基于自适应注意力机制的YOLOv4无人超市商品检测
YOLOV4 FOR UNMANNDE SUPERMARKET COMMODITY DETECTION BASED ON ADAPTIVE ATTENTION MECHANISM
章超华 1丁胜 2苏浩1
作者信息
- 1. 武汉科技大学计算机科学与技术学院 湖北武汉 430065;智能信息处理与实时工业系统湖北省重点实验室(武汉科技大学) 湖北武汉 430065
- 2. 武汉科技大学计算机科学与技术学院 湖北武汉 430065;智能信息处理与实时工业系统湖北省重点实验室(武汉科技大学) 湖北武汉 430065;福建省大数据管理新技术与知识工程重点实验室(泉州师范学院) 福建泉州 362000
- 折叠
摘要
针对无人超市智能结算任务中商品检测实时性不高、堆叠商品检测效果差、相似商品难分类的问题,提出一种基于YOLOv4改进的商品识别算法.使用轻量级网络MobileNetv2进行特征提取加快检测速度;在Mo-bileNetv2的倒残差结构中引入通道注意力和空间注意力放大局部特征权重,从而加强对堆叠商品的检测能力;在损失函数中使用焦点损失(Focal loss)解决类间差异小的难分类问题.实验结果表明,该方法在自建商品数据集Goods上准确率达到了 80.3%,检测速度达到73帧/s,优于YOLOv4算法.
Abstract
Aimed at the problems of low real-time commodity detection,poor detection of stacked commodities,and difficulties in classifying similar commodities in the intelligent settlement task of unmanned supermarkets,a commodity recognition algorithm based on improved YOLOv4 is proposed.The algorithm used the lightweight network MobileNetv2 for feature extraction to speed up the detection speed.The channel attention and spatial attention were introduced into the inverted residual structure of MobileNetv2 to amplify the local feature weight,and thus enhancing the detection ability of stacked commodities.Focal loss was used in the loss function to solve the difficult classification problem with small inter-class difference.The experimental results show that this method achieves 80.3%accuracy and a detection speed of 73 FPS on self-built product data sets,which is better than the YOLOv4 algorithm.
关键词
无人超市/商品检测/注意力机制/深度可分离卷积Key words
Unmanned supermarket/Commodity detection/Attention mechanism/Depthwise separable convolution引用本文复制引用
基金项目
国家自然科学基金项目(61806150)
福建省大数据管理新技术与知识工程重点实验室开放课题(BD201805)
出版年
2024