| 基于Faster R-CNN的新疆棉花幼苗与杂草识别方法 |
| |
| 引用本文： | 许燕,温德圣,周建平,樊湘鹏,刘洋.基于Faster R-CNN的新疆棉花幼苗与杂草识别方法[J].排灌机械工程学报,2021,39(6):602-607. |
| |
| 作者姓名： | 许燕 温德圣 周建平 樊湘鹏 刘洋 |
| |
| 作者单位： | 新疆大学机械工程学院, 新疆 乌鲁木齐 830046 |
| |
| 摘 要： | 针对新疆棉田杂草的伴生特点带来的特征过拟合、精确率低等问题,以新疆棉花幼苗与杂草为研究对象,分析杂草识别率低的影响因素,建立了基于Faster R-CNN的网络识别模型.采集不同角度、不同自然环境和不同密集程度混合生长的棉花幼苗与杂草图像5 370张.为确保样本质量以及多样性,利用颜色迁移和数据增强来提高图像的颜色特征与扩大样本量,以PASCAL VOC格式数据集进行网络模型训练.通过综合对比VGG16,VGG19,ResNet50和ResNet101这4种网络的识别时间与精度,选择VGG16网络训练Faster R-CNN模型.在此基础上设计了纵横比为1∶1的最佳锚尺度,在该模型下对新疆棉花幼苗与杂草进行识别,实现91.49%的平均识别精度,平均识别时间262 ms.为农业智能精确除草装备的研发提供了参考.
|
| 关 键 词： | 新疆棉花苗期 杂草识别 卷积神经网络 Faster R-CNN |
| 收稿时间： | 2019-09-16 |
Identification method of cotton seedlings and weeds in Xinjiang based on Faster R-CNN |
| |
| XU Yan,WEN Desheng,ZHOU Jianping,FAN Xiangpeng,LIU Yang.Identification method of cotton seedlings and weeds in Xinjiang based on Faster R-CNN[J].Journal of Drainage and Irrigation Machinery Engineering,2021,39(6):602-607. |
| |
| Authors: | XU Yan WEN Desheng ZHOU Jianping FAN Xiangpeng LIU Yang |
| |
| Institution: | College of Mechanical Engineering, Xinjiang University, Urumuqi, Xinjiang 830046, China |
| |
| Abstract: | Aiming at the problems of over-fitting and low accuracy caused by the accompanying cha-racteristics of weeds in cotton fields in Xinjiang, taking cotton seedlings and weeds in Xinjiang as research objects, the factors affecting the low recognition rate of weeds were analyzed, and a network recognition model based on Faster R-CNN was established. A total of 5 370 cotton seedlings and weeds were collected from different angles and different natural environments and different intensive levels. In order to ensure sample quality and diversity, color migration and data enhancement were used to improve the color characteristics of the image and to expand the sample size, and the network model training was performed in the PASCAL VOC format data set. By comprehensively comparing the recognition time and accuracy of the four networks VGG16, VGG19, ResNet50 and ResNet101, the VGG16 network training Faster R-CNN model was selected. On this basis, the optimal anchor scale with aspect ratio of 1∶1 was designed. Under this model, Xinjiang cotton seedlings and weeds were identified, and the average recognition accuracy of 91.49% was achieved. The average recognition time was 262 ms. It provides a reference for the development of agricultural intelligent precision weeding equipment. |
| |
| Keywords: | Xinjiang cotton seedling stage weed identification convolutional neural network Faster R-CNN |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《排灌机械工程学报》浏览原始摘要信息 |
| 点击此处可从《排灌机械工程学报》下载免费的PDF全文 |
|
