Applications of convolutional neural network (CNN)-based object detectors in agriculture have been a popular research topic in recent years. However, complicated agricultural environments bring many difficulties for ground truth annotation as well as potential uncertainties for image data quality. Using YOLOv4 as a representation of state-of-the-art object detectors, this study quantified YOLOv4’s sensitivity against artificial image distortions including white noise, motion blur, hue shift, saturation change, and intensity change, and examined the importance of various training dataset attributes based on model classification accuracies, including dataset size, label quality, negative sample presence, image sequence, and image distortion levels. The YOLOv4 model trained and validated on the original datasets failed at 31.91% white noise, 22.05-pixel motion blur, 77.38° hue clockwise shift, 64.81° hue counterclockwise shift, 89.98% saturation decrease, 895.35% saturation increase, 79.80% intensity decrease, and 162.71% intensity increase with 30% mean average precisions (mAPs) for four apple flower bud growth stages. The performance of YOLOv4 decreased with both declining training dataset size and training image label quality. Negative samples and training image sequence did not make a substantial difference in model performance. Incorporating distorted images during training improved the classification accuracies of YOLOv4 models on noisy test datasets by 13 to 390%. In the context of apple flower bud growth-stage classification, except for motion blur, YOLOv4 is sufficiently robust for potential image distortions by white noise, hue shift, saturation change, and intensity change in real life. Training image label quality and training instance number are more important factors than training dataset size. Exposing models to test-image-alike training images is crucial for optimal model classification accuracies. The study enhances understanding of implementing object detectors in agricultural research.

Leaves from genetically unique Juglans regia plants were scanned using X-ray micro-computed tomography (microCT) on the X-ray μCT beamline (8.3.2) at the Advanced Light Source (ALS) in Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA USA). Soil samples were collected in Fall of 2017 from the riparian oak forest located at the Russell Ranch Sustainable Agricultural Institute at the University of California Davis. The soil was sieved through a 2 mm mesh and was air dried before imaging. A single soil aggregate was scanned at 23 keV using the 10x objective lens with a pixel resolution of 650 nanometers on beamline 8.3.2 at the ALS. Additionally, a drought stressed almond flower bud (Prunus dulcis) from a plant housed at the University of California, Davis, was scanned using a 4x lens with a pixel resolution of 1.72 µm on beamline 8.3.2 at the ALS Raw tomographic image data was reconstructed using TomoPy. Reconstructions were converted to 8-bit tif or png format using ImageJ or the PIL package in Python before further processing. Images were annotated using Intel’s Computer Vision Annotation Tool (CVAT) and ImageJ. Both CVAT and ImageJ are free to use and open source. Leaf images were annotated in following Théroux-Rancourt et al. (2020). Specifically, Hand labeling was done directly in ImageJ by drawing around each tissue; with 5 images annotated per leaf. Care was taken to cover a range of anatomical variation to help improve the generalizability of the models to other leaves. All slices were labeled by Dr. Mina Momayyezi and Fiona Duong.To annotate the flower bud and soil aggregate, images were imported into CVAT. The exterior border of the bud (i.e. bud scales) and flower were annotated in CVAT and exported as masks. Similarly, the exterior of the soil aggregate and particulate organic matter identified by eye were annotated in CVAT and exported as masks. To annotate air spaces in both the bud and soil aggregate, images were imported into ImageJ. A gaussian blur was applied to the image to decrease noise and then the air space was segmented using thresholding. After applying the threshold, the selected air space region was converted to a binary image with white representing the air space and black representing everything else. This binary image was overlaid upon the original image and the air space within the flower bud and aggregate was selected using the “free hand” tool. Air space outside of the region of interest for both image sets was eliminated. The quality of the air space annotation was then visually inspected for accuracy against the underlying original image; incomplete annotations were corrected using the brush or pencil tool to paint missing air space white and incorrectly identified air space black. Once the annotation was satisfactorily corrected, the binary image of the air space was saved. Finally, the annotations of the bud and flower or aggregate and organic matter were opened in ImageJ and the associated air space mask was overlaid on top of them forming a three-layer mask suitable for training the fully convolutional network. All labeling of the soil aggregate and soil aggregate images was done by Dr. Devin Rippner. These images and annotations are for training deep learning models to identify different constituents in leaves, almond buds, and soil aggregates Limitations: For the walnut leaves, some tissues (stomata, etc.) are not labeled and only represent a small portion of a full leaf. Similarly, both the almond bud and the aggregate represent just one single sample of each. The bud tissues are only divided up into buds scales, flower, and air space. Many other tissues remain unlabeled. For the soil aggregate annotated labels are done by eye with no actual chemical information. Therefore particulate organic matter identification may be incorrect. Resources in this dataset:Resource Title: Annotated X-ray CT images and masks of a Forest Soil Aggregate. File Name: forest_soil_images_masks_for_testing_training.zipResource Description: This aggregate was collected from the riparian oak forest at the Russell Ranch Sustainable Agricultural Facility. The aggreagate was scanned using X-ray micro-computed tomography (microCT) on the X-ray μCT beamline (8.3.2) at the Advanced Light Source (ALS) in Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA USA) using the 10x objective lens with a pixel resolution of 650 nanometers. For masks, the background has a value of 0,0,0; pores spaces have a value of 250,250, 250; mineral solids have a value= 128,0,0; and particulate organic matter has a value of = 000,128,000. These files were used for training a model to segment the forest soil aggregate and for testing the accuracy, precision, recall, and f1 score of the model.Resource Title: Annotated X-ray CT images and masks of an Almond bud (P. Dulcis). File Name: Almond_bud_tube_D_P6_training_testing_images_and_masks.zipResource Description: Drought stressed almond flower bud (Prunis dulcis) from a plant housed at the University of California, Davis, was scanned by X-ray micro-computed tomography (microCT) on the X-ray μCT beamline (8.3.2) at the Advanced Light Source (ALS) in Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA USA) using the 4x lens with a pixel resolution of 1.72 µm using. For masks, the background has a value of 0,0,0; air spaces have a value of 255,255, 255; bud scales have a value= 128,0,0; and flower tissues have a value of = 000,128,000. These files were used for training a model to segment the almond bud and for testing the accuracy, precision, recall, and f1 score of the model.Resource Software Recommended: Fiji (ImageJ),url: https://imagej.net/software/fiji/downloads Resource Title: Annotated X-ray CT images and masks of Walnut leaves (J. Regia) . File Name: 6_leaf_training_testing_images_and_masks_for_paper.zipResource Description: Stems were collected from genetically unique J. regia accessions at the 117 USDA-ARS-NCGR in Wolfskill Experimental Orchard, Winters, California USA to use as scion, and were grafted by Sierra Gold Nursery onto a commonly used commercial rootstock, RX1 (J. microcarpa × J. regia). We used a common rootstock to eliminate any own-root effects and to simulate conditions for a commercial walnut orchard setting, where rootstocks are commonly used. The grafted saplings were repotted and transferred to the Armstrong lathe house facility at the University of California, Davis in June 2019, and kept under natural light and temperature. Leaves from each accession and treatment were scanned using X-ray micro-computed tomography (microCT) on the X-ray μCT beamline (8.3.2) at the Advanced Light Source (ALS) in Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA USA) using the 10x objective lens with a pixel resolution of 650 nanometers. For masks, the background has a value of 170,170,170; Epidermis value= 85,85,85; Mesophyll value= 0,0,0; Bundle Sheath Extension value= 152,152,152; Vein value= 220,220,220; Air value = 255,255,255.Resource Software Recommended: Fiji (ImageJ),url: https://imagej.net/software/fiji/downloads

The Multiclass Weeds Dataset for Image Segmentation comprises two species of weeds: Soliva Sessilis (Field Burrweed) and Thlaspi Arvense L. (Field Pennycress). Weed images were acquired during the early growth stage under field conditions in a brinjal farm located in Gorakhpur, Uttar Pradesh, India. The dataset contains 7872 augmented images and corresponding masks. Images were captured using various smartphone cameras and stored in RGB color format in JPEG format. The captured images were labeled using the labelme tool to generate segmented masks. Subsequently, the dataset was augmented to generate the final dataset.

The MegaWeeds dataset consists of seven existing datasets:

- WeedCrop dataset; Sudars, K., Jasko, J., Namatevs, I., Ozola, L., & Badaukis, N. (2020). Dataset of annotated food crops and weed images for robotic computer vision control. Data in Brief, 31, 105833. https://doi.org/https://doi.org/10.1016/j.dib.2020.105833

- Chicory dataset; Gallo, I., Rehman, A. U., Dehkord, R. H., Landro, N., La Grassa, R., & Boschetti, M. (2022). Weed detection by UAV 416a Image Dataset. https://universe.roboflow.com/chicory-crop-weeds-5m7vo/weed-detection-by-uav-416a/dataset/1

- Sesame dataset; Utsav, P., Raviraj, P., & Rayja, M. (2020). crop and weed detection data with bounding boxes. https://www.kaggle.com/datasets/ravirajsinh45/crop-and-weed-detection-data-with-bounding-boxes

- Sugar beet dataset; Wangyongkun. (2020). sugarbeetsAndweeds. https://www.kaggle.com/datasets/wangyongkun/sugarbeetsandweeds

- Weed-Detection-v2; Tandon, K. (2021, June). Weed_Detection_v2. https://www.kaggle.com/datasets/kushagratandon12/weed-detection-v2

- Maize dataset; Correa, J. M. L., D. Andújar, M. Todeschini, J. Karouta, JM Begochea, & Ribeiro A. (2021). WeedMaize. Zenodo. https://doi.org/10.5281/ZENODO.5106795

- CottonWeedDet12 dataset; Dang, F., Chen, D., Lu, Y., & Li, Z. (2023). YOLOWeeds: A novel benchmark of YOLO object detectors for multi-class weed detection in cotton production systems. Computers and Electronics in Agriculture, 205, 107655. https://doi.org/https://doi.org/10.1016/j.compag.2023.107655

All the datasets contain open-field images from crops and weeds with annotations. The annotation files were converted to text files so it can be used in the YOLO model. All the datasets were combined into one big dataset with in total 19,317 images. The dataset is split into a training and validation set.

Description

👉 Download the dataset here

This dataset offers an extensive collection of images and corresponding labels representing a wide array of plant diseases. Carefully curated from publicly available sources, it serves as a valuable resource for developing and evaluating machine learning models, particularly in the realms of image classification and Plant Disease Image Dataset.

Dataset Composition:

• Images: The dataset comprises high-quality images organized by plant species and disease type, providing a diverse range of visual data. It includes not only images of diseased plants but also healthy plant samples, ensuring a balanced dataset for training purposes.

• Categories: The images are categorized into various classes based on the plant species and the specific disease affecting them. This categorization allows for more precise model training and testing.

• Cleaned Data: All images have been meticulously cleaned and verified to remove any corrupt or unusable files, ensuring the dataset's reliability and usability.

• Labeling: Each image is labeled with detailed information about the plant species and the type of disease, making it easier to use the dataset for supervised learning tasks.

Download Dataset

Applications:

This dataset is ideal for a variety of machine learning applications, including:

• Disease Detection: Training models to identify and classify various plant diseases, which can be pivotal for early detection and prevention.

• Image Classification: Developing and testing models to accurately classify images based on plant species and health status.

• Agricultural Research: Supporting research in precision agriculture by providing data that can lead to better understanding and management of plant health.

Dataset Structure:

• Organized Folders: The images are structured into folders corresponding to each plant species and disease type, facilitating easy access and manipulation of data.

• Healthy Samples Included: To ensure balanced datasets, healthy plant samples are included alongside diseased ones, enabling models to learn to differentiate between healthy and diseased plants.

• Versatile Use: The dataset's structure and labeling make it suitable for a wide range of research and commercial applications in agriculture and plant biology.

Conclusion:

The Plant Disease Dataset is a comprehensive and well-organized collection, ideal for anyone working on machine learning models in the field of agriculture. Whether you're developing new algorithms for disease detection or enhancing existing models, this dataset provides the rich and diverse data necessary to achieve accurate and reliable results.

This dataset is sourced from Kaggle.

National and international Vitis variety catalogues can be used as image datasets for computer vision in viticulture. These databases archive ampelographic features and phenology of several grape varieties and plant structures images (e.g. leaf, bunch, shoots). Although these archives represent a potential database for computer vision in viticulture, plant structure images are acquired singularly and mostly not directly in the vineyard. Localization computer vision models would take advantage of multiple objects in the same image, allowing more efficient training. The present images and labels dataset was designed to overcome such limitations and provide suitable images for multiple cluster identification in white grape varieties. A group of 373 images were acquired from later view in vertical shoot position vineyards in six different Italian locations at different phenological stages. Images were then labelled in YOLO labelling format. The dataset was made available both in terms of images and labels. The real number of bunches counted in the field, and the number of bunches visible in the image (not covered by other vine structures) was recorded for a group of images in this dataset.

Digital image datasets for Precision Agriculture (PA) still need to be available. Many problems in this field of science have been studied to find solutions, such as detecting weeds, counting fruits and trees, and detecting diseases and pests, among others. One of the main fields of research in PA is detecting different crop types with aerial images. Crop detection is vital in PA to establish crop inventories, planting areas, and crop yields and to have information available for food markets and public entities that provide technical help to small farmers. This work proposes public access to a digital image dataset for detecting green onion and foliage flower crops located in the rural area of Medellín City – Colombia. This dataset consists of 245 images with their respective labels: green onion (Allium fistulosum), foliage flowers (Solidago Canadensis and Aster divaricatus), and non-crop areas prepared for planting. A total of 4315 instances were obtained, which were divided into subsets for training, validation, and testing. The classes in the images were labeled with the polygon method, which allows training machine learning algorithms for detection using bounding boxes or segmentation in the COCO format.

OverviewThis dataset contains real overhead images of wind turbines in the US collected through the National Agriculture Imagery Plan (NAIP), as well as synthetic overhead images of wind turbines created to be similar to the real images. All of these images are 608x608. For more details on the methodology and data, please read the sections below, or look at our website: Locating Energy Infrastructure with Deep Learning (duke-bc-dl-for-energy-infrastructure.github.io).Real DataThe real data consists of images.zip and labels.zip. There are 1,742 images in images.zip, and for each image in this folder, there is a corresponding label with the same name, but a different extension. Some images do not have labels, meaning there are no wind turbines in those images. Many of these overhead images of wind turbines were collected from Power Plant Satellite Imagery Dataset (figshare.com) and then hand labeled. Others were collected using Google Earth Engine or EarthOnDemand and then labeled. All of the images collected are from the National Agricultural Imagery Program (NAIP), and all are 608x608 pixels. The labels are in YOLOv3 format, meaning each line in the text file corresponds with one wind turbine. Each line is formatted as: class x_center y_center width height. Since there is only one class, class is always zero, and the x, y, width, and height are relative to the size of the image and are between 0-1.The image_locations.csv file contains the latitude and longitude for each image. It also contains the image's geographic domain that we defined. Our data comes from what we defined as four regions - Northeast (NE), Eastern Midwest (EM), Northwest (NW), and Southwest (SW), and these are included in the csv file for each image. These regions are defined by groups of states, so any data in WA, ID, or MT would be in the Northwest region.Synthetic DataThe synthetic data consists of synthetic_images.zip and synthetic_labels.zip. These images and labels were automatically generated using CityEngine. Again, all images are 608x608, and the format of the labels is the same. There are 943 images total, and at least 200 images for each of the four geographic domains that we defined in the US (Northwest, Southwest, Eastern Midwest, Northeast). The generation of these images consisted of the software selecting a background image, then generating 3D models of turbines on top of that background image, and then positioning a simulated camera overhead to capture an image. The background images were collected nearby the locations of the testing images.ExperimentationOur Duke Bass Connections 2020-2021 team performed many experiments using this data to test if the synthetic imagery could help the performance of our object detection model. We designed experiments where we would have a baseline dataset of just real imagery, train and test an object detection model on it, and then add in synthetic imagery into the dataset, train the object detection model on the new dataset, and then compare it's performance with the baseline. For more information on the experiments and methodology, please visit our website here: Locating Energy Infrastructure with Deep Learning (duke-bc-dl-for-energy-infrastructure.github.io).

Coccidiosis, Salmonella, and Newcastle are the common poultry diseases that curtail poultry production if they are not detected early. In Tanzania, these diseases are not detected early due to limited access to agricultural support services by poultry farmers. Deep learning techniques have the potential for early diagnosis of these poultry diseases. In this study, a deep Convolutional Neural Network (CNN) model was developed to diagnose poultry diseases by classifying healthy and unhealthy fecal images. Unhealthy fecal images may be symptomatic of Coccidiosis, Salmonella, and Newcastle diseases. We collected 1,255 laboratory-labeled fecal images and fecal samples used in Polymerase Chain Reaction diagnostics to annotate the laboratory-labeled fecal images. We took 6,812 poultry fecal photos using an Open Data Kit. Agricultural support experts annotated the farm-labeled fecal images. Then we used a baseline CNN model, VGG16, InceptionV3, MobileNetV2, and Xception models. We trained models using farm and laboratory-labeled fecal images and then fine-tuned them. The test set used farm-labeled images. The test accuracies results without fine-tuning were 83.06% for the baseline CNN, 85.85% for VGG16, 94.79% for InceptionV3, 87.46% for MobileNetV2, and 88.27% for Xception. Finetuning while freezing the batch normalization layer improved model accuracies, resulting in 95.01% for VGG16, 95.45% for InceptionV3, 98.02% for MobileNetV2, and 98.24% for Xception, with F1 scores for all classifiers above 75% in all four classes. Given the lighter weight of the trained MobileNetV2 and its better ability to generalize, we recommend deploying this model for the early detection of poultry diseases at the farm level.

The dataset contains aerial agricultural images of a potato field with manual labels of healthy and stressed plant regions. The images were collected with a Parrot Sequoia multispectral camera carried by a 3DR Solo drone flying at an altitude of 3 meters. The dataset consists of RGB images with a resolution of 750×750 pixels, and spectral monochrome red, green, red-edge, and near-infrared images with a resolution of 416×416 pixels, and XML files with annotated bounding boxes of healthy and stressed potato crop.

The AI Data Labeling Services market is experiencing rapid growth, driven by the increasing demand for high-quality training data to fuel advancements in artificial intelligence. The market, estimated at $10 billion in 2025, is projected to witness a robust Compound Annual Growth Rate (CAGR) of 25% from 2025 to 2033, reaching a substantial market size. This expansion is fueled by several key factors. The automotive industry leverages AI data labeling for autonomous driving systems, while healthcare utilizes it for medical image analysis and diagnostics. The retail and e-commerce sectors benefit from improved product recommendations and customer service through AI-powered chatbots and image recognition. Agriculture is employing AI data labeling for precision farming and crop monitoring. Furthermore, the increasing adoption of cloud-based solutions offers scalability and cost-effectiveness, bolstering market growth. While data security and privacy concerns present challenges, the ongoing development of innovative techniques and the rising availability of skilled professionals are mitigating these restraints. The market is segmented by application (automotive, healthcare, retail & e-commerce, agriculture, others) and type (cloud-based, on-premises), with cloud-based solutions gaining significant traction due to their flexibility and accessibility. Key players like Scale AI, Labelbox, and Appen are actively shaping market dynamics through technological innovations and strategic partnerships. The North American market currently holds a significant share, but regions like Asia Pacific are poised for substantial growth due to increasing AI adoption and technological advancements. The competitive landscape is dynamic, characterized by both established players and emerging startups. While larger companies possess substantial resources and experience, smaller, agile companies are innovating with specialized solutions and niche applications. Future growth will likely be influenced by advancements in data annotation techniques (e.g., synthetic data generation), increasing demand for specialized labeling services (e.g., 3D point cloud labeling), and the expansion of AI applications across various industries. The continued development of robust data governance frameworks and ethical considerations surrounding data privacy will play a critical role in shaping the market's trajectory in the coming years. Regional growth will be influenced by factors such as government regulations, technological infrastructure, and the availability of skilled labor. Overall, the AI Data Labeling Services market presents a compelling opportunity for growth and investment in the foreseeable future.

The dataset contains soybean crop adult insect high resolution (JPG) raw images ( a total of 3824 images). There were considered four kinds of soybean crop insects raw pictures as:1. A folder Eocanthecona_Bug_A contains 1198 images of Eocanthecona Bug.2. A folder Tobacco_Caterpillar_B includes 990 images of Tobacco Caterpillar.3. A folder Red_Hairy_Catterpillar_C Contains 1001 images of Red Hairy Caterpillar.4. A folder Larva_Spodoptera_D contains 635 images of Larva Spodoptera. 5. We have also uploaded a bounding box folder that contains four CSV files. Each CSV file is associated with above four insect image folders and stores the underlying insect bounding box information with the label (image, xmin, ymin, xmax, ymax, label)The authors developed the dataset under collaborative work between Indira Gandhi Krishi Vishwavidyalaya (IGKV), Raipur (CG), and DSPM IIIT Naya Raipur (CG), India

This dataset includes time series Sentinel-1 images and paddy rice labeling in South Korea for ML/DL model training. It consists of 7,762 training patches and 5,180 validation patches for each patch consists of 256 x 256 pixels. The dataset is saved in hdf5 format separated into training/valdation data, image/labeling, and part number which can be accessed by key: {tr/va}_{im/lb}_{0~4}.

According to the phonological stage of paddy rice, the Sentinel-1 images were acquired through 8-time steps from May 10 to October 20 in 20 days’ interval. In order for the images to capture similar features of rice invariant to more or less difference of growth, minimum and maximum value composite were used at transplanting season and ripening season each. The acquisition year for each patch varies from 2017 to 2019 since it was matched to that of labeling source.

The paddy rice labeling is a rasterized version of farm map produced by Korean Ministry of Agriculture, Food and Rural Affairs(MAFRA). The original source data was produced by visual interpreted by high-resolution satellite images and aerial photos referring the other national GIS data and it is accessible through the national open data platform (http://data.nsdi.go.kr/dataset/20210707ds00001). As the data is distributed in a vector format, it was converted to 10 m x 10 m raster format which is compatible to the Sentinel-1, and used for labeling the images.

Edible Oil Seed Dataset :- The Oil seed classification plays a critical role in the agricultural and industrial sectors, aiding in quality control, sorting, and automation of processing systems. With the rise of machine learning and deep learning technologies, there is a growing need for high-quality, labeled datasets that can support the development and testing of classification models. This paper introduces the Edible Oil Seed Dataset, a carefully curated collection of 10,111 images across six widely cultivated oil seed types: Black Sesame, Groundnut, Mustard, Soybean, Sunflower, and White Sesame. Captured using a high-resolution mobile imaging system with burst-shot capabilities, each image has undergone preprocessing steps such as resizing, normalization, and labeling to ensure suitability for machine learning applications. The dataset provides a solid foundation for tasks involving computer vision in agriculture, such as real-time seed sorting, quality assessment, and educational demonstrations of classification algorithms.

Representing six categories:- 1. Black Sesame Seeds - 1850 2. Groundnuts - 3000 3. Mustard Seeds - 1500 4. Soybean Seeds - 1531 5. Sunflower Seeds -1569 6. White Sesame Seeds - 661 Total Images= 10,111

Device Specifications:- - Primary Camera: Device Model: Xiaomi Redmi 10C - 50 MP sensor, f/1.8 aperture, 26mm (wide), PDAF - Secondary Camera: Device Model: Xiaomi Redmi Note 7S - 48 MP sensor, f/1.8 aperture, 1/2.0" sensor size, 0.8µm pixel size, PDAF - Features: Dual - LED flash, HDR
- Modes Used: Burst Shot Mode (capturing 20+ frames for optimal image selection)

This dataset is intended to bridge the gap between theoretical research and real-world application, making it a valuable resource for developers, researchers, and educators aiming to implement or explore seed classification using artificial intelligence techniques. Its versatility supports diverse use cases from research and development to practical deployment in smart agricultural systems.

The success of any AI-driven system relies heavily on vast amounts of training data. While AI applications in plant stress management have gained attention in recent years, there's still a significant lack of expert-annotated data, especially for tropical and subtropical crops. We're filling in this gap by releasing a public dataset with 4,749 leaf pictures of healthy, nutrient-deficient, and pest-affected tomatoes, eggplants, cucumbers, bitter gourds, snake gourds, ridge gourds, ash gourds, and bottle gourds. This dataset encompasses 57 unique classes, with high-resolution images (3024 x 3024) captured at three different sites in Bangladesh under natural field conditions. An expert panel from the Bangladesh Agricultural Research Institute (BARI) has labeled the images. This collection not only features the largest number of plant stress classes but also introduces the first multi-label classification challenge in the agricultural domain.

This dataset is a collection of raw and annotated Multispectral (MS) images acquired in a heterogenous agricultural environment with MicaSense RedEdge-M camera. The spectra particularly Green, Blue, Red, Red Edge and Near Infrared (NIR) were acquired at sub-metre level.. The MS images were labelled manually using VIA and automatically using Grounding DINO in combination with Segment Anything Model. The segmentation masks obtained using these two annotation techniqes over as well as the source code to perform necessary image processing operations are provided in the repository. The images are focussed over Horseradish (Raphanus Raphanistrum) infestations in Triticum Aestivum (wheat) crops.

The nomenclature of sequecncing and naming images and annotations has been in this format: IMG_1: Blue_2: Green_3: Red_4: Near Infrared_5: RedEdgeExample: An image name IMG_0200_3 represents the scene number 200 in Red channel

This dataset 'RafanoSet'is categorized in 6 directories namely 'Raw Images', 'Manual Annotations', 'Automated Annotations', 'Binary Masks - Manual', 'Binary Masks - Automated' and 'Codes'. The sub-directory 'Raw Images' consists of manually acquired 85 images in .PNG format. over 17 different scenes. The sub-directory 'Manual Annotations' consists of annotation file 'region_data' in COCO segmentation format. The sub-directory 'Automated Annotations' consists of 80 automatically annotated images in .JPG format and 80 .XML files in Pascal VOC annotation format.

The scientific framework of image acquisition and annotations are explained in the Data in Brief paper which is the course of peer review. This is just a prerequisite to the data article. Field experimentation 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'.

Domenico Barretta, Department of Engineering has been associated in consulting and brainstorming role particularly with data validation, annotation management and litmus testing of the datasets.

This dataset contains a semantic segmentation delineation derived from street-level images, focusing on categorizing agricultural and natural landscapes. With 35 distinct classes, including labels such as "field margin," "crop," "cropfield," and "ditch," the dataset draws from Land Use/Cover Area Frame Survey (LUCAS) geospatial dataset. LUCAS images are collected using a consistent sampling framework, offering a representative view of different regions and environments of Europe.

Comprising a total of 1784 north looking images from 2018, this dataset contributes to land cover analysis by providing fine-grained annotations for a variety of landscape elements, as well as, a valuable resource for training and evaluating semantic segmentation models.

The dataset's potential applications span a range of domains, from land use mapping and environmental monitoring to urban planning and agricultural management. By fostering the advancement of machine learning models in accurately segmenting landscapes, this dataset contributes to sustainable land management practices and supports informed decision-making processes.

Dataset Structure

The dataset is organized into batches, with each batch containing two main folders: -batch folder - images: Contains the LUCAS north-looking images captured for each theoretical point. -full_masks: Contains pixel-level annotated masks corresponding to each image, where each pixel is labeled with a class. -partial_masks (only for the first batch): Contains partial masks where some areas of the images are not delineated. -classes_dataset.csv:csv file containing the code and label correspondence

Data Format - Image files are provided in JPEG format. - Full and partial masks are provided in PNG format, where each pixel corresponds to a specific class. - The correspondence between class codes and labels can be found in the provided CSV file.

This data set includes supplementary files to our article \emph{"Deep learning image recognition of cow behavior near an automatic milking robot with an open data set"} (Leonardo Santiago Benitez Pereira, Olli Koskela, Ilpo Pölönen, Ilmo Aronen and Iivari Kunttu, in review, 2020). We acquired continuous video data over two-month period of cows in front of Automatic Milking Station (AMS). Each frame of the video is labeled as a single image belonging to one of classes described below.

This data set includes 253 files of video data having in total um{1526473} labeled frames. The data set used in the article consisted of 280 videos, but for privacy reasons, 27 video files including persons were removed from this data set, but their Java Script Object Notation (JSON) label files are left for, e.g., temporal analyses.

RTI International (RTI) generated 2,611 labeled point locations representing 19 different land cover types, clustered in 5 distinct agroecological zones within Rwanda. These land cover types were reduced to three crop types (Banana, Maize, and Legume), two additional non-crop land cover types (Forest and Structure), and a catch-all Other land cover type to provide training/evaluation data for a crop classification model. Each point is attributed with its latitude and longitude, the land cover type, and the degree of confidence the labeler had when classifying the point location. For each location there are also three corresponding image chips (4.5 m x 4.5 m in size) with the point id as part of the image name. Each image contains a P1, P2, or P3 designation in the name, indicating the time period. P1 corresponds to December 2018, P2 corresponds to January 2019, and P3 corresponds to February 2019. These data were used in the development of research documented in greater detail in “Deep Neural Networks and Transfer Learning for Food Crop Identification in UAV Images” (Chew et al., 2020).