基于YOLOv7的垃圾检测方法研究  

Research on Garbage Detection Method Based on YOLOv7

作　　者：陈君 赵小会 王博士 季虹 李维乾 CHEN Jun;ZHAO Xiaohui;WANG Boshi;JI Hong;LI Weiqian(The Shaanxi Key Laboratory of Clothing Intelligence,School of Computer Science,Xi'an Polytechnic University,Xi'an 710048,China)

机构地区：[1]西安工程大学计算机科学学院陕西省服装设计智能化重点实验室,西安710048

出　　处：《计算机测量与控制》2024年第12期1-8,共8页Computer Measurement &Control

基　　金：国家自然科学基金(62106189);陕西省高速公路施工机械重点实验室开放基金(300102250510);西安工程大学科研基金(BS201847)。

摘　　要：随着社会经济的发展,人们的生活水平持续提高,生活垃圾量急剧攀升;为了有效应对垃圾分拣效率低、准确率差等问题,提出一种以YOLOv7网络为基础模型的垃圾检测算法;该算法对YOLOv7网络进行了一系列改造,首先,在Head模块添加了注意力机制SimAM,增强了模型的感知能力和自适应能力,从而提高检测精度;其次,在主干网络中改进了非极大值抑制算法(soft-NMS)去除冗余的检测框,再次改进了损失函数为边框回归损失函数SIoU,提高了检测的精度和速度;最后,采用C3模块替换YOLOv7有的ELAN-W模块,提升网络对较小目标的检测能力;通过数据集对改进的网络进行测试,平均准确度为98.93%,高于原模型的96.31%,实验结果也表明改进算法的检测效果有较为明显的提升。With the development of social economy and the continuous improvement of people's living standard,the amount of domestic garbage has rapidly increased.In order to effectively deal with the low efficiency and poor accuracy of garbage sorting,a garbage detection algorithm based on YOLOv7 network as a base model is proposed.The algorithm made a series of modifications to the YOLOv7 network,firstly,the attention mechanism SimAM was added to the head module,which enhanced the model's perceptual ability and adaptive ability so as to improve the detection accuracy;Secondly,non-maximum suppression(soft-NMS)was replaced in the backbone network to remove redundant detection frames;Then,the loss function was improved to be the edge regression loss function SIoU,improving the accuracy and speed of detection;Finally,the C3 module was used to replace the ELAN-W module in the YOLOv7,promoting the network s detection ability for smaller targets.Through experiment on the data-set,the average accuracy of the improved network is 98.93%,which is better than the 96.31%of the original model.Experimental results show that the improved algorithm has a more obvious enhancement in detection.

关 键 词：深度学习 目标检测 注意力机制 非极大值抑制 垃圾分类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]