基于改进U-Net的冬季休眠期矮化苹果树修剪枝条分割方法

doi:10.14088/j.cnki.issn0439-8114.2024.05.034

湖北农业科学 ›› 2024, Vol. 63 ›› Issue (5): 194-200.doi: 10.14088/j.cnki.issn0439-8114.2024.05.034

基于改进U-Net的冬季休眠期矮化苹果树修剪枝条分割方法

宋振帅¹, 宋龙², 周艳², 何磊², 朱贺¹, 王治民¹, 韩大龙²

1.石河子大学机械电气工程学院,新疆石河子 832003;
2.新疆农垦科学院机械装备研究所,新疆石河子 832000

收稿日期:2022-09-13 出版日期:2024-05-25 发布日期:2024-06-04
通讯作者: 周艳（1970-）,女,四川大竹人,研究员,博士,主要从事林果机械化研究,（电子信箱）806551889@qq.com。
作者简介:宋振帅（1997-）,男,山东临沂人,硕士,主要从事图像识别与分割研究,（电话）19190249234（电子信箱）1459588016@qq.com;
基金资助:
新疆生产建设兵团重大科技项目（2021AA00503）; 国家重点研发计划项目（2017YFD07014）; 新疆生产建设兵团农业领域重点科技攻关项目（2018AB016）

Segmentation method for pruned branches of dwarfing apple trees during winter dormancy period based on improved U-Net

SONG Zhen-shuai¹, SONG Long², ZHOU Yan², HE Lei², ZHU He¹, WANG Zhi-min¹, HAN Da-long²

1. College of Mechanical and Electrical Engineering, Shihezi University, Shihezi 832003, Xinjiang, China;
2. Institute of Machinery and Equipment, Xinjiang Academy of Agricultural and Reclamation Science, Shihezi 832000, Xinjiang, China

Received:2022-09-13 Published:2024-05-25 Online:2024-06-04

摘要/Abstract

摘要： 针对冬季休眠期矮化苹果树果园修剪中人工修剪及半自动化修剪作业效率低的问题,在U-Net网络模型基础上,通过VGG16与U-Net结合构建改进的U-Net网络模型,采用VGG16作为上采样特征提取网络,运用注意力机制SEnet增强图像特征提取能力,提升分割精度,进而与下采样提取的图像特征进行融合,实现端到端图像分割效果。结果表明,测试集上SE2网络模型（改进U-Net网络模型）的MIoU、MPA均大于原始U-Net网络模型;在SE2网络模型中,当r=8时测试集的MIoU、测试集的MPA、训练集的F_score、测试集的F_score均最大,分别为89.59%、94.17%、0.942 806、0.944 506;在试验台上对SE2网络模型（r=8）进行性能验证,表明SE2网络模型（r=8）分割性能较好。

关键词: 改进U-Net, 网络模型, 冬季休眠期, 矮化苹果树, 修剪枝条, 分割方法

Abstract: In response to the low efficiency of manual and semi-automatic pruning operations in dwarfing apple trees during the winter dormancy period,based on the U-Net network model, an improved U-Net network model was constructed by combining VGG16 with U-Net. Using VGG16 as the upsampling feature extraction network, the attention mechanism SEnet was used to enhance the image feature extraction ability, improve segmentation accuracy, and then fuse with the downsampling extracted image features to achieve the end-to-end image segmentation effect. The results showed that the MIoU and MPA of the SE2 network model （improved U-Net network model） on the test set were greater than those of the original U-Net network model;in the SE2 network model, when r=8, the MIoU of the test set, MPA of the test set, F_score of the training set, and F_score of the test set were all the highest, with values of 89.59%, 94.17%, 0.942 806, and 0.944 506, respectively; the performance of the SE2 network model （r=8） was validated on the test bench, and it was found that the segmentation performance of the SE2 network model （r=8） was good.

Key words: improved U-Net, network model, winter dormancy period, dwarfing apple trees, pruned branches, segmentation method

中图分类号:

TS23-9

宋振帅, 宋龙, 周艳, 何磊, 朱贺, 王治民, 韩大龙. 基于改进U-Net的冬季休眠期矮化苹果树修剪枝条分割方法[J]. 湖北农业科学, 2024, 63(5): 194-200.

SONG Zhen-shuai, SONG Long, ZHOU Yan, HE Lei, ZHU He, WANG Zhi-min, HAN Da-long. Segmentation method for pruned branches of dwarfing apple trees during winter dormancy period based on improved U-Net[J]. HUBEI AGRICULTURAL SCIENCES, 2024, 63(5): 194-200.

参考文献

[1] 周晓雄. 阿克苏地区林果产业发展现状与对策[D].新疆塔里木:塔里木大学,2021.
[2] 张秀莉. 苹果纺锤形改造为主干形的技术与效果[D].新疆塔里木:塔里木大学,2017.
[3] 刘慧,朱晟辉,沈跃,等. 基于多特征融合的树干快速分割算法[J].农业机械学报,2020,51(1):221-229.
[4] MOMTANU C,KHOT L R,SINDHUJN S.Evaluation of mobile 3D light detection and ranging based canopy mapping system for tree fruit crops[J]. Computers and electronics in agriculture, 2019, 158:10.
[5] HAMUDA E,GLAVIN M,JONES E.A survey of image processing techniques for plant extraction and segmentation in the field[J]. Computers and electronics in agriculture,2016,18:121-126.
[6] 黄彪. 枇杷剪枝机器人关键技术的研究[D].广州:华南理工大学,2016.
[7] 严亚飞. 智能枸杞采摘机器人枝条识别与定位关键技术研究[D].合肥:合肥工业大学,2019.
[8] WU C Y, YANG L Y.3D reconstruction of Chinese hickory tree for dynamics analysis[J]. Biosystems engineering, 2014, 119:11.
[9] SPECKMANN H.Providing measured position data for agricultural machinery[J]. Computers and electronics in agriculture, 2000, 25(1):13-16.
[10] 卫长秋,崔建荣,马海红,等. 苹果纺锤形改造成高光效树形的技术要点[J].山西果树,2007(6):46.
[11] KEIR E, KEIGHTLE Y, GERALD W, et al.3D volumetric modeling of grapevine biomass using tripod LiDAR[J]. Computers and electronics in agriculture, 2010, 74(2):8.
[12] FRED W,MITCH B.Graph-based methods for analyzing orchard tree structure using noisy point cloud data[J]. Computers and electronics in agriculture, 2021, 187:16-21.
[13] 郝婕,索相敏,李学营,等. 短枝富士苹果树体结构及相关因素分析[J].河北农业科学,2016,20(3):17-19.
[14] CHEN Y, XIONG Y J.3D point cloud semantic segmentation toward large-scale unstructured agricultural classification[J]. Computers and electronics in agriculture, 2021, 190:198-222.
[15] FU L S, GAO F.Application of consumer RGB-D cameras for fruit detection and localization in field: A critical review[J]. Computers and electronics in agriculture, 2020, 75(6):177-178.
[16] 刘晨. 基于机器视觉工件尺寸的高精度测量技术研究[D].长春:长春工业大学,2020.
[17] CHOLLET F.Deep learning with depth separable convolutions[J]. American journal of cardiology, 2016, 50:1006-1012.
[18] 杨璟,朱雷.基于RGB颜色空间的彩色图像分割方法[J].计算机与现代化,2010(8):147-149,171.
[19] 张亚辉. 基于Faster R-CNN目标检测的机器人抓取系统研究[D].合肥:中国科学院深圳先进技术研究院,2019.
[20] 李建坤. 基于图像SURF特征的电路板缺陷自动检测系统[D].西安:西北大学,2020.

基于改进U-Net的冬季休眠期矮化苹果树修剪枝条分割方法

Segmentation method for pruned branches of dwarfing apple trees during winter dormancy period based on improved U-Net

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	袁鹏, 王珂, 肖坚. 基于RMAU-Net网络模型的高分影像耕地提取[J]. 湖北农业科学, 2023, 62(8): 182-188.
[2]	陈行, 夏丽华, 颜军, 蒋晓旭, 黄腾杰, 邓剑文. 基于改进U-Net网络模型的高分影像养殖池塘提取[J]. 湖北农业科学, 2022, 61(20): 166-171.