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

作　　者：侯维岩[1] 靳东安 王高杰 王洋 丁英强[1] Hou Weiyan;Jin Dongan;Wang Gaojie;Wang Yang;Ding Yingqiang(School of Information Engineering,Zhengzhou University,Zhengzhou 450001,China;Guangdong Shunde Innovative Design Institute,Foshan 528311,China)

机构地区：[1]郑州大学信息工程学院,郑州450001 [2]广东顺德创新设计研究院,佛山528311

出　　处：《电子测量与仪器学报》2021年第10期217-224,共8页Journal of Electronic Measurement and Instrumentation

基　　金：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。

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。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.

关 键 词：商品识别 YOLOv3 k-means++ 深度可分离卷积 倒置残差结构 CIoU 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]