• Skip to homepage
  • Skip to main content
  • Skip to main navigation
  • Skip to meta navigation
Zühlke - zur Startseite
  • Business
  • Careers
  • Events
  • About us

Language navigation. The current language is english

  • Expertise
    • AI implementation
    • Cloud
    • Cybersecurity
    • Data solutions
    • DevOps
    • Digital strategy
    • Experience design
    • Hardware engineering
    • Managed services
    • Software engineering
    • Sustainability transformation
    Explore our expertise

    Highlight Case Study

    Airport concept

    Zurich Airport transforms operations for a data-driven future

    Learn more
  • Industries
    • Banking
    • Insurance
    • Healthcare providers
    • MedTech
    • Pharma
    • Industrial sector
    • Commerce & retail
    • Energy & utilities
    • Government & public sector
    • Transport
    Explore our industries

    Subscribe to recieve the latest news, event invitations & more!

    Sign up here
  • Case studies

    Spotlight case studies

    • Global Research Platforms and Zühlke are fighting Alzheimer's disease
    • Brückner Maschinenbau leverages GenAI to optimise efficiency by improving master data management
    • UNIQA: AI chatbot increases efficiency – 95% accuracy with half the effort
    Explore more case studies

    Highlight Case Study

    Airport concept

    Zurich Airport transforms operations for a data-driven future

    Learn more
  • Insights

    Spotlight insights

    • How to apply low-code technologies in the insurance industry
    • Retail CTO playbook for managing the tech transformation
    • DeepSeek and the rise of open-source AI: A game-changer for businesses?
    Explore more insights

    Highlight Insight

    AI adoption: Rethinking time and purpose in the workplace

    Learn more
  • Academy
  • Contact
    • Austria
    • Bulgaria
    • Germany
    • Hong Kong
    • Portugal
    • Serbia
    • Singapore
    • Switzerland
    • United Kingdom
    • Vietnam

    Subscribe to recieve the latest news, event invitations & more!

    Sign up here
Zühlke - zur Startseite
  • Business
  • Careers
  • Events
  • About us
  • Expertise
    • AI implementation
    • Cloud
    • Cybersecurity
    • Data solutions
    • DevOps
    • Digital strategy
    • Experience design
    • Hardware engineering
    • Managed services
    • Software engineering
    • Sustainability transformation
    Explore our expertise

    Highlight Case Study

    Airport concept

    Zurich Airport transforms operations for a data-driven future

    Learn more
  • Industries
    • Banking
    • Insurance
    • Healthcare providers
    • MedTech
    • Pharma
    • Industrial sector
    • Commerce & retail
    • Energy & utilities
    • Government & public sector
    • Transport
    Explore our industries

    Subscribe to recieve the latest news, event invitations & more!

    Sign up here
  • Case studies

    Spotlight case studies

    • Global Research Platforms and Zühlke are fighting Alzheimer's disease
    • Brückner Maschinenbau leverages GenAI to optimise efficiency by improving master data management
    • UNIQA: AI chatbot increases efficiency – 95% accuracy with half the effort
    Explore more case studies

    Highlight Case Study

    Airport concept

    Zurich Airport transforms operations for a data-driven future

    Learn more
  • Insights

    Spotlight insights

    • How to apply low-code technologies in the insurance industry
    • Retail CTO playbook for managing the tech transformation
    • DeepSeek and the rise of open-source AI: A game-changer for businesses?
    Explore more insights

    Highlight Insight

    AI adoption: Rethinking time and purpose in the workplace

    Learn more
  • Academy
  • Contact
    • Austria
    • Bulgaria
    • Germany
    • Hong Kong
    • Portugal
    • Serbia
    • Singapore
    • Switzerland
    • United Kingdom
    • Vietnam

    Subscribe to recieve the latest news, event invitations & more!

    Sign up here

Language navigation. The current language is english

Homepage zuehlke.com

Can a 20$ device be your entry into machine learning?

June 10, 20204 Minutes to Read
IOT distributed ledger technology
With insights from
Davinder Chandhok Zühlke

Davinder Chandhok

Professional Software Engineerdavinder.chandhok@zuehlke.com
  • Computer vision systems offer enormous potential for reducing operating costs.

  • One solution could be to use cost-effective edge devices to run the algorithms.

  • Hybrid solutions are possible in certain application scenarios.

“More power” – that’s what AI and especially computer vision is often associated with. Indeed, the algorithms need processing power which can result in a complex and costly infrastructure. However, recent advances in microcontroller architectures can make AI and especially computer vision a lot more accessible with costs per device as low as $20.

Computer vision systems can reduce operating costs by supporting personnel in standard or repetitive tasks such as monitoring machines or facilities. Most of the recent advances in deep learning for computer vision rely on expensive graphics cards, such as the NVIDIA Titan V  ($3000). Moreover, most architectures are based on cloud infrastructure. This may be problematic due to latency concerns, complete lack of network infrastructure, or security concerns. These drawbacks can be addressed by employing cost-effective inference on the edge.

Recent advances in microcontroller architectures are enabling deep learning on smaller, cheaper, and lower-power devices, bringing down the cost to as low as $20. These devices form the basis of near real-time applications that can run for months or even years without maintenance. Examples of these applications include preventive maintenance and quality control in production lines, as well as surveillance for security and safety applications.

Microcontroller devices for deep learning inference

There are a currently a variety of options for microcontroller devices that are capable of running deep learning inference. These include full camera/microcontroller packages, such as the OpenMV camera, processor/co-processor products, such as the ARM Cortex-M55/Ethos-U55 combination, and other options in-between with varying selections of peripherals. Below is a table of interesting options and their relevant characteristics:

Tabelle

It is important to note that these options are all intended to run inference models, as opposed to training a model. This means training must still be done on more powerful hardware, but this does not need to purchased outright.

How to develop edge computer vision applications

Development of an edge computer vision application begins just like with traditional deep learning computer vision applications. There is the initial data collection phase, during which images are collected under the same conditions as they would be in the completed solution. The data is then cleaned and preprocessed before training a model appropriate to the inference device.

Once the trained model achieves expected results in the validation environment, it is prepared for deployment on the microcontroller through an optimization process to take advantage of the microcontroller’s features . For certain models, there are further optimizations that remove unnecessary overhead, making it even more efficient on small devices.

This optimized model can then be deployed to the same platform used for initial data capturing and energy consumption benchmarks can be performed. These platforms can be highly optimized for power consumption, depending on requirements, which opens the possibility of running them on battery power alone for extended periods of time without human intervention.

Hybrid edge/server architecture

In certain use cases the microcontroller devices may record new situations that they are unable to classify. This presents an opportunity to use a hybrid edge/server architecture commonly used in self-driving cars to collect/utilize new data, as described by Mohanbir Sawhney. Edge devices (microcontrollers) run inference models and collect new data, and a server retrains the models using the new data in order to expand the abilities of the edge devices. Having implemented such a pipeline in a couple of projects, we perceived that developing a proof-of-concept in this area is not overly complex.

Similar to traditional deep learning solutions

Developing such a solution with microcontrollers is an effective approach to reduce the solution’s computational power, energy footprint and hardware cost, without requiring significant new infrastructure, in contrast to current approaches with powerful hardware. The process remains similar to a traditional deep learning solution, with some extra optimizations to bring the application to a smaller device with a smaller footprint. A bonus is that these deployments do not require connectivity unless continuous data collection is necessary. For continuous data collection, it is also possible to create an unsupervised learning pipeline, similar to that described in the blogpost of my colleague Kevin Henrichs.

Davinder Chandhok Zühlke

Davinder Chandhok

Professional Software Engineer

Davinder Chandhok is a Professional Data Scientist with a focus on computer vision. He has been involved in the development of computer vision solutions for industrial equipment since 2018 and recently began developing skills in cloud technologies to enhance data science projects with cloud connectivity. Davinder Chandhok holds a Bachelor of Engineering in Automation and Control Engineering.

View LinkedIn Profile of Davinder Chandhok
Davinder Chandhok Zühlke

Explore more Insights

Industrial sector

Subscription-based business models as growth opportunity

Learn more
Commerce & retail

Recognising the benefits of a software-driven development approach for physical products

Learn more
colleagues brainstorming
Discover all Insights

Get to know us

  • About us
  • Impact & commitments
  • Facts & figures
  • Careers
  • Event Hub
  • Insights Hub
  • News sign-up

Working with us

  • Our expertise
  • Our industries
  • Case studies
  • Partner ecosystem
  • Training Academy
  • Contact us

Legal

  • Privacy policy
  • Cookie policy
  • Legal notice
  • Modern slavery statement
  • Imprint

Request for proposal

We appreciate your interest in working with us. Please send us your request for proposal and we will contact you within 72 hours.

Request for proposal
© 2025 Zühlke Engineering AG

Follow us

  • External Link to Zühlke LinkedIn Page
  • External Link to Zühlke Facebook Page
  • External Link to Zühlke Instagram Page
  • External Link to Zühlke YouTube Page

Language navigation. The current language is english