Why Seervision?
Automatic triggers based on scene understanding
The Seervision Suite’s computer vision-based scene understanding gives PTZ cameras and any device in an AV installation the ability to see and react live to what is happening in the room.
Through visual and audio triggers, Seervision can autonomously trigger specific actions depending on the area of the room that a person is detected, to offer a hands-free and dynamic live video production.


Smart, adaptive and robust full-body tracking
Our award winning auto-tracking software enables PTZ cameras to automatically recognize and keep track of your subject. Based on full-body identification, the system creates unique IDs from multiple reference points over the body, making it much more reliable than face-based or motion tracking solutions.
This means enhanced performance when people are crossing or when your subject’s face isn’t visible, and it also gives you greater control over the tracking smoothness and reactiveness.
Preset-less automation for flexible spaces
Enhance the hybrid meeting experience with audio-based camera automation that truly immerses remote participants. Gone are the days of retrofitting conference room solutions to large spaces, instead, choose your preferred cameras and automatically point them at active talkers via Seervision’s preset-less beamforming microphone integrations that adapt to the use-case, room layout, and seating configuration.
Because we are hardware agnostic, even if your equipment changes overtime, our software infrastructure will allow you to keep us at the core and maintain your existing automations up-to-date.


Limitless API
Leverage our API to trigger actions through third-party devices by using Seervision as your ‘visual sensor’.
Likewise, use inputs from third-party tools to trigger actions within the Seervision Suite. Together with our Bitfocus Companion module and built-in NodeRED platform, create straightfoward 'if this, then that' flow diagrams that activate presentation switchers, video playback software, or other ProAV equipment.
Powerful features for intuitive automation
Full-Body Auto-Tracking
With our full-body autonomous camera tracking, ensure your subject is always kept in frame with smooth broadcast-quality pan and tilt movements.
Our proprietary algorithm creates unique IDs for every person on-stage and predicts a your subject’s movements to ensure optimal framing at all times.
You can also leverage our deadband, tracking smoothness, and tracking reactiveness settings to tune the tracking to your liking according to your subject’s movements.
Trigger Zones
Trigger Zones allow you to drag and drop different areas on stage to automatically activate specific actions when your subject steps-in.
For each zone, create custom actions to be triggered depending on if the subject enters, stays, or leaves a specific zone.
These ‘events’ can also be sent to other connected devices via our API, so that you can create autonomous multi-camera workflows or activate a different layout in your vision mixer if the subject stands in a specific zone.
Person Specific Automation
With Person Specific Automation, you can choose to store an image of a talent, associate a name with it, and make trigger zones react only to the specific talent.
This means you can create different tracking behaviors for distinct presenters, or even send these ‘events’ externally to your video mixer to trigger person-specific lower thirds.
With Person Specific Automation, the autonomous workflow can adapt to the person on stage so that no manual intervention is necessary – the possibilities are truly endless!
Active Speaker Tracking
Leverage our integration with certain beam-forming ceiling array microphones to adaptively point the camera at the active speaker – without relying on camera presets.
Perfect for high-impact spaces, boardrooms, training rooms, or all-hands venues, capture your audience members automatically, bringing them closer to your hybrid audience.
Use single person or group framing to adapt the solution to your meeting preferences, and create custom logic that adapts to the room layout.
API
Make use of our powerful API to use the Seervision Suite as the ‘brain’ of other connected systems.
From simple remote control presenter handovers, to Trigger Zone-based vMix switching, or even Siri-enabled commands, make your devices work together to automate your productions to a new height!
Visit our API documentation to learn more, and explore the messages that Seervision can send and receive to create automation workflows with other API-capable devices.

System Overview
Seervision is an IP-based system that requires the camera, server, and interface to be on the same network. Our software analyzes people in the scene and sends multiple commands per second for camera and lens trajectories. As we only control the camera’s movement, your image quality and output feed delay won’t be affected.
Education
Explore our typical setups in higher education to enhance lecture capturing through automation
Corporate
Dive into our common meeting room setups with ceiling microphones that enable preset-less speaker tracking
Specifications
Our 2U hardware systems are a versatile choice for a variety of applications, supporting both single-camera and multi-camera setups. With their robust feature set, they provide a reliable, secure, and easy-to-use solution for anyone in need of such a system.
- Secure on-premise Linux-based 2U servers
- Support for SDI, NDI and NDI|Hx
- Fully IP-based, allowing for remote control
- Web-based user interface via Google Chrome
- Mouse, Keyboard, Joystick, or API control
- Native integration with 3rd party PTZs
- Plug-and-play solution via VISCA over IP
- Works for single camera or multi-camera setups
PTZ Integrations
The Seervision Suite is compatible with a wide range of third-party PTZ cameras and robotic camera heads