News
iCatch’s SoCs are powering a diversity of camera applications in
multiple markets.
AI ePTZ Webcam by V37M
Introduction
Take the following demo video for example:
As the meeting attendees enter the room one by one, human tracking will detect the number of attendees and their locations respectively. Then the location information is passed to the ISP to best-fit all attendees into the frame. his features makes the webcam more efficient and usable by only showing the region of interest. The presenter tracking feature utilizes the information from both human tracking and audio beamforming computed by external Audio CODEC. Audio beamforming provides the approximate location of the presenter and human tracking can determine the exact location of the presenter based on the previous information provided by audio beamforming.
Take the following demo video for example:
With audio beamforming and human tracking, V37M can provide a PIP overlaid window with a zoomed-in view on the current presenter. This feature can help the meeting attendees to know and focus on
the current presenter.
Live Demo
We have implemented deep-learning based human tracking feature in the V37M SBC. As you can see, as I move across the camera FoV, the NPU inside V37M keep tracks of my position which is highlighted by the green bonding box. This function is the fundamental technology that enables the autoframing feature. That concludes today’s introduction of V37M applied to ePTZ webcam application.
For more information about iCatch’s products, please visit: www.icatchtek.com
For sales contact, please leave your message at: https://www.icatchtek.com/Requests