农业装备与车辆工程2025，Vol.63Issue(5)：8-15,53,9.DOI:10.3969/j.issn.1673-3142.2025.05.002
基于视觉识别的玉米株间杂草清除装置设计与试验
Design and experiment of weed removal device for maize plants based on visual recognition
摘要
Abstract
In response to the problems of the high seedling damage rate of the existing inter-plant weeders and the large computational amount of the recognition algorithm,a corn inter-plant weed removal device based on visual recognition was designed.The key components,namely the rotating device and the weeding teeth,were designed and analyzed,and key parameters such as the maximum stress of the tooth tips of the weeding teeth,which was 20.867 MPa,were determined.By analyzing the movement trajectory of weeding,the key parameters affecting the movement trajectory were determined.An intelligent control system with STM32F103 as the core was designed.The centroid of the plants was recognized based on the image stitching and skeleton extraction algorithms,and the inter-plant distance information between the plants was obtained through the mutual conversion between the pixel coordinate system and the actual coordinate system.The control system precisely controlled the rotating device according to the inter-plant distance information.Tests were carried out based on the design and analysis.The test results showed that when the forward speed was 0.45 m/s,the weeding effect was good,with a weeding rate of 90.5%and a seedling damage rate of 2.05%,which met the operation requirements.The weed removal device designed by this research institute meets the requirements for inter plant weed control,providing a basis for the development and improvement of inter plant weed control devices.关键词
视觉识别/骨架提取/图像拼接/玉米植株/杂草清除Key words
visual identity/skeleton extraction/image stitching/corn plants/weed cleaner分类
农业科技引用本文复制引用
张敬文,彭强吉,康建明,赵露强,邸志峰,王少伟,陈玉龙..基于视觉识别的玉米株间杂草清除装置设计与试验[J].农业装备与车辆工程,2025,63(5):8-15,53,9.基金项目
山东省农业科学院农业科技创新工程(CXGC2024A09) （CXGC2024A09）
黄三角国家农高区省级科技创新发展专项资金项目(2022SZX46) （2022SZX46）
