EVS Overcam automates key camera positions for autonomous control

The new AI-based solution that EVS will demonstrate at this IBC mimics traditional camera framing to enhance storytelling for productions of any budget.

In IBC 2019 (stand 8.B90), EVS will present Overcam, a machine learning-powered software solution that enables autonomous control of robotic cameras in live sports environments. With Overcam, owners and rights holders will be able to create more affordable and immersive productions capturing the action from more camera angles much more economically.

Overcam controls multiple robotic cameras deployed around a field and then uses “intelligent tracking” to analyze key game parameters, such as players and ball positions, directing the cameras to frame the scene. Its real-time processing means it integrates with existing multi-camera live production workflows, where robotic cameras can be mixed with manual cameras. This solves the persistent challenge of camera positions versus budget and optimizes conventional productions.

The system is based on neural networks and computer vision that automate key camera positions. This is driven by VIA Mind, the EVS AI engine that integrates machine learning methods to power a growing number of EVS solutions.

While the first iteration of the solution is aimed at live football, especially smaller leagues with tighter production budgets, the system can ultimately be used for other sports such as basketball and hockey.

And Typical Overcam deployment in football would see The system simultaneously drives the main central camera along with two offside cameras and a tactical camera. It can also provide an affordable way to capture additional camera angles for large sporting event productions.

Overcam has been created to help businesses and sports clubs save money, expand camera coverage, standardize hard-to-access viewing angles, and place cameras in expensive or restricted areas that avoid blocking seat sales.

Christophe Messa, product director at EVS, assures that "some of the camera positions, such as offside positions in football, play an important role in overall coverage, especially in replays. At the same time, budget constraints require a trade-off in terms of the way resources are deployed. Overcam covers these important positions, improving the final output."

Overcam's AI-based approach goes beyond automation and simple tracking to accurately mimic the movements of human camera operators, creating smooth, natural-looking framing of the action with optimal optical visual results, including true zoom and depth of field. The system runs on a compact 2 rack unit server, which may be located at headquarters or in a remote operations center. On game day, there is no long preparation time required. It is easy to implement and the cameras calibrate automatically.