How Staqu’s ‘Jarvis’ is securing RCB’s home ground for crowd control

The Indian Premier League (IPL) is known for packed stadiums and electric crowds. But last year’s stampede outside M Chinnaswamy Stadium showed how quickly excitement can turn into tragedy - and why crowd safety is becoming a major concern ahead of IPL 2026.

While the fans of Royal Challengers Bengaluru (RCB) celebrated the long-awaited victory, the overcrowding during celebrations left 11 dead and dozens injured. To ensure such a disaster never repeats, RCB and the Karnataka State Cricket Association (KSCA) have undergone a major security overhaul. 

To this end, the cricket team has partnered with AI startup Staqu Technologies, which offers AI-powered video analytics and management solutions, to upgrade the stadium’s 500+ existing CCTV cameras with its “JARVIS” system. The technology will intelligently monitor crowd movement, detect unusual patterns, and enable real-time alerts to help prevent overcrowding.

Atul Rai, Founder and Chief Executive Officer of Staqu Technologies, in an interaction with Business Today, explained how JARVIS will function at the M Chinnaswamy Stadium throughout the IPL 2026, and how authorities can take prompt action before crowd situations escalate into potential incidents.

How Jarvis will operate in RCB’s home ground

Rai elaborated on how the AI system “Jarvis” will work as a smart AI layer, monitoring the crowd as soon as they enter the stadium gates. He highlighted the system monitors around 30,000 people inside the stadium while keeping an eye on crowd movement, queues, and restricted areas.

“The system continuously tracks crowd build-up and triggers alerts before critical thresholds are breached," Rai stated. 

"Specific risk signals it monitors for include sudden crowd surges, restricted area intrusions, and violent behaviour patterns, shifting crowd management fundamentally from reactive to predictive," he added.

The real-time insights provided by the system help the on-ground team to redistribute crowd flows across gates. It monitors specific risk signals to take timely preventive action.

Differentiating celebration from a stampede

Are AI systems smart enough to distinguish between a high-energy "last-over win" celebration and an actual panic situation at a stadium? Rai explains that Jarvis combines the power of density estimation with activity recognition.

The system has been trained to recognise specific anomalies of a crowd, such as how many people are in a zone, along with their behaviour, identifying whether they are running, stationary, fighting, or have fallen.

Rai explained, “The power of this approach lies in its precision. A marathon can visually resemble a stampede, but the density and formation context tell a completely different story.”

“It is only when an unexpected spike in density coincides with running activity in a given zone that the system flags a potential emergency, making it far more accurate than any single-model assessment,” he added.

From recognition to protection

Atul Rai revealed that AI deployment remains the core pillar for Staqu, hence the Jarvis system is integrated with visual recognition, including OCR for number plates and facial recognition for flagged individuals into a unified system, “making it easier for authorities to monitor multiple threat vectors from one place”.

In a stadium setup, this technology helps spot “unauthorised access” and also carefully monitors who’s entering and leaving, so security can take action if something goes wrong.

Beyond the stadium, Staqu’s facial recognition and smart surveillance systems are already being used by various state police departments to track crowds, monitor vehicles, and detect suspicious objects for investigations. 

The company claims to provide a 99% detection accuracy in similar high-stakes environments like the G20 Summit and the Ayodhya Ram Mandir inauguration

Jarvis capabilities beyond stadiums

Rai further highlighted that its AI-powered system helps in law enforcement to automate the "passive" task of watching screens, and redirects police manpower towards active, on-ground tasks. 

Here’s how Jarvis helps police to take timely action:

- Faster Investigations: Jarvis replaces the manual review of the CCTV footage, as AI can now scan from criminal databases in minutes and match faces with the flagged person or criminal.

-Smart Prison Surveillance: Jarvis also helps keep track of fights, overcrowding, restricted access, and contraband detection with correctional facilities.

“This significantly reduces dependency on constant human vigilance, allowing prison staff to focus on control, response, and inmate management rather than screen monitoring,” Rai said.

- Vehicle Intelligence: Rai further revealed that JARVIS is also being deployed by Gurgaon Police to automatically detect vehicles with fake or suspicious number plates using technology dubbed Automatic Number Plate Recognition (ANPR). Looking ahead, Staqu is making surveillance data even more accessible via Jarvis GPT, which debuted in February 2025. This allows security operators to extract data using natural language. This showcased how an AI-powered surveillance system can shift crowd management from reactive to predictive, and can potentially be lifesaving.