Skip to content

Visual AI for Agriculture

March 26, 2025 at 9 AM Pacific

Register for the Zoom

By submitting you (1) agree to Voxel51’s Terms of Service and Privacy Statement and (2) agree to receive occasional emails.

Brewing Better AI: Unlocking Coffee Data with FiftyOne

Paula Ramos
Voxel51

AI in agriculture is only as good as the data behind it, but messy datasets, poor annotations, and hidden biases slow progress. Join Paula for a dynamic session on semantic segmentation, where she will show how FiftyOne can transform dataset curation, annotation analysis, and model evaluation for agricultural AI. Using real-world coffee datasets from Colombia, we’ll dive into the segmentation of coffee fruits at different maturation stages, leveraging FiftyOne’s powerful tools, from uniqueness detection to similarity search and embedding visualizations. Whether interested in farm robotics, remote sensing, or plant phenotyping, this talk will give you actionable techniques to refine your datasets and supercharge your AI workflows.

About the Speaker

Paula Ramos has a PhD in Computer Vision and Machine Learning, with more than 20 years of experience in the technological field. She has been developing novel integrated engineering technologies, mainly in Computer Vision, robotics, and Machine Learning applied to agriculture, since the early 2000s in Colombia. During her PhD and Postdoc research, she deployed multiple low-cost, smart edge & IoT computing technologies, such as farmers, that can be operated without expertise in computer vision systems. The central objective of Paula’s research has been to develop intelligent systems/machines that can understand and recreate the visual world around us to solve real-world needs, such as those in the agricultural industry.

How Open Source Technology will Transform Precision Agriculture

Guy Coleman
University of Copenhagen

There’s no doubt that advances in vision technology (algorithms, data, computation and software) are transforming the way fields in agriculture are managed. The unit of management is moving from whole fields and farms to individual plants and even insects. Yet the approach taken—generally closed source, proprietary solutions—mean we aren’t innovating as fast as we could, and we have removed the tools for innovation from the key innovators themselves: farmers. Using his experience with the open-source OpenWeedLocator for DIY weed recognition and the WeedAI platform for image data sharing, Guy will discuss how transforming our approach to an open-source model, will benefit companies, farmers, and the future of food production.

About the Speaker

Guy Coleman is a postdoctoral researcher at the University of Copenhagen in the field of weed recognition technologies and evolutionary biology. He completed a PhD in image-based opportunities for weed recognition tools, and is passionate about how open-source development is a more efficient way forward for innovating in agriculture.