Imagimob Ready Models are production ready ML models that you can use without the time, cost and resources needed to create custom models. These are ideal for companies that don't have or want to spend the resources to collect, validate, and label the necessary data, and then train custom machine learning models on that data.
The Baby Cry model is created to be used in smart home or lifestyle products that want to alert adults to the sound of baby or toddler crying in another room, or to activate baby soothing features.
- Captures more than 86-95% of baby cries at up 5 meters distance from device
- Robust against the most common background sounds, particularly indoor
- Suitable for babies and children 0-4 years old
The Coughing model is designed for use in healthcare products or wearables. It detects coughing, which can indicate illness or other respiratory conditions, and can be used to identify potential environmental hazards.
- Captures at least 84-94% of coughs
- Robust against the most common indoor and outdoor background sounds
- Measures coughs per hour to identify 'sick' versus 'healthy' user
This model uses audio event detection to identify emergency vehicle sirens. This can be used to alert pedestrians to emergency vehicles in their vicinity, or to trigger other safety features in wearables.
- Captures over 80-95% of siren sounds
- Robust against common traffic background sounds in different environments
- Able to detect siren sounds from all directions
This model is ideal for companies with healthcare or wearable products that want to identify snoring. This important feature can be used to identify health or environmental issues.
- Captures more than 89-96% of snores
- Robust against the most common background sounds, particularly indoor
- Flexibly designed to be used in wearables or in devices that are placed near the bed
(Don't see what you're looking for? Contact sales to find out what new models are in the works!)
Alarm detection brings more safety to everyday life. Use Acoustic Event Detection in smart home devices to trigger notifications to customers phones or wearables when a fire alarm or other indoor alarm goes off.
This audio-based Ready Model can be integrated into nearly any smart home product. Click 'I'm interested!' below to register your interest and we will let you know when this model is available.
Adding gesture control to your devices makes life easier for anyone using your product. Want to turn off the tv? Just swipe your hand to the right. Want to turn on your coffee machine? Swipe up.
This radar-based Ready Model has limitless possibilities for consumer products. Click 'I'm interested!' below to register your interest and we will let you know when this model is available.
Radar can be used to detect different surfaces, enabling better than ever performance in products like robot vacuum cleaners and lawn mowers. This Edge AI model makes your product better over time with continuous learning.
Click 'I'm interested!' below to register your interest and we will let you know when this model is available.
Do you ever take off your headphones and realize hours later that you forgot to turn them off, they've kept playing music and the battery is drained? Using CAPSENSE™ and a robust Machine Learning model, you can now get a solution that detects whether or not a device is being worn.
This Ready Model can be integrated into wearables to power them down when they are not in use, providing a better user experience. It can integrated into safety helmets, to make sure they are in use in cases where they need to be worn.
Smart devices can detect yelling and audio for a wide variety of uses. Add yelling detection to security systems. Or add commotion detection to your smart speaker to adjust the volume of music playing in a room or venue.
Click 'I'm interested!' below to register your interest and we will let you know when this model is available.
Arc-faults cause more than 30,000 fires in homes in the US each year. Using Machine Learning, you can more accurately detect when an actual arc-fault is happening and trigger the circuit interrupter, thus limiting potential harm to the electrical circuits, and avoiding a fire.
This Ready Model is intended to be run in arc fault circuit interrupters (AFCI), and triggers based on the current and voltage measurements of the electrical signals
We are continuously releasing new Ready Models, with various sensors and uses. Most of our Ready Models are based on:
- Audio: for detecting specific sounds
- Capacitive Sensing: for using touch to trigger an event
- Radar: for detecting presence, objects or materials
- IMU: for detecting the motion of humans such as falling or vibrations in a machine
- Complete models ready to be put into production
- Fast time to market - no development or AI know-how required
- High accuracy and production quality
- Fully tested on a large library of datasets to ensure model works in wide range of scenarios
- Low memory footprint and inference time
- Data is kept local and not shared to the cloud
- Can be launched right away on embedded hardware (deployment-ready Infineon MCUs such as PSoC™ 6 and AURIX. Talk to us about how to deploy on other hardware).
- Easy to integrate and deploy into consumer products
- Using ML models to add new features makes them future-proof, model improvements and updates with OTA software in ModusToolbox™
- Designed to work with wearables, health and safety devices that are familiar and convenient for end-users
Can't wait to get your hands on one of our Ready Models? Fill out this form and we will contact you shortly.
Interested in a Ready Model you don't see here? Get in touch so we can get the right model in your device as soon as possible!