Calgary Flames / Scotiabank Saddledome
Shorter Concession Lines and Faster Entry on Game Night
The Calgary Flames used Safari AI at the Scotiabank Saddledome to measure entry throughput, concession lines, and concourse traffic in real time, using the venue's existing cameras.
Measured from the Saddledome's existing cameras, game night by game night
Most game-night sales happened in two short intermissions, with no live view of the lines.
Staffing for gates and stands was set before doors opened and adjusted by radio once lines were already long. When a fan left a line to make puck drop, the sale was gone, and no report recorded it.
- Concession wait times were not measured, so walk-aways were invisible
- Ticket scans showed who got in, not how long fans waited outside
- Crowded concourse areas only surfaced when staff radioed them in
Gates, stands, and concourse in one live view.
Connected arena cameras via an on-premise server
Existing gate, concourse, and concession cameras fed a lightweight on-premise server Safari AI deployed in the building, so video was processed on site.
Measured entry, lines, and foot traffic
Computer vision counted fans through each entry lane, measured line length and wait time at every stand, and mapped foot traffic across the concourse.
Built live dashboards by gate, stand, and period
Operations and F&B teams saw waits, entry throughput, and crowd heatmaps by stand and game period, against each target.
Note: Illustrative data
Shorter lines, faster gates, more sales before puck drop.
Wait time and line length were measured at every stand through every intermission, so staff reach the busiest stands before fans give up and head back to their seats.
Fans were counted through each entry lane in the pre-game rush, so gate staffing follows the line outside rather than last week's scan totals.
Foot traffic was mapped by stand and game period, showing where intermission demand lands and which registers to open next.
Action Center: From Insight to Action.
Measurements like these feed Safari AI's Action Center, which sends staff to the stand or gate that needs them before the line costs a sale.
- Real-time recommendations to improve KPIs via email, SMS, robocall, mobile app, Power BI, or API.
- Recommendations grounded in your own written SOPs, not generic best practices.
See this in your own building.
The Flames measured entry, concession lines, and concourse traffic from cameras already in the Saddledome. We'll walk through which gates and stands are the best fit for a pilot on your cameras.
