Over the last 5 years we have built Sterblue, an AI-powered cloud platform to support energy companies managing their critical assets: wind turbines, transmission & distribution grids and cooling towers. Machine learning was a huge part of our product.
Millions of images have been processed on the platform. We have used AI to detect discrepancies (corrosion, cracks, vegetation, etc.), to locate assets in space, to generate automatic flight paths for drones, and many other applications.
5 years ago, showing bounding boxes on an image on a Linkedin or blog post was the big marketing trend. We chose to do it the hard way, by scaling up with AI.
We labeled millions of images worked with multiple labeling companies. We also dealt with tens of different taxonomies for the same physical problem, we faced labeling quality challenges, we built AI training pipeline using tens of open source frameworks and ecosystem partners, we integrated real users in the loop and ... we showed some results.
The type of results that tell to a customer “for your use case A, you save 23% of your time whilst reducing your false negative rate by 14%”
With LabelFlow, we now want to support every AI-applied company in the world to build the next big thing
. We start small with our labeling tool, with a strong focus on user experience. That’s just the beginning.
We are a team of enthusiastic developers and data scientists. We will unveil the team soon, stay tuned.