- Applications
- Products
- Acquisition & Production
- Infrastructure
- Management & Systems
- Cloud Solutions
- OEM Developer Solutions
- Services
- Company
- Support
- Knowledge Center
- Contact
- Select Language
Vision[Ai]ry Facial Tracking (Ft) is the first in a suite of products that use video analytics to automate the functions of a camera operator. Vision[Ai]ry FT uses AI-based facial recognition to detect, locate and track the position of faces within the video stream directly from the camera.
It then uses these facial positions to drive the pan, tilt and zoom axes of the robotic camera system to maintain the desired framing of the face or faces in the image. This eliminates the need for a camera operator to manually adjust for the position of the subject in the image.
Vision[Ai]ry Ft v1.2 is the latest update to our facial tracking system. This version adds links between robotic presets and framing templates, a new template preview feature, display enhancements, and more.
Vision[Ai]ry Ft’s algorithm ensures that faces will be accurately identified and located as long as at least 50% of the face is visible in the image. The algorithm is trained against a diverse set of race, gender and age data that includes a wide variety of poses, head coverings and accessories.
The clean, simple UI provides a live display of the video from the camera with detected faces and framing target clearly indicated, all surrounded by easy-to-understand status info, tracking controls and framing template library.
The adjustable damping and deadband settings allow the user to tailor the behaviour and performance of the system to suit the movements of the talent. This ensures that the system maintains optimal framing and tracking, eliminating undesirable movement and overshoot.
Vision[Ai]ry Ft automatically calibrates the camera lens and adjusts tracking gain to avoid over-reacting at higher zooms, where small pan or tilt changes result in much larger changes in framing.
Framing templates allow all framing parameters, including the framing target location and size, deadband and damping, to be stored and recalled. This enables the operator to create an unlimited number of shot compositions that can be instantly applied to any camera.
By linking a framing template to a robotic preset, the desired framing parameters are automatically recalled and applied to the camera. This is particularly useful in automation workflows where it eliminates the need for the automation operator to touch up shots before taking them to air, allowing them to focus on other aspects of the production.
| Specifications | Vision[Ai]ry Ft |
|---|---|
| Number of robots controlled | No fixed limit |
| Minimum PC requirements | i7-2.9 GHz, 8 cores, 8 GB RAM, Intel integrated graphics, Solid State drive |
| Video sources | Local, eg: SDI capture card NDI |
| Number of faces that can be tracked simultaneously | Up to 30 |
Complete overview of Vision[Ai]ry Ft
How Can Facial Recognition and Tracking Assist Camera Operators?
Watch our walkthrough video of Vision[Ai]ry Ft version 1.1.
The first step is a consultation with a member of our sales team or one of our certified Ross resellers to discuss the specific needs of your organization. Next, we will look for a mutually convenient opportunity to coordinate a demo.
613-652-4886
