Huddly cameras are software-defined and designed to evolve. Built from the ground up, Huddly’s unique combination of beautifully designed hardware, upgradable software platform and Huddly desktop app deliver a video collaboration experience like no other - the Huddly camera will get better and smarter throughout its lifetime with cutting-edge new features. The Huddly camera features a convolutional neural network that uses visual data to evolve and get smarter in a way that is similar to the human brain.

In machine learning, a convolutional neural network (CNN) is a class of deep, feed-forward artificial neural networks, most commonly applied to analyzing visual imagery.Inspired by biological processes, the Huddly camera features a multi-layered CNN design with the connectivity pattern between neurons resembling the organization of the animal visual cortex. Using its CNN, the Huddly camera can instantly identify visual patterns, allowing it to recognize people and objects. Examples: People counting, meeting room availability, content capturing, action recognition (like voting, whiteboarding, standing up, walking around, falling down.

All data processing happens in the camera without the need to be sent to a computer or the cloud for processing, meaning the Huddly camera allows for a superior level of privacy and security. This also moves compute-intensive operations to the edge, minimising the need for bandwidth and allowing for immediate response.

Complying to USB, video and audio standards, the Huddly camera will support most platforms and collaboration platforms. Combined with its portable form factor and multiple mounting options, the Huddly camera is the world’s most versatile conferencing camera.