基于Faster R-CNN的防排水板料袋自动拆垛视觉定位系统  

Automatic Disassembly and Visual Positioning System for Waterproof and Drainage Sheet Bags based on Faster R-CNN

作　　者：赵东哲 周英森 李保路 ZHAO Dong-zhe;ZHOU Ying-sen;LI Bao-lu(Hebei Guochuang Jingjinji Technology Development Co.,Ltd.,Shijiazhuang 050081,China;Hebei Academy of Sciences,Shijiazhuang 050081,China;Hebei Province Mechatronics Pilot Base Co.,Ltd.,Shijiazhuang 050081,China;Jingjinji National Technology Innovation Center Hebei Center,Shijiazhuang 050081,China)

机构地区：[1]河北省国创京津冀科技发展有限公司,石家庄050081 [2]河北省科学院,石家庄050081 [3]河北省机电一体化中试基地有限公司,石家庄050081 [4]京津冀国家技术创新中心河北中心,石家庄050081

出　　处：《价值工程》2024年第23期58-61,共4页Value Engineering

基　　金：基于Faster R-CNN算法的防排水板自动上料系统研究,河北省科学院科技计划项目(2022G23)。

摘　　要：针对防排水板生产过程存在的聚丙烯、聚乙烯等袋装物料上料任务重、效率低的问题,设计了一种基于2D视觉+点激光位移传感器+机器人的自动拆垛系统。介绍了该系统视觉定位原理,重点讲述基于Faster R-CNN的袋装物料视觉识别技术、三坐标转化定位技术等。实验结果表明,系统可实现袋装物料的精准识别和定位,有效提升料袋的拆垛上料的速度,降低人力成本。Aiming at the problems of heavy loading tasks and low efficiency of bagged materials such as polypropylene and polyethylene in the production process of waterproof and drainage boards,an automatic palletizing system based on 2D vision,point laser displacement sensors,and robots has been designed.The visual positioning principle of the system was introduced,with a focus on the visual recognition technology for bagged materials based on Faster R-CNN and the three-dimensional transformation positioning technology.The experimental results show that the system can achieve precise identification and positioning of bagged materials,effectively improve the speed of unpacking and loading of bags,and reduce labor costs.

关 键 词：防排水板 拆垛 Faster R-CNN 视觉识别 视觉定位 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]