Tobacco Aerial Dataset: Corrected Image–Mask Pairings and Standardized Test Split

This dataset is derived from the “Tobacco Aerial Dataset” by Imran Moazzam, available at Mendeley Data (DOI: https://doi.org/10.17632/5dpc5gbgpz.2). The dataset was originally introduced in:Moazzam, I.S.; Khan, U.S.; Qureshi, W.S.; Nawaz, T.; Kunwar, F. Towards automated weed detection through two-stage semantic segmentation of tobacco and weed dpixels in aerial imagery. Smart Agricultural Technology 2023, 4, doi:https://doi.org/10.1016/j.atech.2022.100142. This version makes the following modifications: The correction of mismatched image–mask pairings The addition of a test split, with paths to the images in the set. The omission of Campaign no. 2. This version of the dataset was used in:Bunica-Mihai, A., Ichim, L., Popescu, D. (2026). Tobacco and Weed Segmentation from Remote Images Using Artificial Intelligence. In: Rojas, I., Joya, G., Catala, A. (eds) Advances in Computational Intelligence. IWANN 2025. Lecture Notes in Computer Science, vol 16009. Springer, Cham. https://doi.org/10.1007/978-3-032-02728-3_6. The original dataset is licensed under CC BY 4.0, and all original credit belongs to the original authors. Users of this derived dataset should also cite the original dataset and associated publication.本数据集源自Imran Moazzam发布的《烟草航拍数据集（Tobacco Aerial Dataset）》，可通过Mendeley Data获取，DOI链接为：https://doi.org/10.17632/5dpc5gbgpz.2。 该数据集首次发表于以下研究：Moazzam, I.S.; Khan, U.S.; Qureshi, W.S.; Nawaz, T.; Kunwar, F. 《面向航拍影像中烟草与杂草像素的两阶段语义分割实现杂草自动化检测》，《智能农业技术（Smart Agricultural Technology）》2023年第4卷，DOI：https://doi.org/10.1016/j.atech.2022.100142。 本版本作出如下修改： 1. 修正了图像与掩码（mask）不匹配的配对问题； 2. 新增了测试集划分（test split），并提供了数据集内图像的存储路径； 3. 移除了第二批次（Campaign no. 2）的数据。 本版本数据集曾应用于以下研究：Bunica-Mihai, A., Ichim, L., Popescu, D. (2026). 《基于人工智能的遥感影像烟草与杂草分割》，收录于Rojas, I., Joya, G., Catala, A. 主编的《计算智能进展（Advances in Computational Intelligence）》，2025年国际人工神经网络工作会议（IWANN 2025）论文集，《计算机科学讲义（Lecture Notes in Computer Science）》第16009卷，Springer, Cham出版社，DOI链接：https://doi.org/10.1007/978-3-032-02728-3_6。 原始数据集采用CC BY 4.0许可协议，原作者版权归属不变。使用本衍生数据集的用户，需同时引用原始数据集及相关发表文献。