果树枝条识别与修剪点坐标确定方法
Identification of branches of fruit trees and determination of coordinates of pruning points
宋振帅 1周艳 2钟灵 2仪杰 1宋龙 2何磊2
作者信息
- 1. 江苏航空职业技术学院航空工程学院,江苏 镇江 212134
- 2. 新疆农垦科学院机械装备研究所,新疆 石河子 832000
- 折叠
摘要
为了实现休眠期果树的修剪识别问题,研究了基于语义分割的网络模型识别修剪枝条与确定修剪点坐标的方法.通过双目相机搭建了视觉系统获取果树的数据集,采用分别融入预训练权重与CBAM(注意力机制)的VGG16和RestNet-50作为U-Net主干特征提取网络的2种深度学习模型分割修剪枝条,同时获取其效果并进行对比.在获得的分割图像基础上采用骨架提取和修剪点聚类2种方法进行修剪点坐标的确定.结果表明,基于VGG16特征提取网络的U-Net模型识别结果较好,该模型在测试集的平均交并比(MIOU)、平均像素准确率(MPA)和训练时F分数分别为84.80%、91.83%和92.679%.分割出人工模拟果树的模型图像,采用修剪点聚类的方法,可以较快、实时地确定修剪点的二维坐标,为实现修剪作业奠定基础.
Abstract
In order to realize the pruning recognition of dormant fruit trees,a network model based on semantic segmentation was stud-ied to identify pruned branches and determine the coordinates of pruning points.A binocular camera was used to build a visual system to obtain the data set of fruit trees.VGG16 and RestNet-50,which were respectively integrated with pre-training weights and CBAM(attention mechanism),were used as two deep learning models of U-Net backbone feature extraction network to segment pruned branches.At the same time,their effects were obtained and compared.Based on the obtained segmented image,two methods,skele-ton extraction and pruning point clustering,were used to determine the coordinates of pruning points.The results showed that the U-Net model based on VGG16 feature extraction network had better recognition results.The mean intersection over union(MIOU),mean pixel accuracy(MPA)and F scores during the training of the model were 84.80%,91.83%and 92.679%respectively.By segmenting the model image of artificial simulated fruit trees and using the pruning point clustering method,the two-dimensional coordinates of pruning points could be determined quickly and in real time,which laid the foundation for pruning operations.
关键词
枝条识别/修剪点坐标/提取/预训练权重/CBAM(注意力机制)Key words
branches identification/coordinates of pruning points/extraction/pre-training weight/CBAM(attention mechanism)引用本文复制引用
基金项目
兵团重大科技项目(2021AA00503)
国家重点研发计划项目(2017YFD07014)
新疆兵团农业领域重点科技公关项目(2018AB016)
江苏航空职业技术学院院级课题(JATC24010114)
出版年
2024
NETL
NSTL
万方数据