Ross Video is launching a new camera motion system that uses artificial intelligence to detect, locate and track the position of faces within a video stream directly from the camera.
Vision[Ai]ry Ft uses facial positions to drive the pan, tilt and zoom axes of the robotic camera system in order to maintain the desired framing of the face or faces in the image.
According to Ross, the new system reduces the burden on camera operators by removing the need for manual correction of camera positions to deal with variations in talent seating position, posture and height.
The system’s framing settings can be saved to templates that can be automatically recalled with robotic presets to provide a hands-free camera workflow when combined with production automation solutions such as Ross’s OverDrive.
The company says its AI algorithm can recognise a diverse set of race, gender and age data, and can accurately identify and locate faces as long as at least 50 per cent is visible in the image. The solution’s user interface provides a live display of the video feed with detected faces and framing target clearly indicated, along with status info, tracking controls and framing template library. In addition, damping and deadband settings enable the user to tailor the system to the talent in order to maintain optimal framing and tracking while eliminating undesirable movement and overshoot, said Ross.