Create products enhanced with embedded AI for industrial applications and home appliances
Factory Automation
Human Machine Interface
Smart Retail
Smart Appliances
Medical
Develop your product from scratch with Avnet Silica machine learning solutions
With a dedicated team of field application engineers, design solution engineers and sales people, the engagement with Avnet Silica results in delivering complete end-to-end solutions with support for:
- Chip level solutions
- System-on-Modules
- Production ready carrier boards
- Linux development
- Application support in cooperation with partners
Chip-Down Solutions
Development boards
System-on-Modules & Carrier boards
Industrial Application Processor Solutions
Use Case for Smart Retail: Print the price label by automated food recognition with machine learning
The implementation principle is valid for other markets, including industrial automation, medical or other markets.
Fruit classification on a retail weight scale to define the price of the fruitChallenges:
Fruit classification in itself is not a very big challenge today, but developing the real use case within a complex environment is:
- What if the fruit is in a plastic bag?
- What if you cannot control lighting in the store?
- How do you recognize the differences between similar fruit, like tangerines and oranges?
- What if you do not have sufficient training data?
The fruit is recognized based on vision with an embedded camera in combination with the weight parameter from the scale. Both vision data and weight values are treated jointly for the implementation on an optimized ResNet-like network. Training of the network is realized with pictures of fruit created with synthetic data instead of real images. Synthetic data is artificially manufactured and avoids the need of a big amount of training data. The Neural network is running on an embedded module with an NXP i.MX 8M Plus processor with integrated Neural Processing Unit (NPU). The product and price details are displayed on a touch screen.
Results:
Results are remarkable and the fruit is recognized accurate and in less than 4ms on an embedded solution with integrated machine learning capabilities in a complex environment of a retail shop.
Interested in this solution? Get in touch with us.
Inference comparison on the different processing engines of the NXP i.MX 8M Plus Application Processor for the fruit classification application
More use cases
Operator user identification
Allow access to an authorized employee to control a machine or a crane with user identification based on face recognition and voice control. Only known workers can operate the crane. The HMI (Human Machine Interface) is implemented with Yocto/Linux and QT GUI (Graphical User Interface).
Traffic monitoring (Smart City)
Road traffic is monitored to obtain information on different traffic parameters, such as the number of vehicles in a specific time frame, vehicle classification, average speed, individual speed of each vehicle, or number plate recognition.
Industrial Safety: Detection of wearing safety equipment
Detect if a worker wear his safety equipment like a helmet or security vest, and if it is not the case, send a notification to the supervisor. This is important for employee safety and for insurance companies. The implementation is vision based with object detection and object recognition tasks.
Your Machine Learning application
You want to use machine learning in for your own products, or want to discuss your ideas?
Get in touch with us to discuss your application
Machine Learning and AI - Training SeriesMaking edge intelligence a reality shouldn't be difficult. With embedded devices and eIQ™ Machine Learning (ML) software enablement from NXP, you can build your next intelligent application for the IoT edge. Want to learn more? Choose from the training options offered below to dive deeper into the world of AI and learn more about machine learning through NXP's EdgeVerse™ processor continuum and eIQ machine learning development software. |
eIQ™ MLThe NXP® eIQ™ machine learning software development environment enables the use of ML algorithms on NXP MCUs, i.MX RT crossover MCUs, and i.MX family SoCs. eIQ software includes inference engines, neural network compilers and optimized libraries. This software leverages open-source technologies and is fully integrated into our MCUXpresso SDK and Yocto development environments, allowing you to develop complete system-level applications with ease. |
Layerscape® 1046A and 1026A ProcessorsThe LS1046A and LS1026A processors integrate quad and dual 64-bit Arm® Cortex®-A72 cores with packet processing acceleration and high-speed peripherals. |
Layerscape® LX2160A ProcessorFor Edge Computing, Layerscape® LX2160A processor offers outstanding computing performance with a powerful packet offload and Ethernet controllers. |
AI Cloud with Microsoft Cognitive Services using i.MX8
Speech & Audio Processing | Image & Video Analytics
Beyond Machine Learning with NXP's i.MX 8M Plus Applications Processor
This webinar consists of two parts: a general presentation and additional in-depth topics. The event is intended for both decision makers, engineers and to anyone curious to get more details about the new i.MX 8M Plus Family of microprocessors.