RafanoSet: Dataset of manually and automatically annotated Raphanus Raphanistrum weed images for object detection and segmentation in Heterogenous Agriculture Environment

This dataset is a collection of manually and automatically annotated multispectral Images over Raphanus Raphanistrum infestations among Wheat crops. The collection of these MS images was done in field environment, at noon on 13 January 2022. The images were captured manually using the MicaSense RedEdge-M at 1m AGL manually over the crop rows containing a mix of Wheat crop and Horseradish weed. Annotated images were obtained using VIA annotator version 1.0.6. The dataset RafanoSet contains 5 sub-directories named ‘Automated Annotations’, ‘Binary Masks – Automated', ‘Binary Masks – Manual‘, ‘Manual Annotations’ and ‘Raw Images’. The sub-directory ‘Raw Images’ consists of 85 .png images. The sub-directory ‘Manual Annotations’ consists of 1 json file named ‘region_data’. The sub-directory ‘Binary Masks - Manual’ consists of 80 .jpg images representing manually segmented binary mask instances. The sub-directory ‘Binary Masks – Automated' consists of 80 .png images representing automatically segmented binary mask instances. The sub-directory ‘Automated Annotations’ consists of 80 .jpg files and 80 .xml files sharing the same names. One image scene, i.e. 5 images across different spectra were removed from ‘automated’ due to poor results. The scientific framework of image acquisition and annotations are explained in the Data in Brief paper. This is just a prerequisite to the data article. Roles: The image acquisition was performed by Mariano Crimaldi, a researcher, on behalf of Department of Agriculture and the hosting institution University of Naples Federico II, Italy.Shubham Rana has been the curator and analyst for the data under the supervision of his PhD supervisor Prof. Salvatore Gerbino. They are affiliated with Department of Engineering, University of Campania 'Luigi Vanvitelli'. We are also in the process of articulating a data-in-brief article associated with this repository Domenico Barretta, Department of Engineering has been associated in consulting and brainstorming role particularly with data and annotation management and litmus testing of the datasets.