Date 09/07/21

Don’t build your embedded ML/AI pipeline from scratch

Developing embedded real-time applications is on its own one of the most complex and time consuming software disciplines. However tempting it may be to start incorporating machine learning (ML) models and new state-of-the-art artificial intelligence techniques into your products, there are many hurdles along the way and a large risk of failure for the project.

As an alternative there are software platforms available that can help embedded developers with the data science, machine learning model creation, training and evaluation parts, which lets the embedded developers focus on their areas of expertise. This will vastly speed up embedded software development. 

AI is here to stay
It’s now a bit more than 5 years since the Google DeepMind computer AlphaGo beat the human Go world champion player Lee Sedol. This marked an important breakthrough for computers to take on much more challenging cognitive tasks than ever before. Less than a year later, the Asilomar AI Principles for “Beneficial Intelligence” were established and signed by more than 1000 AI researchers, to prevent AI research from leading to harmful superintelligence. There was no doubt that the expectations on AI and the related field of machine learning were high.

Between then and now, a lot has happened. We don’t have general AI, but that was never the expectation in such a short time perspective. One significant change is mental: Algorithms will become much more present and have a larger role in our lives, and they need data to work efficiently. This is now common knowledge among all of us. Secondly, some of the most mature machine learning techniques such as classification and anomaly detection are now there generating value and revenue.

Slower at the Edge
Still, most of the value is generated in online businesses, where the algorithms can run on big servers with a lot of compute power. Numerous reports indicate that there is an undiscovered treasure hiding in the ten billion IoT, or edge, devices out there that are rarely using anything else than simple thresholding or some rudimentary signal processing. Not only are these devices numerous, their number is also expected to more than double, to 25 billion, by 2030. Many companies see the opportunity of making their IoT devices smarter to act more autonomously, thereby cutting field personnel costs and reducing downtime. However, we see that the more rapid adoptions of machine learning that happens in the connected cloud businesses is not present at the edge yet. 

There is something there that slows down the progress. To get the machine learning models and software to the edge devices we must first bridge a gap: These companies have their main expertise in embedded software development, a field that requires knowledge that spans many complex areas. The teams are composed of firmware developers, hardware engineers with sensor and microcontroller knowledge, testers, and sometimes software engineers with signal processing knowledge. They may have 30+ years of knowledge. They are good, really good, at what they are doing.

So, what happens when a large corporate decides that the company will launch a new digital initiative where automation, insight and value will be created from AI? They now have the option to to build all of this inhouse, or  hire a team of consultants work a few months to implement a solution or to buy a solution off the shelf. Let’s take a closer look at these alternatives.

1) Doing it on your own from scratch may seem like a tempting approach. You own the software, have full control over it, and you have all the knowledge in your team. But let’s look at what it actually means. First, the group needs to hire data scientists and/or machine learning engineers. Among the around 25 million developers in the world, machine learning engineers are counted in hundreds of thousands worldwide, so finding the right people is hard. As soon as you have your team in place, with all what that means, you can start building the model building infrastructure. This involves writing software for the data collection pipeline, data management, labelling or annotation of data, model building, model training and model deployment. These are many steps and a lot of software to write. Consider also that machine learning in general and “tinyML” (the branch of ML for resource constrained devices) in particular, is a lively research field where you constantly need to be on top of things to get the most out of your system.


2) To hire consultants that work for a few months or half a year to set up the system can look like a nice short cut. Some of the typical hurdles involve, as before, finding good people for the work. Second, it is important that the consultants get a deep understanding of your specific problem, which often is not included in the time frame of the project. Lastly, when the project is over and the experts have left, there is usually no one at the company that deeply understands what was done and how to make changes to it. 


3)To buy a solution or service off the shelf means that you will get a head start in your project by utilizing a tool that experts in the field have developed during years and put a lot of time, energy and clever ideas into. Let’s look at such a solution below.


Let the embedded developers do what they are best at
To find a tool that does the job of the machine learning expert lets the team of embedded developers continue to do what they are best at. At Imagimob we have worked with embedded AI for many years, and in numerous real customer projects we have found solutions that can speed up the model development process, from data collection to deployment. We have gone through all the painful steps of creating code for data management, labelling, training, and iterating on models and last but not least translating the model to C code that can easily be deployed on a microcontroller. We know where people spend time, since we have been there ourselves. 

After a few years we decided to make this tool – Imagimob AI – available to the public. What we have in mind is the team of embedded developers that are curious to start deploying AI models but don’t have the expertise in building it all from scratch. Imagimob AI takes the user through a few steps of data management, labelling, model generation and training, where the end result is plain, well written C code – easy-to-read and make modifications to. We believe that this transparency and flexibility is something that embedded developers appreciate. Tutorials with step-by-step instructions and example data are included for a range of different projects such as human motion recognition, radar gesture detection and audio projects with sound detection. Users can get started quickly and generate the embedded code with a click of a button.

What does Imagimob AI offer the embedded developer?

With Imagimob AI the workflow of building AI models is greatly simplified and embedded developers can quickly iterate over the process and receive C-code as output that is easily integrated into their embedded projects. 

For embedded developers with no previous experience in machine learning, Imagimob AI offers a number of advantages such as:

  • Suggesting what model architecture to use based on the current type of project and data.
  • Suggesting the type of preprocessor that best fits the data. 
  • No need to understand the frameworks for model training or to log in and use cloud services or other training clusters.
  • No need to implement software for data collection and labelling.
  • No need to be on top of the latest in machine learning.


For embedded developers with experience in machine learning, Imagimob AI enables him or her to:

  • Get suggestions for model building and the ability to edit the architecture and add your own model layers and preprocessor code.
  • Import models (trained or untrained) from other machine learning frameworks, train if necessary, and convert them into C code.
  • Focus on data quality and careful labelling instead of tracking bugs in your data management scripts.
  • Spend time on integrating efficient code on the microcontroller instead of being on top of and implementing the latest AI research.

Do you want to learn more how you can benefit from Imagimob AI? Sign up for a Free Trial!


Date 11/25/21

Imagimob AI in Agri-tech

Imagimob has been part of an EU project, together with 55 co...

Date 11/12/21

Webinar: Build and deploy a keyword spotting AI ap...

During this webinar we will demonstrate how easy it is to de...

Date 10/19/21

Deploying Edge Models - Acconeer example

Date 10/11/21

Imagimob AI used for condition monitoring of elect...

Date 09/21/21

Tips and Tricks for Better Edge AI models

Date 09/07/21

Don’t build your embedded ML/AI pipeline from scra...

Date 06/18/21

Imagimob AI integration with IAR Embedded Workbenc...

Date 06/17/21

Video recording of webinar "Gesture control using ...

Date 05/10/21

Webinar - Imagimob to present at Arm AI Virtual Te...

Date 04/23/21

Gesture Visualization in Imagimob Studio

Date 04/01/21

New team members

Date 03/15/21

Imagimob featured in Dagens Industri

Date 03/09/21

Imagimob AI 2.6

Date 02/22/21

Customer Case Study: Increasing car safety through...

Date 01/22/21

tinyML Summit 2021

Date 01/19/21

The Future is Touchless: Radical Gesture Control P...

Date 12/18/20

Veoneer, Imagimob and Pionate in joint research pr...

Date 11/20/20

Edge computing needs Edge AI

Date 11/12/20

Imagimob video from tinyML Talks

Date 10/28/20

Agritech: Monitoring cattle with IoT and Edge AI

Date 10/19/20

Arm Community Blog: Imagimob - The fastest way fro...

Date 10/01/20

Edge Computing World in Santa Clara, CA, USA

Date 09/21/20

Imagimob video from Redeye AI seminar

Date 09/02/20

Edge AI Summit 2020 (US)

Date 08/20/20

Edge AI & Industrial Edge (Germany)

Date 06/07/20

Case study - How to Build an Embedded AI applicati...

Date 05/20/20

Redeye - Artificial Intelligence Seminar 2020

Date 05/07/20

Webinar - Gesture control using radar and Edge AI

Date 04/08/20

Nordic Semiconductors

Date 03/11/20

CES 2020 - Las Vegas

Date 02/23/20

How to build an embedded AI application

Date 12/23/19

Hannover Messe

Date 12/11/19

Edge AI for techies, updated December 11, 2019

Date 12/11/19

Edge AI for techies, updated December 11, 2019

Date 12/05/19

Article in Dagens Industri: This is how Stockholm-...

Date 10/24/19

Imagimob AI - the video

Date 10/17/19

The past, present and future of edge machine learn...

Date 09/06/19

The New Path to Better Edge AI Applications

Date 07/01/19

Edge Computing in Modern Agriculture

Date 06/14/19

The Guide to Successful AI Projects - A Real World...

Date 04/07/19

Our Top 3 Highlights from Hannover Messe 2019

Date 03/26/19

The Way You Collect Data Can Make or Break Your Ne...

Date 04/04/18

The AI Project Process - How to succeed including ...

Date 03/23/18

AI Research and AI Safety

Date 03/11/18

What is Edge AI / tinyML ?

Date 01/30/18

Wearing Intelligence On Your Sleeve

Date 01/30/18

Imagimob and Autoliv demo at CES 2018

Date 11/23/17

Wearing Intelligence On Your Sleeve - Part 2 (vide...

Date 05/24/17

Wearing Intelligence On Your Sleeve - Part 1

LOAD MORE keyboard_arrow_down