,提高特征间的信息传播能力;改进特征提取网络的上采与下采样倍数,提高网络对小目标的特征提取能力;改进分类与回归损失函数,提高网络的学习能力。实验结果表明,改进YOLOX算法的mAP@0.75为89.9%,比原算法提高了4个百分点,而每秒检测帧数仅下降0.3,在不损失性能的情况下,检测精度有明显的提升。Garbage classification and recycling can improve environmental pollution,protect residents’living environment and ensure sustainable ecological development.However,traditional artificial garbage classification methods are inefficient and sub‐jective.This paper proposes a garbage classification and detection method based on improved YOLOX to improve the efficiency and accuracy of garbage classification.By training YOLOX network on self-made garbage classification dataset,garbage detec‐tion and classification have been realized.In order to achieve better detection effect,ECA attention mechanism is introduced into the network to improve the information transmission ability between features.Improving the up sampling and down sampling times of the feature extraction network to improve the feature extraction ability of small targets.The classification and regression loss functions are improved to improve the learning ability of the network.The experimental results show that the mAP@0.75 of the im‐proved YOLOX algorithm is 89.9%,which is 4 percentage points higher than that of the original algorithm,and the number of de-tected frames per second only decreases by 0.3.The detection accuracy is significantly improved without loss of performance.

关 键 词：YOLOX 目标检测 垃圾分类 注意力机制 深度学习 

分 类 号：P391.41[天文地球—地球物理学]