AI at a New Frontier : Rapid Temperature and Mask Detection

Home>Solution>Computing

As the COVID-19 virus’s worldwide impact continues, the search for improved ways to mitigate the impacts of such epidemics has become increasingly important. The epidemic has affected almost every aspect of people's lives; their travel, work, shopping, medical treatment etc.. However, traditional epidemic prevention methods have proven to no longer meet the needs of large-scale epidemic prevention work. Recently, the development and application of AI-based epidemic prevention technologies and products has shown great promise. Artificial or Assisted Intelligence (AI) based tools for epidemic symptom detection can be applied to many scenarios, within densely populated places such as airports, stations, shopping malls, office buildings, campuses, communities, etc., where there is a large flow of people. These techniques can be utilized to easily realize large-scale and rapid body temperature detection, personnel identification, mask on/off detection and other illness detection & prevention work.

The EDOM AI epidemic prevention solutions are based on the NVIDIA Jetson Xavier NX module, Cyberlink FaceMe, highly accurate AI engine, and the Melexis thermal IR array, Framos depth camera and Innolux 11.6" TFT LCD Display NB modules. This solution will help EDOM’s customers develop high-precision body temperature detection, intelligent identification terminal products, and achieve rapid market adoption.

-EDOM Is Your Best Solutions Partner-

Dec Block Diagram

NVIDIA Jetson Xavier NX

NVIDIA Jetson Xavier NX delivers up to 21 TOPS for running modern AI workloads, consumes as little as 10 watts of power, and has a compact form factor smaller than a credit card. It can run modern neural networks in parallel and process data from multiple high-resolution sensors, opening the door for embedded and edge computing devices that demand increased performance but are constrained by size, weight, and power budgets.
Cyberlink FaceMe

Cyberlink FaceMe® is uniquely positioned to integrate edge-based AI facial recognition into a wide range of IoT and AIoT solutions. FaceMe® is optimized to run on most hardware configurations, from high-end workstations to low-power chipsets typically used in IoT devices. It supports more than 10 operating systems, including Windows, Android, iOS, and various Linux distributions. FaceMe® can run on low-power CPUs to enable facial recognition on cost-effective IoT/AIoT devices, as well as be integrated with high-end servers, workstations and personal computers equipped with GPU to provide highly efficient performance.
Melexis MLX90640 32x24 IR array

Melexis MLX90640 32x24 IR array is a fully calibrated 32x24 pixels thermal IR array in an industry standard 4-lead TO39 package with digital interface. The MLX90640 contains 768 FIR pixels. An ambient sensor is integrated to measure the ambient temperature of the chip and supply sensor to measure the VDD. The outputs of all sensors IR, Ta and VDD are stored in internal RAM and are accessible through I2C.
FRAMOS Industrial Depth Camera

The FRAMOS Industrial Depth Camera D435e is built with Intel® RealSense™ technology. The depth camera has industrial M12 ethernet and M8 power connectors and features a wide field of view for depth and RGB sensors. Its water- and dust resistant housing is optimized for industrial environments. The FRAMOS Industrial Depth Camera D435e is ideal for OEMs and integrators who need 3D as well as 2D vision in their products and applications. The FRAMOS Industrial Depth Camera D435e is compatible with the Cross-platform SDK for Intel® RealSense™ devices, enabling multiple programming languages, wrappers, sample code and tools.
INNOLUX N116BCA-EA1

INNOLUX N116BCA-EA1 is a 11.6” (11.6” diagonal) TFT Liquid Crystal Display NB module with LED Backlight unit and 30 pins eDP interface. This module supports 1366 x 768 HD mode and can display 262,144 colors.