The YEESI Lab Dataset
收藏资源简介：
The Tanzanian agriculture industry faces a great challenge caused by pests and diseases threatening food security. Pests such as tomato leaf miners, aphids, fall armyworms (FAW), and bean leaf miners devastate crops. Also, diseases such as maize streak virus, early blight, Powdery mildew, Leaf spot, Rusty brown leaf, foliar disease, Bacterial Wilt, Blossom end rot, Flower abortion, Leaf Curl and Black rot have caused the crop failure that leads to yield reduction. So, precisely and accurately detecting such pests and diseases to improve agriculture productivity in the country is paramount. However, manual detection is cumbersome, time-consuming and costly. So, automating the procedure using machine vision technologies is necessary for sustainable prosperous agriculture. Therefore, this dataset presents the first Tanzanian agricultural classification dataset that contains 7992 healthy and unhealthy crops images (maize, beans, green peppers, onions, okra, watermelons, sunflowers, African eggplants, tomatoes, Chinese cabbage, hot peppers, wheat, leaf kale and cabbage). Images were collected in real-world conditions in Morogoro, Tanzania, in August and September 2022, using smartphones and professional GoPro Hero 9 cameras. The dataset is called YEESI Dataset. It is used as Open Data. The authors expect this dataset to revolutionize applications of Artificial Intelligence (AI) in agriculture for evaluating classification models related to crop pests, diseases and weed problems from open data.
坦桑尼亚农业产业正面临病虫害威胁粮食安全所引发的严峻挑战。诸如番茄潜叶蛾、蚜虫、草地贪夜蛾（FAW）及豆潜叶蝇等害虫会对作物造成毁灭性破坏。此外，玉米条纹病毒、早疫病、白粉病、叶斑病、锈褐色叶病、叶部病害、细菌性萎蔫病、脐腐病、落花症、卷叶病与黑腐病等病害均会引发作物减产乃至绝收。因此，精准检测此类病虫害对于提升该国农业生产力至关重要。 然而人工检测流程繁琐、耗时且成本高昂，因此借助机器视觉技术实现检测自动化，对于推动农业可持续繁荣发展而言必不可少。 为此，本数据集为首个坦桑尼亚农业分类数据集，共收录7992张健康与受病虫害侵袭的作物图像，涵盖玉米、菜豆、青椒、洋葱、秋葵、西瓜、向日葵、非洲茄子、番茄、大白菜、辣椒、小麦、羽衣甘蓝及卷心菜共14类作物。图像于2022年8月至9月间，在坦桑尼亚莫罗戈罗省的真实田间场景中采集，采集设备包括智能手机与专业GoPro Hero 9运动相机。本数据集命名为YEESI数据集，以开放数据形式对外发布。 作者期望该数据集能够推动人工智能（Artificial Intelligence）在农业领域的应用革新，助力基于开放数据开展作物病虫害、杂草相关分类模型的评估工作。
