XMOS announced its reference solution for Automatic License Plate Recognition (ALPR), designed to move ALPR in parking garages away from complex, resource-intensive hardware and towards simple on-device AI.

 

Developed in partnership with computing specialist Cloudtop, the reference design can read slow-moving license plates at a distance of 3-5 meters with high accuracy. Thanks to the capabilities of XMOS’ xcore.ai silicon, Cloudtop’s machine learning model – originally designed to work with high-resolution video frames – has been seamlessly adapted to work in low power, low-cost scenarios without sacrificing accuracy.

 

Parking garages that utilize ALPR have traditionally integrated hardware that is far beyond the spec required for slow-moving, close-range plate recognition. High-resolution cameras, operating on complex machine learning models that depend on cloud connectivity for image processing, have made the implementation of ALPR prohibitively expensive in many cases.

 

XMOS’ reference design instead provides the required power and intelligence on-device, dramatically lowering both power consumption and the Bill of Materials (BOM) in comparison to standard ALPR solutions. In removing the need for high-cost hardware and virtually eliminating the need for cloud connectivity, such a device becomes a realistic component of the ALPR infrastructure across the smart city.

 

XMOS and Cloudtop will showcase the solution at the tinyML Summit in San Francisco, between 28-30th March, and invite all attendees to visit their exhibition stand and poster presentation.