基于Halcon和AlexNet网络的自主叉车托盘检测

2021 International Conference on Internet, Education and Information Technology (IEIT) Pub Date : 2021-04-01 DOI:10.1109/IEIT53597.2021.00025

F. Jia, Zhaosheng Tao, Fusong Wang

{"title":"基于Halcon和AlexNet网络的自主叉车托盘检测","authors":"F. Jia, Zhaosheng Tao, Fusong Wang","doi":"10.1109/IEIT53597.2021.00025","DOIUrl":null,"url":null,"abstract":"Pallet detection is the key step of cargo handling for autonomous forklifts. Due to the influence of complex background, the recognition rate of pallet detection is low. In order to improve the recognition rate, a pallet detection method based on point cloud is proposed. In this method, time-of-flight (ToF) camera is used to collect the point cloud. AlexNet network which is provided by Halcon software is used for deep learning, and deep learning is used to extract the region of interest of pallet contour. The extracted region of interest is processed to obtain the regions of the pallet contour, and the pallet center is solved. The experimental results show that the precision of pallet detection can reach 92.0%. This method has high recognition rate in complex background, and has reference value for the design of pallet detection system of autonomous forklifts.","PeriodicalId":321853,"journal":{"name":"2021 International Conference on Internet, Education and Information Technology (IEIT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Pallet Detection Based on Halcon and AlexNet Network for Autonomous Forklifts\",\"authors\":\"F. Jia, Zhaosheng Tao, Fusong Wang\",\"doi\":\"10.1109/IEIT53597.2021.00025\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Pallet detection is the key step of cargo handling for autonomous forklifts. Due to the influence of complex background, the recognition rate of pallet detection is low. In order to improve the recognition rate, a pallet detection method based on point cloud is proposed. In this method, time-of-flight (ToF) camera is used to collect the point cloud. AlexNet network which is provided by Halcon software is used for deep learning, and deep learning is used to extract the region of interest of pallet contour. The extracted region of interest is processed to obtain the regions of the pallet contour, and the pallet center is solved. The experimental results show that the precision of pallet detection can reach 92.0%. This method has high recognition rate in complex background, and has reference value for the design of pallet detection system of autonomous forklifts.\",\"PeriodicalId\":321853,\"journal\":{\"name\":\"2021 International Conference on Internet, Education and Information Technology (IEIT)\",\"volume\":\"42 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-04-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 International Conference on Internet, Education and Information Technology (IEIT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/IEIT53597.2021.00025\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 International Conference on Internet, Education and Information Technology (IEIT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IEIT53597.2021.00025","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 0

摘要

托盘检测是自动叉车货物装卸的关键环节。由于受复杂背景的影响，托盘检测的识别率较低。为了提高托盘的识别率，提出了一种基于点云的托盘检测方法。该方法采用飞行时间(ToF)相机采集点云。利用Halcon软件提供的AlexNet网络进行深度学习，利用深度学习提取托盘轮廓感兴趣的区域。对提取的感兴趣区域进行处理，得到托盘轮廓区域，求解托盘中心。实验结果表明，该方法对托盘的检测精度可达92.0%。该方法在复杂背景下具有较高的识别率，对自主叉车托盘检测系统的设计具有参考价值。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Pallet Detection Based on Halcon and AlexNet Network for Autonomous Forklifts

Pallet detection is the key step of cargo handling for autonomous forklifts. Due to the influence of complex background, the recognition rate of pallet detection is low. In order to improve the recognition rate, a pallet detection method based on point cloud is proposed. In this method, time-of-flight (ToF) camera is used to collect the point cloud. AlexNet network which is provided by Halcon software is used for deep learning, and deep learning is used to extract the region of interest of pallet contour. The extracted region of interest is processed to obtain the regions of the pallet contour, and the pallet center is solved. The experimental results show that the precision of pallet detection can reach 92.0%. This method has high recognition rate in complex background, and has reference value for the design of pallet detection system of autonomous forklifts.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

2021 International Conference on Internet, Education and Information Technology (IEIT)

自引率

0.00%

发文量