Roboflow

The software we use everyday doesn't leverage the power of sight. But it will soon. Roboflow has raised an additional $40M to further grow open source and enterprise visual AI. Delivering on the promise of computer vision and visual AI is bigger than any one co. Open source packages we maintain with the community see millions of downloads. Roboflow Universe supports 500M+ user created and shared images across 150k+ models. The hosted platform has delivered 1M hours of GPU training to open source projects. We remain committed to being the starting point for those tinkering, creating, and scaling up your computer vision projects from dataset to model to deployment (and, increasingly, in reverse order). We've also seen rapid adoption from 25,000 organizations, including some of the world's largest Fortune 100 companies, operating at worldwide scale. Roboflow's solutions keep trains on the tracks, ensure your packages show up on time, and provide the building materials for your homes. 40% of global GDP (!) is wrapped up in these operationally intensive, real world businesses, and they're seeing millions in ROI partnering with Roboflow. We'd love to build with you.

? In case you missed it, supervision 0.25.0 can track keypoint objects! ?? > Run a keypoint detector > Convert the result to Detections > Apply tracking > Visualize! ?? ?? Step-by-step guide: https://lnkd.in/gMaEix_F ?? P.S. we'll be adding more guides soon, so watch this space! #roboflow #computervision #supervision

Making complex video analysis robust! ?????? Trust me—it’s easy to build a video analysis that works well for 30 seconds. Building one that holds up for 24 hours is a different story. Objects may be small, move quickly, or get occluded by others—factors that all impact video quality. It’s great to see Supervision addressing these challenges in the 0.25.0 release! ?? ? ?? supervision-0.25.0 release notes: https://lnkd.in/d4PMt5tP As usual, thanks to all the collaborators who worked on this release. Linas Kondrackis, Onuralp SEZER ??????, Kshitij Aucharmal, Kader M., Prakhar Jain, Soham Kalburgi, Jo?o Marcos Cardoso Ramos da Silva, Andrey Blazejuk and others! ???? #computervision #python #github #opensource

Making complex video analysis robust! ?????? Trust me—it’s easy to build a video analysis that works well for 30 seconds. Building one that holds up for 24 hours is a different story. Objects may be small, move quickly, or get occluded by others—factors that all impact video quality. It’s great to see Supervision addressing these challenges in the 0.25.0 release! ?? ? ?? supervision-0.25.0 release notes: https://lnkd.in/d4PMt5tP As usual, thanks to all the collaborators who worked on this release. Linas Kondrackis, Onuralp SEZER ??????, Kshitij Aucharmal, Kader M., Prakhar Jain, Soham Kalburgi, Jo?o Marcos Cardoso Ramos da Silva, Andrey Blazejuk and others! ???? #computervision #python #github #opensource

I'm working on an XR + AI app to enhance fan engagement during live soccer games by showing player positions on a 3D map. I’m sharing a quick demo below, along with a link to the project’s GitHub page! Here’s a look at my progress so far: ?? Tech Overview: With the help of Roboflow sport repo, I’m using YOLO for detecting players and the pitch. Then, leveraging Roboflow’s homography transformation, these positions are mapped onto a 2D space and I bring the data into Unity to visualize player locations in a 3D environment. ?? What’s Next? The current demo is running on desktop, as I don’t have access to an Apple Vision Pro, Meta Quest or etc for XR testing yet. But I’m excited to keep developing and look forward to refining it for a more immersive XR experience. There’s still work to do, but every step has been a valuable learning experience. ?? GitHub: https://lnkd.in/djCm2qG2

We're live with our webinar on Florence-2! It's a massively useful model that handles a variety of tasks. Can be used off the shelf or with fine-tuning. Come join, welcome for everyone: https://lu.ma/tned46xg

Build a computer vision model to identify and label objects in just seconds -- with the new Box Prompting tool added to Roboflow. Check out a few examples here: https://lnkd.in/gTK2NeSh

Let’s celebrate the winner of AI Breakthrough of the Year – Roboflow! ?? At the forefront of the open-source AI movement, Roboflow is pushing the boundaries of AI to new heights. Congratulations to all the standout finalists in the category: Provoke Solutions UnityPoint Health Upvote Wells Enterprises Thank you to Lean TECHniques for supporting this award and driving digital innovation through AI. #2024PrometheusAwards #UniteIowaTech