All your experts
on a single platform
All your experts
Finally – the tool for data teams to create end-to-end computer vision applications at scale
No more one-person
Deploying algorithms in complex, high-value environments is hard work. Robovision AI takes the weight off data scientists’ shoulders with a single platform that empowers operators to manage & retrain AI applications themselves
Why current AI applications don’t scale
- Data experts are asked to spend time on production processes and adapting parameters, instead of focusing on where they excel: creating new algorithms
- There being no standard for scripts means there are no clear templates for collaboration and algorithms and their components are hard to re-use
- Closed environments make it near impossible for companies to consolidate their intellectual property
And why Robovision AI does
- Scripting itself is scripted. It is standardized and automatic, creating algorithms that can be used and reused without the need of an expert
- No need for data teams to cover the basic tasks either. Using the same platform, operators and product experts take over once the framework is up and running
- A standardized test environment allows you to test your own algorithms using the same parameters time and again, greatly improving system stability
- Build your IP with every line of code and keep the knowledge in-house
Tons of ready to use Algorithms
Wether you want to pick, detect, track, cut, sort, locate, classify, count, estimate, measure or spot.
to work together
Label, train, deploy & retrain - all in one web app.
The Robovision AI Software Development Kit is a Python tool for data scientists that standardizes the implementation of algorithms.
In return it helps the developer to debug and test the algorithms on a runtime that will automatically parallelize the algorithm to allow for higher throughput.
Designed to Scale
Docker is a set of platform as a service products that uses OS-level virtualization to deliver software in packages called containers. Containers are isolated from one another and bundle their own software, libraries and configuration files; they can communicate with each other through well-defined channels.
Kubernetes is an open-source system for automating deployment, scaling, and management of containerized applications. It groups containers that make up an application into logical units for easy management and discovery.
Ray is a high-performance distributed execution framework targeted at large-scale machine learning and reinforcement learning applications. It achieves scalability and fault tolerance by abstracting the control state of the system in a global control store and keeping all other components stateless.
Robovision AI can inherit customers’ custom name, copyright, logos, icons, website links, documentation, and other elements of your corporate identity.
You can use whichever type of smart camera or vision system you wish. Interesting brands to explore are: IDS, net-gmbh, Basler, Axis, Sony (video security), We support all cameras with GiGE vision, RTSP enabled, OpenCV support and the like. If there’s a project that requires a non-supported camera, we’ll be happy to help you fix that.
Are you using satellite images, hyperspectral images, microscopic images, or simply images of dogs? Our platform treats each of them the same, as long as you download them in the following graphic file formats. JPEG, JPG, PNG, BMP & GIF.
Some projects need a higher dimensional understanding of the real world. Our tooling therefore supports 3D point clouds that represents the 3D shape of any object or DICOM (Digital Imaging and Communications in Medicine) for medical images like CT-scans.