电子测量与仪器学报

侯维岩,靳东安,王高杰,王洋,丁英强.基于嵌入式系统的智能售货柜目标检测算法[J].电子测量与仪器学报,2021,35(10):217-224

基于嵌入式系统的智能售货柜目标检测算法

Object detection algorithm of intelligent vending cabinet via embedded system

DOI：

中文关键词: 商品识别 YOLOv3 k-means++ 深度可分离卷积倒置残差结构 CIoU

英文关键词:commodity recognition YOLOv3 k-means++ depth separable convolution inverted residual structure CIoU

基金项目:国家自然科学基金重大研究计划（92067106）、广东省科技创新战略专项资金（纵向协同管理方向）（2018FS05020102）、佛山市高质量专利培育（1920025003148）项目资助

作者	单位
侯维岩	1. 郑州大学信息工程学院
靳东安	1. 郑州大学信息工程学院
王高杰	2. 广东顺德创新设计研究院
王洋	2. 广东顺德创新设计研究院
丁英强	1. 郑州大学信息工程学院

Author	Institution
Hou Weiyan	1. School of Information Engineering, Zhengzhou University
Jin Dongan	1. School of Information Engineering, Zhengzhou University
Wang Gaojie	2. Guangdong Shunde Innovative Design Institute
Wang Yang	2. Guangdong Shunde Innovative Design Institute
Ding Yingqiang	1. School of Information Engineering, Zhengzhou University

摘要点击次数: 685

全文下载次数: 649

中文摘要:

针对普通商品识别算法在智能售货柜嵌入式系统平台上检测速度慢、识别率低的问题,提出了一种在 YOLOv3 基础上的改进型商品识别算法 DS_YOLOv3。利用 k-means++聚类算法得到适应于售货柜中售卖饮料图像数据的先验框;采用深度可分离卷积替换标准卷积,并加入倒置残差模块重构 YOLOv3 算法,减少了计算复杂度使其能在嵌入式平台实时检测;同时引入 CIoU 作为边界框回归损失函数,提高目标图像定位精度,实现了对传统 YOLOv3 算法的改进。在计算机工作站和 Jeston Xavier NX 嵌入式平台上进行了典型场景下的商品检测实验。实验结果表明,DS_YOLOv3 算法 mAP 达到了 96. 73%,在 Jeston Xavier NX 平台上实际检测的速率为 20. 34 fps,满足了基于嵌入式系统平台的智能售货柜对实时性和商品识别精度的要求。

英文摘要:

In order to solove the problem of slow detection speed and low recognition rate of common commodity recognition algorithms on the intelligent vending cabinet embedded system platform, an improved commodity recognition algorithm DS_YOLOv3 is proposed on the basis of YOLOv3. The traditional YOLOv3 neural network algorithm is improved by obtaining a prior bounding box suited for the image data of beverages sold in the vending cabinet by using k-means++ clustering algorithm, using the deep separable convolution to replace the standard convolution and adding the inverted residual module to reconstruct the YOLOv3 algorithm, which could reduce the computational complexity and enable real-time detection on the embedded platform, and introducing CIoU as the bounding box regression loss function to enhance the accuracy of target image positioning. The commodity testing experiment under typical scenarios is performed on a computer workstation and Jeston Xavier NX embedded platform. The results show that the accuracy of DS _YOLOv3 algorithm reaches 96. 73%, and the actual detection rate on the Jeston Xavier NX platform is 20. 34 fps, which meet the real-time and commodity detection recognition accuracy requirements of the intelligent vending cabinet based on the embedded system platform.

查看全文查看/发表评论下载PDF阅读器