[1]魏宏彬,张端金,杜广明,等.基于改进型YOLO v3的蔬菜识别算法[J].郑州大学学报(工学版),2020,41(02):7-12.[doi:10.13705/j.issn.1671-6833.2020.03.002]
 Wei Hongbin,Zhang Duanjin,Du Guangming,et al.Vegetable Detection Algorithm Based on Improved YOLO v3[J].Journal of Zhengzhou University (Engineering Science),2020,41(02):7-12.[doi:10.13705/j.issn.1671-6833.2020.03.002]
点击复制

基于改进型YOLO v3的蔬菜识别算法()
分享到:

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
41
期数:
2020年02期
页码:
7-12
栏目:
出版日期:
2020-05-31

文章信息/Info

Title:
Vegetable Detection Algorithm Based on Improved YOLO v3
作者:
魏宏彬张端金杜广明肖文福
郑州大学信息工程学院
Author(s):
Wei HongbinZhang DuanjinDu GuangmingXiao Wenfu
School of Information Engineering, Zhengzhou University
关键词:
蔬菜识别K-means卷积神经网络特征金字塔YOLOv3
Keywords:
Vegetable identificationK-meansconvolutional neural networkfeature pyramidYOLOv3
DOI:
10.13705/j.issn.1671-6833.2020.03.002
文献标志码:
A
摘要:
针对超市的散装蔬菜区排队称重问题(称重设备能够自动识别蔬菜种类将有效地提高超市的 运行效率),提出一种基于改进型 YOLOv3的蔬菜识别方法。 首先,利用高清摄像头以及网络爬虫技术 采集蔬菜图片;其次,通过 K-means 聚类分析得到 15组适应于蔬菜数据集的先验框;再次,采用一种新 的边界框回归损失函数 DIoU 来提高检测任务的精度;最后,因蔬菜数据集中的大目标较多,通过增强特 征提取网络,获取 5组不同尺度的特征构成特征金字塔从而实现蔬菜识别任务。 改进型YOLOv3算法 在测试集上的平均精度 mPA 达到 93.2%,识别速度是 35f·s-1。 该方法在保证实时检测目标的同时提 升了识别的平均精度。
Abstract:
The queuing and weighing problem was common in bulk vegetable area of supermarket. If weighingequipment could automatically recognize vegetable, it would effectively improve the operational efficiency ofsupermarket. Therefore, a vegetable recognition method based on improved YOLOv3 was proposed. Firstly ,vegetable pictures were collected by using high-definition camera and web crawler technology. Secondly, 15groups of anchors suitable for vegetable datasets were obtained by K -means clustering analysis. Thirdly, a newbounding box regression loss function DIoU was proposed to improve the precision of detection task. Finally, asthere were many large objects in vegetable datasets, 5 groups of feature pyramids with different scales were ob-tained by enhancing feature extraction network to realize vegetable detection task. The mAP of the improvedYOLOv3 algorithm on the test dataset was 93. 2%, and the recognition rate was 35 fps. This method improvedthe recognition of mAP while guaranteeing real-time object detection.
更新日期/Last Update: 2020-05-30