A5005325561- Smart Agriculture and AI
- Remote Sensing in Agriculture
- Species Distribution and Climate Change
- Plant Pathogens and Fungal Diseases
- Leaf Properties and Growth Measurement
- Spectroscopy and Chemometric Analyses
- Food Supply Chain Traceability
- Plant Pathogenic Bacteria Studies
- Remote Sensing and LiDAR Applications
- Greenhouse Technology and Climate Control
- Insect and Arachnid Ecology and Behavior
- Plant and animal studies
- Genomics and Phylogenetic Studies
- Date Palm Research Studies
- Genetic Mapping and Diversity in Plants and Animals
- Plant Virus Research Studies
- Plant Disease Management Techniques
- Insect Resistance and Genetics
BASF (United States)
2022-2023
Weeds compete with productive crops for soil, nutrients and sunlight are therefore a major contributor to crop yield loss, which is why safer more effective herbicide products continually being developed. Digital evaluation tools automate homogenize field measurements of vital importance accelerate their development. However, the development these requires generation semantic segmentation datasets, complex, time-consuming not easily affordable task. In this paper, we present deep learning...
Plant fungal diseases are one of the most important causes crop yield losses. Therefore, plant disease identification algorithms have been seen as a useful tool to detect them at early stages mitigate their effects. Although deep-learning based can achieve high detection accuracies, they require large and manually annotated image datasets that is not always accessible, specially for rare new diseases. This study focuses on development algorithm strategy requiring few images (Few-shot...
Performing accurate and automated semantic segmentation of vegetation is a first algorithmic step towards more complex models that can extract biological information on crop health, weed presence phenological state, among others. Traditionally, based normalized difference index (NDVI), near infrared channel (NIR) or RGB have been good indicator presence. However, these methods are not suitable for accurately segmenting showing damage, which precludes their use downstream phenotyping...
The use of digital technologies and artificial intelligence techniques for the automation some visual assessment processes in agriculture is currently a reality. Image-based, recently deep learning-based systems are being used several applications. Main challenge these applications to achieve correct performance real field conditions over images that usually acquired with mobile devices thus offer limited quality. Plagues control problem be tackled field. Pest management strategies relies on...
Estimation of damage in plants is a key issue for crop protection. Currently, experts the field manually assess plots. This time-consuming task that can be automated thanks to latest technology computer vision (CV). The use image-based systems and recently deep learning-based have provided good results several agricultural applications. These applications outperform expert evaluation controlled environments, now they are being progressively included non-controlled A novel solution based on...
The use of digital technologies and artificial intelligence techniques for the automation some visual assessment processes in agriculture is currently a reality. Image-based, recently deep learning-based systems are being used several applications. Main challenge these applications to achieve correct performance real field conditions over images that usually acquired with mobile devices thus offer limited quality. Plagues control problem be tackled field. Pest management strategies relies on...
Deep Neural Networks (DNN) have emerged as powerful tools for plant visual symptoms classification in agronomic applications. Recent advancements multi-crop neural networks, coupled with relevant metadata, shown improved accuracy simultaneously classifying diverse across extensive datasets. In this study, we extend the capabilities of networks to tackle semantic segmentation, enabling estimation disease coverage on images. To achieve this, curated a challenging dataset comprising over...