Imagimob AI consists of; Imagimob AI Capture and Imagimob AI Studio. Imagimob AI Capture comprises a mobile app and a capture device. It’s used to capture and label synchronised sensor data and video (or other metadata) during the data capture phase. The mobile app allows for immediate labelling in the field. Once the data capture is ready, it is sent to a dedicated cloud service for further processing.
Imagimob AI Studio is used to do the AI modelling, feature engineering, AI learning, hardware optimisation, testing and tuning. It includes functionality for collecting, labelling and analyzing data. You can playback sensor data synchronised with video (or other metadata), in order to understand the data better.
The software use techniques inspired from the entire machine learning field in combination with our own innovations and techniques to design the best possible solution for a certain application. The aim is always high accuracy with low CPU and memory consumption with small MCUs in mind.
The deliverable from Imagimob AI is an application, built for a specific purpose. The application is an embedded software package that includes the trained AI model and optimised for a target hardware device. It can be easily integrated into 3rd party hardware platforms. For OEM devices an application is a source code / pre-compiled library written in ANSI C.
Imagimob AI Studio is becoming more and more automated which means that the leadtime to create an application is constantly getting shorter and shorter.
License type: License