Morphological recognition of rice seedlings based on GoogLeNet and UAV image

ZHU Wei; MA Lixin; ZHANG Ping; LIU Deying

doi:10.7671/j.issn.1001-411X.202107041

Journal of South China Agricultural University > 2022 > 43(3): 99-106. > DOI: 10.7671/j.issn.1001-411X.202107041

ZHU Wei, MA Lixin, ZHANG Ping, et al. Morphological recognition of rice seedlings based on GoogLeNet and UAV image[J]. Journal of South China Agricultural University, 2022, 43(3): 99-106. DOI: 10.7671/j.issn.1001-411X.202107041

Citation:

PDF (1352 KB)

Morphological recognition of rice seedlings based on GoogLeNet and UAV image

1.
College of Engineering, Nanjing Agricultural University, Nanjing 210031, China
2.
Jiangsu Agricultural Machinery Testing Station, Nanjing 210017, China

More Information

Received Date: July 22, 2021
Available Online: May 17, 2023

Graphical Abstract

Abstract

Abstract

Objective
In view of the current situation that the quality of transplanting is mainly based on manual observation and random sampling in China, it is proposed to use the convolutional neural network GoogLeNet to recognize the morphology of rice seedlings.

Method
Firstly, clear and intact images of rice seedlings were obtained by UAV aerial photography at low altitude. Data sets of floating seedlings, damaged seedlings and qualified seedlings were made by cutting and marking. Then, based on the GoogLeNet structure training data, the optimal network recognition model was obtained. Finally, the image classification experiment of seedlings per hole was carried out, and compared with traditional image classification algorithms (SVM, BP neural network).

Result
Under the condition of using the same samples, the seedling morphology recognition method based on GoogLeNet completed the judgment and classification was faster and more accurately. The average accuracy of seedling morphology recognition was 91.17%, and the average detection time was 0.27 s. Compared with SVM and BP neural network, the average classification accuracy increased by 21 and 13 percentage points respectively, and the detection time was shortened by 1.09 and 0.58 s respectively.

Conclusion
This study can provide the relevant support for evaluation of rice transplanting quality.
- Rice,
- Transplanting quality,
- Seedling morphology,
- GoogLeNet,
- UAV; Image classification

FullText(HTML)

References (22)

References

[1]	李鸣钰, 高西宁, 潘婕, 等. 未来升温1.5 ℃与2.0 ℃背景下中国水稻产量可能变化趋势[J]. 自然资源学报, 2021, 36(3): 567-581.
[2]	李忠华, 刘欣. 影响高速插秧机作业质量的因素分析[J]. 现代化农业, 2014(4): 56-57. doi: 10.3969/j.issn.1001-0254.2014.04.032
[3]	辛明金, 邬立岩, 宋玉秋, 等. VP6型水稻插秧机作业质量试验研究[J]. 中国农机化学报, 2016, 37(4): 19-23.
[4]	潘海珠, 陈仲新. 无人机高光谱遥感数据在冬小麦叶面积指数反演中的应用[J]. 中国农业资源与区划, 2018, 39(3): 32-37.
[5]	胡琪, 武红旗, 轩俊伟, 等. 基于无人机DSM的小麦倒伏信息提取[J]. 安徽农业科学, 2020, 48(16): 227-231. doi: 10.3969/j.issn.0517-6611.2020.16.064
[6]	赵春霞. 基于ResNet18的图像分类在农作物病虫害诊断中的应用[J]. 农业与技术, 2021, 41(19): 10-13.
[7]	程千, 徐洪刚, 曹引波, 等. 基于无人机多时相植被指数的冬小麦产量估测[J]. 农业机械学报, 2021, 52(03): 160-167.
[8]	王林惠, 甘海明, 岳学军, 等. 基于图像识别的无人机精准喷雾控制系统的研究[J]. 华南农业大学学报, 2016, 37(6): 23-30. doi: 10.7671/j.issn.1001-411X.2016.06.004
[9]	ASHOURLOO D, AGHIGHI H, MATKAN A A, et al. An investigation into machinelearning regression techniques for the leaf rust disease detection using hyperspectral measurement[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2016, 9(9): 4344-4351.
[10]	HAQ M A, RAHAMAN G, BARAL P, et al. Deep learning based supervised image classification using UAV images for forest areas classification[J]. Journal of the Indian Society of Remote Sensing, 2020, 49(3): 601-606.
[11]	王丽君, 淮永建, 彭月橙. 基于叶片图像多特征融合的观叶植物种类识别[J]. 北京林业大学学报, 2015, 37(1): 55-61.
[12]	陶惠林, 徐良骥, 冯海宽, 等. 基于无人机高光谱遥感数据的冬小麦产量估算[J]. 农业机械学报, 2020, 51(7): 146-155. doi: 10.6041/j.issn.1000-1298.2020.07.017
[13]	赵静, 潘方江, 兰玉彬, 等. 无人机可见光遥感和特征融合的小麦倒伏面积提取[J]. 农业工程学报, 2021, 37(3): 73-80. doi: 10.11975/j.issn.1002-6819.2021.03.009
[14]	刘嘉政, 王雪峰, 王甜. 基于深度学习的5种树皮纹理图像识别研究[J]. 北京林业大学学报, 2019, 41(4): 146-154.
[15]	ZHANG Q, CHEN MESJ, LI B. A visual navigation algorithm for paddy field weeding robot based on image understanding[J]. Computers and Electronics in Agriculture, 2017, 143: 66-78. doi: 10.1016/j.compag.2017.09.008
[16]	李静, 陈桂芬, 安宇. 基于优化卷积神经网络的玉米螟虫害图像识别[J]. 华南农业大学学报, 2020, 41(3): 110-116. doi: 10.7671/j.issn.1001-411X.201907017
[17]	WEI D, HUANG Y B, ZHAO C J, et al. Identification of seedling cabbages and weeds using hyperspectral imaging[J]. International Journal of Agricultural and Biological Engineering, 2015, 8(5): 65-72.
[18]	林相泽, 朱赛华, 张俊媛, 等. 基于迁移学习和Mask R-CNN的稻飞虱图像分类方法[J]. 农业机械学报, 2019, 50(7): 201-207. doi: 10.6041/j.issn.1000-1298.2019.07.021
[19]	陈进, 韩梦娜, 练毅, 等. 基于U-Net模型的含杂水稻籽粒图像分割[J]. 农业工程学报, 2020, 36(10): 174-180. doi: 10.11975/j.issn.1002-6819.2020.10.021
[20]	杨万里, 段凌凤, 杨万能. 基于深度学习的水稻表型特征提取和穗质量预测研究[J]. 华中农业大学学报, 2021, 40(1): 227-235.
[21]	中华人民共和国国家质量监督检验检疫总局, 中国国家标准化管理委员会. 水稻插秧机试验方法: GB/T 6243—2017[S]. 北京: 中国标准出版社, 2017.
[22]	中华人民共和国农业农村部. 水稻插秧机: DG/T 008—2019[S]. 北京: 中国农业出版社, 2019.

Cited By

Cited by

Periodical cited type(9)

1.	圣文顺，余熊峰，林佳燕，陈欣. 融合注意力与特征金字塔的小尺度目标检测算法. 计算机工程. 2024(01): 242-250 .
2.	伍仪霖，周子勇. 运用机器学习方法提取Sentinel-2影像烃微渗漏异常——以Marsel 探区为例. 地球物理学报. 2024(04): 1330-1341 .
3.	满自红，王志成，陈耀年，王让军，王一峰，王明霞，尚素琴. 基于EasyDL平台的甘肃陇南核桃主要病害诊断模型的构建及应用. 西北农业学报. 2024(05): 971-980 .
4.	徐岸峰，黄学彬，王波. 改进GoogLeNet的自然场景图像多标记分类仿真. 计算机仿真. 2024(11): 258-261+392 .
5.	王兴旺，郑汉垣，王芳. 白鹤草莓GCD-EF-CV病虫害识别模型研究与应用. 山西农业大学学报(自然科学版). 2023(01): 65-74 .
6.	王宏乐，叶全洲，王兴林，刘大存，梁振伟. 基于YOLOv7的无人机影像稻穗计数方法研究. 广东农业科学. 2023(07): 74-82 .
7.	邹立雯，梁春英，周正，李普，李圳鹏，张荣丹. 深度学习在水稻秧苗识别中的应用. 热带农业工程. 2023(04): 93-96 .
8.	陈裕锋，冯佩雯，凌金生，张书琪，余振鹏，熊琳琳，刘洪，谢家兴. 基于无人机多光谱图像的水稻品种鉴定. 南京农业大学学报. 2023(05): 995-1003 .
9.	郑晓玲，郑永钊. 基于神经网络的无人机农药喷洒区域智能识别. 黎明职业大学学报. 2023(02): 94-101 .

Other cited types(8)

Get Citation

PDF

XML

Article views (943) PDF downloads (293) Cited by(17)

Turn off MathJax

Article Contents

Abstract

References

Morphological recognition of rice seedlings based on GoogLeNet and UAV image

Abstract

References

Cited by

Periodical cited type(9)

Other cited types(8)

Catalog

Export File

Citation

Format

Content