首页|面向多目标医疗垃圾分类的智能识别分拣系统设计

面向多目标医疗垃圾分类的智能识别分拣系统设计

扫码查看
原文链接
  • 万方数据
  • 维普
医疗垃圾中存在大量的病毒和细菌,为解决医疗垃圾源头智能分类问题,开发了基于机器视觉和Delta机构的智能分拣平台样机,并提出一种三阶段的多目标医疗垃圾识别分拣(medical waste recognition-in-dexes-sorting,MWRIS)算法.第 1 阶段提出数据增强扩容的IE-YOLOv4 算法建立起医疗垃圾识别模型,与Faster R-CNN、RetinaNet、CenterNet等 5 种模型比较;第 2 阶段索引分类模型用于管理分类规则;第 3 阶段定位分拣算法指导目标定位分拣.在集成了MWRIS算法的分拣样机上,采集 14 种,2 217 张医疗样本图像,完成医疗垃圾分拣实验.结果表明,使用IE-YOLOv4 的MWRIS算法对医疗垃圾识别准确率显著提升至 99.30%,分拣实验对目标定位准确率达到96.17%,最终分类正确率为86.67%,验证了多目标医疗垃圾识别分拣系统的有效性.
Design of an intelligent identification and sorting system used for classification of multiobjective medical waste
Medical waste contains lots of viruses and bacteria.To intelligently sort medical waste from the source,an in-telligent sorting platform based on machine vision and the Delta mechanism was developed,and a three-stage multiob-jective recognition-indexes-sorting(MWRIS)algorithm was proposed.In the first stage,the IE-YOLOv4 algorithm of data enhancement and expansion was proposed to establish a medical waste identification model,which was compared with five models,including Faster R-CNN,RetinaNet,and CenterNet.In the second stage,the index classification mod-el was used to manage the classification rules.In the third stage,the positioning sorting algorithm was used to guide tar-get positioning and grabbing.For the sorting prototype integrated with the MWRIS algorithm,2 217 medical sample im-ages of 14 kinds were collected,and the medical waste sorting experiment was completed.The results showed that the MWRIS algorithm using IE-YOLOv4 can significantly improve the accuracy of medical waste identification to 99.30%,the accuracy rate of target positioning in the sorting experiment reaches 96.17%,and the final classification accuracy reaches 86.67%,verifying the effectiveness of the proposed medical waste identification and sorting system.

machine visionobject detectionDelta sorting systemmechanical designartificial intelligencemedical wastegarbage classificationintelligent dustbin

张歆羽、杨钟亮、周哲画、张凇、毛新华

展开 >

东华大学 机械工程学院,上海 201620

青岛虚拟现实研究院有限公司,山东 青岛 266100

曼彻斯特大学,曼彻斯特 M13 9PL

北京中丽制机工程技术有限公司,北京 101111

展开 >

机器视觉 目标检测 Delta分拣系统 机械设计 人工智能 医疗垃圾 垃圾分类 智能垃圾箱

国家自然科学基金浙江省健康智慧厨房系统集成重点实验室开放基金

519051752014E10014

2024

10.11992/tis.202204039

智能系统学报
中国人工智能学会　哈尔滨工程大学

智能系统学报

CSTPCD北大核心
影响因子：0.672
ISSN：1673-4785
年,卷(期)：2024.19(3)
  • 5