For several years now, the enforcement of track limits has been among the most persistently controversial matters arising in Formula 1 grands prix.
Drivers naturally push to the limits of what’s permissible to find lap time; they also have a penchant for reporting rivals who they believe have crossed the proverbial lines. And, of course, for vociferously denying when they have done so.
Teams inevitably stand by their man and the resulting debates can occupy a great deal of bandwidth, often delaying race outcomes. In the 2023 Austrian Grand Prix alone, the FIA had to review more than 1,000 suspected track-limit violations, a figure that clearly illustrates how essential more advanced tools had become to speed up the process.
Behind the scenes, this is why the FIA and Catapult created an automated tool to detect when cars cross the white lines and integrate it into RaceWatch, the system used by race control and the remote operations centre to monitor everything happening on track.
When a single race can generate hundreds of potential incidents to review, it’s easy to understand why a system capable of assisting the stewards was needed, accelerating the review process and allowing teams to be notified of a possible infringement within seconds. According to the FIA, this computer‑vision‑based tool has cut by 95% the number of cases that require human involvement to reach a decision.
RaceWatch, the race management software developed by the FIA and Catapult
Photo by: FIA
The FIA will be able to send the footage directly to the teams
The computer‑vision system integrated into RaceWatch can recognize a car’s silhouette and analyse its behaviour against predefined reference points captured by a camera. This allows it to determine whether a car has crossed the reference line.
Looking ahead to 2026, several practical and functional updates are planned. The first is that the FIA will be able to send teams the footage of any track‑limit infringements committed by their drivers, making the process even more transparent and reducing the potential time lost to quibbling. This also helps streamline and speed up the workflow, giving teams faster feedback.
The other update, arguably the most significant and intriguing, concerns how track limits will be detected, thanks to a more advanced system that also rethinks the entire data‑analysis workflow. The AI‑based recognition now relies on high‑performance GPUs to process in real time all the information needed to verify every single lap, increasing both the accuracy and the speed of the checks.
RaceWatch, the race management software developed by the FIA and Catapult
Photo by: FIA
Distributed process to crunch more data
“The new system will be based on a centralised camera controller, which will not only allow us to set all the distances from a single point, but also to distribute the required processing,” explains Chris Bentley, the FIA’s Single Seater Head of Information Systems Strategy, in an exclusive interview with Motorsport.com.
“We’ll be able to run the computer‑vision software on any machine in the network, send it the portion of video to process, and receive the result, enabling us to handle more and more data.”
Increasing the data-processing capability ties in with another tool developed by the governing body together with Catapult: a highly advanced positioning system.
The system tested at the end of 2024
Photo by: FIA
Thanks to the innovations introduced in recent years, the FIA is now able to track a car’s position with increasingly high precision, combining multiple data sources. It’s not just about absolute coordinates: the system cross‑references positioning data, sector‑time information and ideal racing lines, effectively creating a real‑time “digital twin” of what is happening on track.
“This allows us to use all the data that we’ve got to start looking at the white line around the track,” says Bentley, “even though they’re maybe not covered by any particular camera.
“The camera becomes slightly secondary in these cases because we’re going to use geofencing on the positioning data. We’re going to use delays in when cars get to certain positions to work out where it went off, and the changes in the line that the car follows, because obviously there’s an optimal line that all the cars follow. It’s very rare for them to stray away from the racing line.”
How the new ECAT system will work
The core concept is named “Every Car All Turns (ECAT)”, the idea being that the system interprets a car’s behaviour by measuring it against a reference model. By cross‑referencing this information with the micro‑sector timing data, RaceWatch can understand what happened at that specific point on the track and flag the episode for a possible review.
The system is able to track multiple cars simultaneously
Photo by: FIA
“If a car deviates from the ideal line, it will potentially cover more distance,” says Bentley.
“That allows us to see a difference in the sector time and go back to understand where it went off track or what happened. The idea is to use all the data, enrich it with the available video and trace these elements, so that the system tells us what is happening instead of having to look for it manually.”
“The goal is to take the system to the next level. It works across the entire track, all the time, so it can automatically understand what’s going on. This is the evolution of what we’re trying to do go from a manual process to semi-automatic process, with still a manual element to it because you have to evaluate strikes and black-and-white flags”.
The FIA actively works with circuits to improve coverage and to identify the best camera placement, but this isn’t always possible and varies from track to track. However, with this new system, cameras, while still important, are no longer the only foundation of the analysis.
RaceWatch, the Race Management Software developed by the FIA and Catapult
Foto di: FIA
The system can now detect a potential track‑limit infringement purely from positioning data: if it shows an abnormal deviation, if the car enters a virtual zone drawn on the track, or if its trajectory strays too far from the ideal racing line, RaceWatch can generate an alert.
“It’s allowed us to move up a level, manage all the cameras in one place, distribute the process in the computer vision and process other elements that we’ve had available in one place,” says Bentley.
“So basically, we can automatically flag when a car goes off track because the positioning data changes, or use geofencing: we can draw chicanes and virtual zones on the track that trigger an alert if a car enters them. All of this will already be operational this year, we’ve been working on it throughout 2025.”
The topic of track limits has long had an element of subjectivity. Making the process even more data-driven adds to the fidelity of decision-making.
Will it also significantly reduce the debate over track limits? Most fans will dearly hope so.
We want your opinion!
What would you like to see on Motorsport.com?
– The Motorsport.com Team
Disclaimer : This story is auto aggregated by a computer programme and has not been created or edited by DOWNTHENEWS. Publisher: motorsport.com
