检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:杨满仙 陈燕红[1,2,3] 李雨晴 李永可 YANG Manxian;CHENG Yanhong;LI Yuqing;LI Yongke(Xinjiang Agricultural University,Urumqi 830052,P.R.China;Engineering Research Center of Intelligent Agriculture Ministry of Education,Urumqi 830052,P.R.China;Xinjiang Agricultural Informatization Engineering Technology Research Center,Urumqi 830052,P.R.China)
机构地区:[1]新疆农业大学,乌鲁木齐830052 [2]智能农业教育部工程研究中心,乌鲁木齐830052 [3]新疆农业信息化工程技术研究中心,乌鲁木齐830052
出 处:《中国科学数据(中英文网络版)》2025年第1期55-65,共11页China Scientific Data
基 金:科技部科技创新2030--“新一代人工智能”重大项目(2022ZD0115805);新疆维吾尔自治区重大科技专项课题(2022A02011-3)。
摘 要:棉花是新疆重要经济作物,由于种植结构调整、农药不合理使用与气候变化等原因,棉花易受多种虫害侵袭,影响其产量与品质。因此,构建复杂场景下棉田昆虫图像数据集对棉田害虫综合治理具有基础性意义。本文构建了复杂场景下新疆棉田主要昆虫图像数据集,用于真实环境下棉田昆虫的识别与检测。本数据集包含13种(类)常见的棉田昆虫,共3225张图像,原始图像共24 GB,均通过严格筛选,确保图像质量。对每张图像的棉田昆虫进行人工标注,构建图像分类数据集和目标检测数据集,数据集大小共29.7 GB。使用常见的深度学习模型对数据集进行评估,确保数据集的可用性和可靠性。本数据为棉田昆虫图像分类、目标检测等提供基础数据,对促进农业领域的发展、棉花虫害防治研究及提高棉花产量具有重要的实际应用价值。Cotton is an important cash crop in Xinjiang.However,due to the adjustments in planting structure,inadvisable pesticide application,and climate change,cotton is vulnerable to various pests,which affect its yield and quality.Therefore,the construction of an insect image dataset in cotton fields under complex conditions holds fundamental significance for the integrated pest management strategies in cotton fields.In this paper,we compiled a dataset of common insects in Xinjiang cotton fields under complex conditions for the identification and detection of insects in cotton fields.This dataset covers 13 species(classes)of common cotton field insects,comprising a total of 3,225 images,with a data size of 24 GB,all of which have been rigorously screened to ensure image quality.Moreover,each image in the dataset has been manually labeled to identify the cotton field insects present.In this way,we obtained both an image classification dataset and a target detection dataset,with a data size of 29.7 GB.The dataset has undergone rigorous evaluation using standard deep learning models to ensure its accessibility and reliability.The dataset can provide basic data for insect image classification and target detection in cotton fields,and has important practical application value for facilitating agricultural field development,cotton pest control research and improving cotton yield.
关 键 词:棉田昆虫 CottonInsect数据集 图像分类 目标检测
分 类 号:S435.622[农业科学—农业昆虫与害虫防治] TP391.41[农业科学—植物保护]
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.229