SeSame / Weed Aerial Dataset

Sesame-weed aerial dataset was recorded with the Phantom 3 standard drone and Agrocam NDVI.
Photographs of sesame fields were taken near Ballo Shahabal, Jhang, Punjab, Pakistan. These campaigns range in length from 16 to 45 days for the sesame crop. A ground sampling distance of 0.33 cm/pixel is achieved by flying the drone at an average height of 15 feet. The three channels of the Agrocam camera—NIR, G, and B—when combined, produce NGB composite images. Agrocam lacks the R (red channel), therefore the green grass appears orange in the pictures. Pictures were captured for both datasets at a resolution of 1920 × 1080 pixels, however for faster processing, we cropped non-overlapping images to a size of 480 x 352 pixels. Using the MATLAB Image Labeler app, we labelled the photos by hand. A label image in 8-bit unsigned grayscale is produced by the software. The depicted image has the pixel values 0, 1, and 2 assigned to the background, crop, and weed, respectively. Since there are no aerial dataset available publicly to the best of our knowledge, these datasets could be utilized to support further research in Sesame crop.
No. Field Attribute/ images Timing Around / Date Captured Soil Condition
1 S3 Test / 120 6:30am / 09 Aug 2020 Before irrigation
2 S1 Train / 600 8:30am / 09 Aug 2020 Before irrigation
3 S1 Test / 120 11:30am / 10 Aug 2020 Before irrigation
4 S1 Test / 120 6:00pm / 19 Aug 2020 Before irrigation
5 S4 Test / 120 8:30am / 21 Aug 2020 After irrigation
6 S2 Train / 600 2:00pm / 21 Aug 2020 After irrigation
7 S3 Test / 120 3:30pm / 28 Aug 2020 After irrigation
8 S4 Test / 120 6:00pm / 06 Sep 2020 After irrigation

Citation Request: if you use these datasets in your research or projects by any means, please cite following publications.
1) Patch-wise weeds coarse segmentation mask from aerial imagery of sesame crop
(Published in Computers and Electronics in Agriculture 2022, HEC Recognized W category, Impact factor 6.757, Q1)
2) Towards automated weed detection through two-stage semantic segmentation of tobacco and weed pixels in aerial Imagery
(Published in Smart Agricultural Technology (A companion journal of Computers and Electronics in Agriculture))
3) A Patch-Image Based Classification Approach for Detection of Weeds in Sugar Beet Crop
(Published in IEEE Access, Impact factor 3.1, Q1)

Acknowledgement Request
This work is funded by the Higher Education Commission of Pakistan and the National center for Robotics and Automation (DF-1009–31). Please Acknowledge.

Find More data and research papers in related links attached.

芝麻植物冠层数据集由 Phantom 3 标准无人机与 Agrocam NDVI 相机共同采集。该数据集收录了位于巴基斯坦旁遮普省江信地区巴洛沙哈巴尔的芝麻田照片。采集活动历时16至45天，覆盖芝麻生长周期的不同阶段。无人机以平均15英尺的高度飞行，实现了0.33厘米/像素的地面采样距离。Agrocam 相机的NIR、G和B三个通道结合，生成NGB复合图像。由于Agrocam 相机缺少R（红色通道），因此图片中的绿色草地呈现为橙色。数据集的图像以1920 × 1080像素的分辨率采集，但为了加快处理速度，我们将非重叠图像裁剪至480 x 352像素。使用 MATLAB 图像标签器应用程序，手动对照片进行标记。软件生成了8位无符号灰度标签图像。图像中的像素值0、1和2分别对应背景、作物和杂草。据我们所知，目前尚无公开的芝麻冠层航空数据集，因此这些数据集可用于支持芝麻作物进一步研究的开展。

表头：
No. - 序号
Field - 数据集名称
Attribute/images - 属性/图像数量
Timing Around / Date Captured - 采集时间/日期
Soil Condition - 土壤状况

示例数据：
1. S3 - 测试集/120张图像 - 6:30am / 2020年8月9日 - 灌溉前
2. S1 - 训练集/600张图像 - 8:30am / 2020年8月9日 - 灌溉前
3. S1 - 测试集/120张图像 - 11:30am / 2020年8月10日 - 灌溉前
4. S1 - 测试集/120张图像 - 6:00pm / 2020年8月19日 - 灌溉前
5. S4 - 测试集/120张图像 - 8:30am / 2020年8月21日 - 灌溉后
6. S2 - 训练集/600张图像 - 2:00pm / 2020年8月21日 - 灌溉后
7. S3 - 测试集/120张图像 - 3:30pm / 2020年8月28日 - 灌溉后
8. S4 - 测试集/120张图像 - 6:00pm / 2020年9月6日 - 灌溉后

引用请求：如果您在研究或项目中以任何方式使用这些数据集，请引用以下出版物。
1) 基于芝麻作物航空影像的斑点杂草粗分割掩膜（发表于《计算机与电子农业》2022年，HEC认可W类别，影响因子6.757，Q1）
2) 通过烟草和杂草像素在航空影像中的两阶段语义分割实现杂草自动检测（发表于《智能农业技术》（《计算机与电子农业》的配套期刊）
3) 基于斑点图像的糖 beet 作物杂草检测分类方法（发表于《IEEE Access》，影响因子3.1，Q1）

致谢请求：本工作由巴基斯坦高等教育委员会和国家机器人与自动化中心（DF-1009–31）资助。请致谢。

更多数据和研究成果请参阅附上的相关链接。