BDTI and its partners, Tryolabs S.A. and Jabil Optics, are delighted to announce MaskCam: an open-source smart camera prototype reference design based on the NVIDIA Jetson Nano capable of estimating the number and percentage of people wearing face masks in its field of view.
MaskCam was developed as part of an independent, hands-on evaluation of the Jetson Nano for building real-world edge AI/vision applications. Our evaluation sought to answer questions such as: How difficult is it to create an application using the Jetson Nano and NVIDIA’s tools and SDKs? How complete is NVIDIA’s support ecosystem, including hardware, software, documentation and community presence? Where did things work well, and where did we encounter snags or sharp edges? You can read our detailed report at https://bdti.com/maskcam.
Overall, our team was impressed with the Jetson Nano and its ecosystem. The quality documentation and examples for the NVIDIA SDKs, the breadth of the hardware partners and modules available to be used with the Jetson Nano, and containerization tools from balena all facilitated rapid development of our smart mask detection camera. The fact that we were able to conceptualize, design, and create a production-ready prototype of MaskCam in a short time with a small team speaks to this. While there were certainly challenges, we were able to overcome all of them.
MaskCam’s source code is available under the MIT License at https://github.com/bdtinc/maskcam and we encourage you to try it out — if you have a Jetson Nano Developer Kit and a USB web camera, you can get the MaskCam software running on your system with two simple commands described in the README. Questions? Please email [email protected].