数据驱动的农业深度学习方法计量分析

doi:10.19788/j.issn.2096-6369.000023

Abstract

Abstract:

With the development and application of artificial intelligence, computer vision, deep learning and other science and technology in the field of agriculture, the data-driven deep learning model for agriculture has become a new research paradigm for agricultural information extraction, and agricultural datasets are the basis for deep learning model training, and high-quality, large-scale, and diverse datasets can effectively improve the model performance, thus boosting the application of deep learning in the field of smart agriculture. To help researchers in related fields better understand the driving force of data for deep learning and give full play to the application of deep learning in the field of agriculture, this paper analyzes the datasets through metrology and summarizes the basic qualities of agricultural datasets such as type, scale, and source, which are divided into four categories according to the deep learning methods, such as target detection, image segmentation, and image recognition, and into seven categories according to the application areas, such as visual navigation, feature recognition, non-destructive testing and other 7 categories. The results show that the type of dataset is dominated by image data, and the data volume of images is concentrated in the range of 500 to 1500, and due to the specificity of agricultural data collection, most of the dataset is constructed by individuals and some of them are from public datasets, and the dataset is mainly utilized to carry out feature recognition. In the future, as the scale of the model becomes larger and larger, the requirements for the dataset are also upgraded, and it is necessary to continuously construct large-scale, balanced distribution, and accurately labeled datasets.In this paper, we provide a theoretical basis for data to promote deep learning agricultural applications by emphasizing the driving force and the importance of data to the deep learning model.

Key words: Digital agriculture, deep learning, datasets, metrological analysis

LI JiaLe, ZHANG JianHua, WANG Jian, ZHOU GuoMin. Metrological Analysis of Data-driven Deep Learning Methods for Agriculture[J].Journal of Agricultural Big Data, 2024, 6(3): 400-411.

Figures/Tables 9

Fig. 1

Table 1

Fig. 2

Fig. 3

Table 2

Fig. 4

Table 3

Fig. 5

Table 4

References 26

[1]	詹骐源. 机器学习的发展史及应用前景[J]. 科技传播, 2018, 10(21): 138-139.
[2]	徐清华, 郑誉煌, 戴冰燕. 基于深度残差网络的水果图像分类算法研究[J]. 工业控制计算机, 2020, 33(12):37-38+40.
[3]	彭顺正, 黄筑斌, 岳延滨. 基于深度学习的油菜籽粒图像分割方法初探[J]. 农技服务, 2020, 37(10):37-39.
[4]	LIU Y, LIU S, XU J, et al. Forest pest identification based on a new dataset and convolutional neural network model with enhancement strategy[J/OL]. Computers and Electronics in Agriculture, 2022, 192:106625. https://doi.org/10.1016/j.compag.2021.106625.
[5]	ATTRI I, AWASTHI L K, SHARMA T P, et al. A review of deep learning techniques used in agriculture[J/OL], Ecological Informatics, 2023, 77:102217. https://doi.org/10.1016/j.ecoinf.2023.102217.
[6]	ZHU Y, ABDALLA A, TANG Z. et al. Improving rice nitrogen stress diagnosis by denoising strips in hyperspectral images via deep learning[J]. Biosystems Engineering, 2022, 219:165-176. https://doi.org/10.1016/j.biosystemseng.2022.05.001.
[7]	XUAN G, GAO C, SHAO Y, et al. Apple detection in natural environment using deep learning algorithms[J]. IEEE Access, 2020, 216772-216780. https://doi.org/10.1109/ACCESS.2020.3040423.
[8]	孙烨, 董春雨. 复杂性视阈下的当代人工智能发展——以深度学习为例[J]. 系统科学学报, 2023, 31(4):13-22.
[9]	赵亚楠, 邓寒冰, 刘婷, 等. 基于弱监督学习的玉米苗期植株图像实例分割方法[J]. 农业工程学报, 2022, 38(19):143-152.
[10]	苏令涛, 李瑞泽, 张功磊, 等. 基于深度学习的农作物病虫害识别研究[J]. 数学建模及其应用, 2022, 11(4):1-12.
[11]	张庆辉, 张媛, 张梦雅. 有遮挡人脸识别进展综述[J]. 计算机应用研究, 2023, 40(8):2250-2257+2273.
[12]	马永建, 汪传建, 赵庆展, 等. 基于GF-1遥感影像的荒漠区耕地分类与提取方法[J]. 石河子大学学报(自然科学版), 2021, 39(3):383-390.
[13]	宋晓倩, 张学艺, 张春梅, 等. 基于深度迁移学习的酿酒葡萄种植信息提取[J]. 江苏农业学报, 2020, 36(3):689-693.
[14]	袁盼丽, 汪传建, 赵庆展, 等. 基于深度学习的寒旱区多时序影像土地利用及变化监测——以新疆莫索湾垦区为例[J]. 干旱区地理, 2021, 44(6):1717-1728. doi: 10.12118/j.issn.1000–6060.2021.06.20
[15]	冯权泷, 陈泊安, 李国庆, 等. 遥感影像样本数据集研究综述[J]. 遥感学报, 2022, 26(4):589-605.
[16]	田地. 采用遗传算法优化的深度学习模型在育种中的实践[J]. 分子植物育种, 2024, 22(1):286-291.
[17]	尉震行. 目标识别算法综述[J]. 中国设备工程, 2019,(1):94-97.
[18]	黄雯珂, 滕飞, 王子丹, 等. 基于深度学习的图像分割综述[J]. 计算机科学, 2024, 51(2):107-116. doi: 10.11896/jsjkx.230900002
[19]	向雁, 侯艳林, 姜文来, 等. LSTM模型在耕地面积预测领域的构建与应用[J]. 科技导报, 2021, 39(9):100-108. doi: 10.3981/j.issn.1000-7857.2021.09.012
[20]	CORTEZ B, CARRERA B, KIM Y J, et al. An architecture for emergency event prediction using LSTM recurrent neural networks[J]. Expert Systems with Applications, 2018, 97: 315-324. https://doi.org/10.1016/j.eswa.2017.12.037
[21]	田鹏菲, 王皞阳. 机器视觉技术在我国农业领域内的应用分析[J]. 江苏农业科学, 2023, 51(14):13-21.
[22]	黄凯奇, 任伟强, 谭铁牛. 图像物体分类与检测算法综述[J]. 计算机学报, 2014, 37(6): 1225-1240.
[23]	HORAK K, SABLATNIG R. Deep learning concepts and datasets for image recognition: overview 2019[C]// Proceedings Volume 11179, Eleventh International Conference on Digital Image Processing (ICDIP 2019), 2019:111791S. https://doi.org/10.1117/12.2539806
[24]	孙书魁, 范菁, 孙中强, 等. 基于深度学习的图像数据增强研究综述[J/OL]. 计算机科学,1-23[2023-12-07].
[25]	ARSENOVIC M, KARANOVIC M, SLADOJEVIC S, et al. Solving current limitations of deep learning based approaches for plant disease detection[J]. Symmetry, 2019, 11(7): ID 939.
[26]	管博伦, 张立平, 朱静波, 等. 农业病虫害图像数据集现状及高质量构建综述[J]. 智慧农业, 2023, 5(3):17-34.

序号	类型	细分	论文数量（篇）
1	图像数据	作物	80	194
		病虫害	53
		水果	25
		畜禽	20
		昆虫	6
		花朵	3
		杂草	3
		农田障碍物	3
		农田火源	1
2	遥感数据	作物	19	39
		耕地	16
		河流	2
		设施农业	2
3	其他数据	气象数据	7	15
		农产品数据	2
		光谱图像	3
		视频	1
		音频	1
		蛋白质质谱数据	1
	总计		248

序号	类型	来源	使用频率(次)
1	个人构建	相机	65	188
		手机	60
		无人机	17
		图像采集系统	16
		摄像头	11
		光谱成像设备	11
		诱虫灯	3
		录音设备	2
		传感器	2
		孢子囊捕捉设备	1
2	公开数据集	PlantVillage	12
		AI Challenger 2	4
		Imagenet	2	33
		GWHD数据集	1
		WSD数据集	1
		Plantpathology	1
		Ai Studio	1
		EVRI	1
		IDADP	1
		IP102	1
		DeepLearning	1
		Digipathos	1
		UCI	1
		CrowdAI	1
		Fruits-360	1
		Mendeley	1
		Kaggle	1
		竞赛数据集	1
3	卫星遥感数据	中国资源卫星应用中心	20	31
		LandSat-8卫星遥感图像	3
		GEE平台	1
		EAS	1
		Google Earth	3
		WHU-RS19数据集	1
		UCMercedLandUse数据集	1
		高德卫星地图	1
4	网络	网络爬虫爬取	11	22
		搜索引擎	6
		我国农业网站	3
		中国气象数据网	2
5	其他	高校	2	8
		气象站	2
		国家统计局	1
		研究所	1
		国家级和省级农业数据	1
		DIA 质谱数据集	1
	总计		282

序号	应用类型	方法	使用频率（次）
1	目标检测	YOLO v3	20	93
		YOLO v4	14
		YOLO v5	23
		YOLOx	5
		YOLO v7	4
		YOLACT	2
		传统帧间差分法	1
		SSD模型	7
		CoTNet模型	1
		3DConvNet算法	1
		EfficientDet	2
		Center Net	1
		1DCNN 检测模型	2
		PCA-SVM模型	1
		Vi T分类网络	2
		Att-BiGRU-RNN分类模型	1
		Resnet50模型	4
		AlexNet模型	1
		Full dilated-RCF	1
2	图像识别	卷积神经网络CNN	40	88
		3D 卷积神经网络	2
		对象卷积神经网络OCNN	1
		DenseNet	7
		残差神经网络ResNet	14
		倒残差网络MobileNetv2	2
		EESP深度学习模型	1
		VGG16	9
		LeNet-5	1
		Inception V3	1
		SE-ResNeXt-101模型	1
		ShuffleNet算法	1
		BM-DCNN	1
		全卷积神经网络（FCN）	1
		SqueezeNet	2
		时间卷积神经网络（TCN）	1
		DNN	2
		BiseNet卷积神经网络	1
3	图像分割	U-Net语义分割模型	16	77
		UPerNet语义分割模型	1
		Faster R-CNN语义分割模型	19
		DeepLabv3+语义分割模型	7
		ICNet语义分割模型	1
		MobileNetV3语义分割模型	9
		SegNet语义分割模型	1
		MSSN语义分割模型	1
		R-Linknet网络	1
		Mask R-CNN实例分割模型	6
		Tensorflow	4
		Keras	2
		Xception模型	4
		CornDisNet网络分割模型	1
		Easy DL图像分割模型	1
		SP-Vnet分割神经网络	1
		AutoLNet分割网络	1
		PD-Net	1
4	预测	LSTM模型	9	9
	总计		267

序号	应用领域	实际应用	论文数量/篇
1	特征识别	作物病虫害识别检测	57	123
		作物整株、芽苗、稻穗、种子、生长期等识别	25
		动物个体身份、声音、行为等识别	16
		农作物及农田地物遥感图像识别	25
2	无损检测	农产品分类分级	25	56
		农产品质量问题检测	10
		作物体内成分检测	8
		作物病害分级	6
		昆虫数量和种类检测	4
		农产品数量检测	3
3	信息采集	耕地信息提取与监测	16	36
		作物表型信息获取	13
		农产品经济指标评估	6
		农田技术指标采集	1
4	目标精准定位	采摘机械作业	23	27
4		杂草精准定位	4	27
5	田间管理	精准灌溉	5	7
		农田环境监测	1
		土壤健康管理	1
6	视觉导航	规避障碍物	3	5
6		路径规划	2	5
7	其他	河流识别	2	4
		农田灾害预警	1
		精准饲养	1
	总计		258

Metrological Analysis of Data-driven Deep Learning Methods for Agriculture

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 9

References 26

Related Articles 11

Metrics

Comments

Recommended 0

[1]	DU JiaKuan, LI YanFei, SUN SiWen, LIU JiDong, JIANG TengDa. Pan-spatiotemporal Feature Rice Deep Learning Extraction Based on Multi-source Data Fusion [J]. Journal of Agricultural Big Data, 2024, 6(1): 56-67.
[2]	CHEN Lei, ZHOU Na, ZHU PengXuan, YUAN Yuan. A Dataset for Constructing Agricultural Knowledge Graph [J]. Journal of Agricultural Big Data, 2024, 6(1): 1-8.
[3]	MAO KeBiao, YUAN ZiJin, SHI JianCheng, WU ShengLi, HU DeYong, CHE Jin, DONG LiXin. Theory and Engineering Technology Implementation of Artificial Intelligence Retrieval Paradigm for Parameters of Remote Sensing Based on Big Data [J]. Journal of Agricultural Big Data, 2023, 5(4): 1-12.
[4]	ZHAO HongXin, SHAO MingYue, PAN Pan, WANG ZhiAo, MU Qiang, HE ZiKang, ZHANG JianHua. A Training Dataset for Deep Neural Network Model Recognition of Common Cotton Diseases [J]. Journal of Agricultural Big Data, 2023, 5(4): 47-55.
[5]	WANG Kexiao, ZHOU Rui, LI Bo. Biochemistry Indexes and Reflectance Spectra Datasets of Rape Pod Pericarp at Different Maturities [J]. Journal of Agricultural Big Data, 2023, 5(1): 29-33.
[6]	Lixue Kuang, Guofeng Xu, Zhijun Chen, Yinping Li, Yang Cheng, Youming Shen. Quality Datasets of ‘Fuji’ Apples Cultivated in China in 2017 [J]. Journal of Agricultural Big Data, 2022, 4(3): 49-53.
[7]	Kebao Bi Hongwen Li Yang Lu Zhongjun Zhang Dongmei Lv Zhiqun Liu, Yu Wang Xiaonan Zhang. The Application and Future of Big Data in Digital Agriculture in Heilongjiang Province [J]. Journal of Agricultural Big Data, 2020, 2(1): 21-28.
[8]	Dong Tang Wenfeng Du Weicheng Sun Guangrong Jia Xinwei Liang. Research and Design of Agricultural and Rural Digital Resources Architecture [J]. Journal of Agricultural Big Data, 2019, 1(3): 28-37.
[9]	Lingxu Zhang,Rui Han,Wenming Li,Yinxue Shi,Chi Liu. A Survey of Big Data Deep Learning Systems and a Typical Agricultural Application [J]. Journal of Agricultural Big Data, 2019, 1(2): 88-104.
[10]	Lei Wu,Xiaohe Liang,Jisiguleng Wu,Rui Wang. Method and Agricultural Empirical Study of Query Reformulation Based on Word Embedding [J]. Journal of Agricultural Big Data, 2019, 1(2): 114-120.
[11]	Li Xianjiang, Chen Youqi, Zou Jinqiu, Shi Shuqin, Guo Tao, Cai Weimin, Chen Hao. Application of Convolutional Neural Networks in High-Resolution Image Classification [J]. Journal of Agricultural Big Data, 2019, 1(1): 67-77.