Application overview
Detecting children in a parked car is an important safety function in modern vehicles. Legacy systems may only detect presence or movement inside the vehicle which leads to false alerts and inconvenience to the end user.
Powered by our low power AWRL6432 or the high resolution AWRL6844 radar, engineers can easily train models to distinguish between simple movement in the vehicle (from toys to phones to lanyards) and the actual breathing and movement of a baby or child.
Starting evaluation
Data collection
Capture accurate Radar data with the AWRL6844 or AWRL6432 device, enabling full AI processing done completely on the edge through the integrated MCU and hardware accelerator.
Data quality assessment
This image showcases the macrodoppler feature as a baby is in the rear footwell of the vehicle. The movement of a child's breathing can be distinguished from the movement of toys and other objects that may be moving in the vehicle.
Build and train your model
Radar data is collected using TI's capture tools and labelled using standard machine learning workflows. The model is trained using two separate networks.
The first network detects on a per-seat basis if the seat is occupied or not. This uses the macrodoppler feature to prevent false alarms. The second network looks at any occupied zones and determines based on point cloud features if that occupant is a child.
Deploying your model
This demo and associated tools can work on either the AWRL6844 or AWRL6432 devices. The higher resolution AWRL6844 device can perform child classification for up to 2 rows, while the AWRL6432 demo focuses on 1 row detection.
All the hardware, software and resources you’ll need to get started
Hardware
AWRL6432
Single-chip low-power 57-GHz to 64-GHz automotive mmWave radar sensor.
AWEL6844
Automotive single-chip high-performance, low-power, 57GHz to 64GHz mmWave radar sensor.
AWRL6844EVM
Easy-to-use evaluation module for the xWRL6844 mmWave radar sensor.
AWRL6432BOOST
BoosterPack™ evaluation module for single-chip low-power mmWave radar sensor.
Software & development tools
Radar Toolbox for Edge AI
Learn more about how TI’s 60GHz and 77GHz industrial mmWave sensors can measure distance and relative velocities of people or objects.
Industrial automation | Detection
Accurately determine different human poses with our integrated radar edge AI optimized devices.