DEEPCRAFT™ Edge AI Solutions

nobutton

About

About DEEPCRAFT™

DEEPCRAFT™ is Infineon's comprehensive new Edge AI software & tools offering. With DEEPCRAFT products and solutions, you significantly accelerate your path to innovative, trustworthy and convenient Machine Learning implementation. Leverage our broad portfolio to add low-power and low-memory smart features to your embedded devices.

The portfolio

The DEEPCRAFT Edge AI software platform & tools allow you to implement AI/ML functionalities in your next generation IoT edge  devices easily and conveniently. With DEEPCRAFT you can develop custom models from scratch based upon highly convenient and intuitive workflows and interfaces, or integrate off-the-shelf Ready Models and Solutions into your product, enabling you to considerably shorten time to market.

Deepcraft
Deepcraft
Deepcraft

DEEPCRAFT customer journey overview

The DEEPCRAFT customer journey is designed to be flexible to enter at any stage and to meet any Edge AI need; build, bring or buy the machine learning model that suits your needs.

Deepcraft
Deepcraft
Deepcraft

DEEPCRAFT™ Studio

DEEPCRAFT™ Studio (formerly Imagimob Studio) is a development platform for AI on edge devices. Use DEEPCRAFT Studio's unique and powerful modeling capabilities to make a custom Edge AI model using any time series or computer vision data. You can also get support from machine learning engineers to build the best model possible.

To make development as smooth as possible, users will find many DEEPCRAFT™ Studio Accelerators easily accessible in DEEPCRAFT Studio. These are the starting point for taking an AI model into production, and include the datasets, preprocessing, model architecture and instructions developers can utilize as the basis for training production-ready Edge AI models.

DEEPCRAFT Studio uses a unique, intuitive Graph UX interface. This lets users visualize the end-to-end machine learning workflow as graphs, providing a clear understanding of the modeling workflow from building to evaluating machine learning models.

Together with ModusToolbox™ and AURIX™ Development Studio, DEEPCRAFT™ Studio offers Infineon customers an end-to-end solution for machine learning model development and deployment into products. DEEPCRAFT Studio is developed by Imagimob, an Infineon Technologies company.

Learn more
Try today

DEEPCRAFT™ Ready Models

DEEPCRAFT Ready Models (formerly Imagimob Ready Models) are the fastest way for Infineon's customers to take AI features into production. These fully tested, market-ready models are designed to give companies a way to add AI into products without developing machine learning models on their own. DEEPCRAFT Ready Models are optimized to work with Infineon's sensors and MCUs.

DEEPCRAFT Ready Models use various sensors, and new models are always in development. There are currently eight Ready Models available:

  • DEEPCRAFT Ready Model for Baby Cry Detection
  • DEEPCRAFT Ready Model for Cough Detection
  • DEEPCRAFT Ready Model for Direction of Sound Arrival Detection
  • DEEPCRAFT Ready Model for Factory Alarm & Siren Detection
  • DEEPCRAFT Ready Model for Fall Detection
  • DEEPCRAFT Ready Model for Gesture Detection
  • DEEPCRAFT Ready Model for Siren Detection
  • DEEPCRAFT Ready Model for Snore Detection

 

Learn more
Try today

DEEPCRAFT™ Voice and Audio

DEEPCRAFT™ solves voice and audio challenges for edge device providers by leveraging the audio and AI acceleration capabilities of Infineon’s PSOC™ Edge MCUs while achieving optimal system-level power and performance.  The ability to run AI models locally allows for increased control, simplicity, reliability, security and brand consistency.

DEEPCRAFT™ Voice Assistant

Edge device providers are increasingly seeking intuitive and human-centric ways to allow users to interact with their products.  DEEPCRAFT Voice Assistant allows you to build a custom voice interface that is flexible to phrasing variations and aligned with your product’s brand and interface.  Voice Assistant is optimized for PSOC Edge MCUs, enabling AI-powered voice capabilities in many applications like wearables, robotics and smart home devices.

Edge device providers are also looking for ways to enable AI features in their products without requiring their customers go through the hassle of cloud connectivity.  Local AI processing can ensure reliability and brand consistency by eliminating the risk of cloud provider APIs changing over time.  DEEPCRAFT Voice Assistant is a cutting-edge voice recognition solution designed to address these needs and to enable optimal performance and system level power efficiency.

DEEPCRAFT™ Audio Enhancement

Edge devices powered by voice features like AI-powered voice control must separate unwanted environmental noise from a user’s voice to accurately respond and react to commands. DEEPCRAFT Audio Enhancement provides a suite of advanced audio pipeline components to ensure device providers deliver best-in-class voice products such as speakers, thermostats, wearables, as well as small and large appliances. 

DEEPCRAFT Audio Enhancement delivers AI-powered components that:

  • Remove environmental noise with Noise Suppression
  • Remove device generated noise with Acoustic Echo Cancellation
  • Focus on the intended voice with Beamforming.                  
FAQs

What is Edge AI?

‘Edge’ refers to a device that is at the edge of a network. ‘AI’ in this case means that artificial intelligence is the method for processing the data. 

Edge AI is when artificial intelligence (AI) algorithms are processed locally on a hardware device close to a sensor or a signal. The algorithms use data that is created on the device. Deep learning is a commonly used type of machine learning algorithm.

Read more in this article from the Infineon Technologies company Imagimob here.

What types of sensors and data can I use with DEEPCRAFT?

With DEEPCRAFT Studio, you can use data from sensors with any type of time series data. 

Some of the sensors supported are:

  • Radar
  • Microphone
  • Camera
  • IMU
  • Accelerometer

Is DEEPCRAFT Edge AI only available for Infineon hardware?

DEEPCRAFT software is optimized for deployment on Infineon hardware. If you have other hardware, you can still use much of the DEEPCRAFT offering, with some coding work.

About DEEPCRAFT™

DEEPCRAFT™ is Infineon's comprehensive new Edge AI software & tools offering. With DEEPCRAFT products and solutions, you significantly accelerate your path to innovative, trustworthy and convenient Machine Learning implementation. Leverage our broad portfolio to add low-power and low-memory smart features to your embedded devices.

The portfolio

The DEEPCRAFT Edge AI software platform & tools allow you to implement AI/ML functionalities in your next generation IoT edge  devices easily and conveniently. With DEEPCRAFT you can develop custom models from scratch based upon highly convenient and intuitive workflows and interfaces, or integrate off-the-shelf Ready Models and Solutions into your product, enabling you to considerably shorten time to market.

Deepcraft
Deepcraft
Deepcraft

DEEPCRAFT customer journey overview

The DEEPCRAFT customer journey is designed to be flexible to enter at any stage and to meet any Edge AI need; build, bring or buy the machine learning model that suits your needs.

Deepcraft
Deepcraft
Deepcraft

DEEPCRAFT™ Studio

DEEPCRAFT™ Studio (formerly Imagimob Studio) is a development platform for AI on edge devices. Use DEEPCRAFT Studio's unique and powerful modeling capabilities to make a custom Edge AI model using any time series or computer vision data. You can also get support from machine learning engineers to build the best model possible.

To make development as smooth as possible, users will find many DEEPCRAFT™ Studio Accelerators easily accessible in DEEPCRAFT Studio. These are the starting point for taking an AI model into production, and include the datasets, preprocessing, model architecture and instructions developers can utilize as the basis for training production-ready Edge AI models.

DEEPCRAFT Studio uses a unique, intuitive Graph UX interface. This lets users visualize the end-to-end machine learning workflow as graphs, providing a clear understanding of the modeling workflow from building to evaluating machine learning models.

Together with ModusToolbox™ and AURIX™ Development Studio, DEEPCRAFT™ Studio offers Infineon customers an end-to-end solution for machine learning model development and deployment into products. DEEPCRAFT Studio is developed by Imagimob, an Infineon Technologies company.

Learn more
Try today

DEEPCRAFT™ Ready Models

DEEPCRAFT Ready Models (formerly Imagimob Ready Models) are the fastest way for Infineon's customers to take AI features into production. These fully tested, market-ready models are designed to give companies a way to add AI into products without developing machine learning models on their own. DEEPCRAFT Ready Models are optimized to work with Infineon's sensors and MCUs.

DEEPCRAFT Ready Models use various sensors, and new models are always in development. There are currently eight Ready Models available:

  • DEEPCRAFT Ready Model for Baby Cry Detection
  • DEEPCRAFT Ready Model for Cough Detection
  • DEEPCRAFT Ready Model for Direction of Sound Arrival Detection
  • DEEPCRAFT Ready Model for Factory Alarm & Siren Detection
  • DEEPCRAFT Ready Model for Fall Detection
  • DEEPCRAFT Ready Model for Gesture Detection
  • DEEPCRAFT Ready Model for Siren Detection
  • DEEPCRAFT Ready Model for Snore Detection

 

Learn more
Try today

DEEPCRAFT™ Voice and Audio

DEEPCRAFT™ solves voice and audio challenges for edge device providers by leveraging the audio and AI acceleration capabilities of Infineon’s PSOC™ Edge MCUs while achieving optimal system-level power and performance.  The ability to run AI models locally allows for increased control, simplicity, reliability, security and brand consistency.

DEEPCRAFT™ Voice Assistant

Edge device providers are increasingly seeking intuitive and human-centric ways to allow users to interact with their products.  DEEPCRAFT Voice Assistant allows you to build a custom voice interface that is flexible to phrasing variations and aligned with your product’s brand and interface.  Voice Assistant is optimized for PSOC Edge MCUs, enabling AI-powered voice capabilities in many applications like wearables, robotics and smart home devices.

Edge device providers are also looking for ways to enable AI features in their products without requiring their customers go through the hassle of cloud connectivity.  Local AI processing can ensure reliability and brand consistency by eliminating the risk of cloud provider APIs changing over time.  DEEPCRAFT Voice Assistant is a cutting-edge voice recognition solution designed to address these needs and to enable optimal performance and system level power efficiency.

DEEPCRAFT™ Audio Enhancement

Edge devices powered by voice features like AI-powered voice control must separate unwanted environmental noise from a user’s voice to accurately respond and react to commands. DEEPCRAFT Audio Enhancement provides a suite of advanced audio pipeline components to ensure device providers deliver best-in-class voice products such as speakers, thermostats, wearables, as well as small and large appliances. 

DEEPCRAFT Audio Enhancement delivers AI-powered components that:

  • Remove environmental noise with Noise Suppression
  • Remove device generated noise with Acoustic Echo Cancellation
  • Focus on the intended voice with Beamforming.                  

FAQs

What is Edge AI?

‘Edge’ refers to a device that is at the edge of a network. ‘AI’ in this case means that artificial intelligence is the method for processing the data. 

Edge AI is when artificial intelligence (AI) algorithms are processed locally on a hardware device close to a sensor or a signal. The algorithms use data that is created on the device. Deep learning is a commonly used type of machine learning algorithm.

Read more in this article from the Infineon Technologies company Imagimob here.

What types of sensors and data can I use with DEEPCRAFT?

With DEEPCRAFT Studio, you can use data from sensors with any type of time series data. 

Some of the sensors supported are:

  • Radar
  • Microphone
  • Camera
  • IMU
  • Accelerometer

Is DEEPCRAFT Edge AI only available for Infineon hardware?

DEEPCRAFT software is optimized for deployment on Infineon hardware. If you have other hardware, you can still use much of the DEEPCRAFT offering, with some coding work.

Documents

Documents

Design resources