End to End


Robovision AI is an AI-powered computer vision platform that enables customers to build, train, and run machine learning models for high-performance, scalable computer vision applications.

Instead of hard-coding, we train algorithms much like how we teach our children, through repeatedly showing unique examples. This process starts by transferring intelligence of domain experts to algorithms through annotating images and video streams.

The next step in the process is to train AI by feeding it annotated data sets. Our platform makes it easy to experiment and measure accuracy.

Simple configuration and calibration

Our software provides the tools to continuously improve accuracy and fine-tune your deployed AI applications. Varying conditions such as camera angle/position, light and weather conditions can impact the performance of your AI. Retrain your AI for specific streams or scenes, all without the need of data science knowledge.

The Robovision AI store is where you can find use-cases developed by us, our partners and customers. We have pre-trained the models on publicly available data and therefore it provides a base level accuracy. Access to our AI store can be provided either directly through us or one of our partners.

The brain of the platform

A Pipeline

At Robovision we deconstruct machine vision challenges into chains of algorithm and application cells that work together in what we call pipelines This capability provides the flexibility to offer the myriad of use-cases we bring to the market.

Data Driven


Our software has been built to easily arrange cells and construct pipelines. This capability provides the flexibility to offer the myriad of use-cases that Robovision brings to the market. For example, the below pipeline we can use for both a security and traffic application.

Request a demo

Application deployment, scaling and management


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.