A Mask Detection Smart Camera Using the Nvidia Jetson Nano: System Architecture and Developer Experience


Date:  Tuesday, May 25

Start Time: 1:00 pm

End Time: 1:30 pm

MaskCam is a prototype reference design for a smart camera that counts the number of people wearing masks in its field of view and reports statistics to the cloud. Based on the Nvidia Jetson Nano, all AI processing is handled on the device. In this presentation, BDTI and Tryolabs share their story of developing MaskCam, and how we went from concept to working prototype with a small team in just a few months. We explain the hardware and software design of the camera and present our experiences working with Jetson Nano (both the Dev Kit and the system-on-module), NVIDIA’s DeepStream framework and containerization via balenaOS/balenaCloud. Our solution features a custom tracking component, static video file serving, video streaming over RTSP, and MQTT communication to report statistics and receive commands using a web interface. Working with Jabil Optics, we present estimated manufacturing costs for volume production.

Track

Session Speakers

  • Braulio Ríos is a Machine Learning Engineer with over ten years of experience in the software and electronics industries. After finishing his degree in electrical engineering, he started his career in embedded system development for the automotive and healthcare industries. He then shifted to signal processing and machine learning development as he joined Tryolabs in 2016. At Tryolabs, he previously worked on projects for a diverse set of industries requiring a wide variety of skills, especially embedded machine learning, computer vision, demand forecasting and price optimization. He also has practical experience with full-stack and cloud development. Most recently, he joined the Tryolabs R&D team to develop video analytics solutions that run on low computing power devices.

  • Evan is a computer vision engineer at BDTI. He worked as a hardware engineer for eight years, designing circuitry for mission-critical industrial applications as well as advanced consumer electronics. His YouTube channel, Edje Electronics, focuses on democratizing access to computer vision technology by providing easy-to-follow projects and tutorials on using TensorFlow, OpenCV, and more. He received a B.S. in Electrical Engineering from Montana Tech, and an M.S. in Electrical Engineer with a focus on ASIC design from Washington State University.


Share

A Mask Detection Smart Camera Using the Nvidia Jetson Nano: System Architecture and Developer Experience