Keeping Station Curbs Moving
Brightline used Safari AI to count, classify and time vehicles at the pickup and drop-off zones around its train stations.
Measured from existing curbside cameras
Curb space at busy stations was managed by eye.
Pickup and drop-off zones served rideshare, taxis, shuttles and private cars at once. Without data, staff could not tell which vehicles overstayed, which used the wrong zone, or when the curb was about to back up, until it already had.
- There was no count of how many vehicles used each zone, or for how long
- Unauthorized stops and wrong-zone unloading went unrecorded
- Manual curb surveys were slow and only covered a few hours
Every vehicle at the curb, counted and timed.
Connected to curbside cameras via an on-premise server
Existing curbside and station-approach cameras fed a lightweight on-premise server Safari AI deployed, so video was processed on site.
Classified vehicles and timed every stop
Computer vision counted and classified each vehicle, read plates where authorized, and timed how long it stayed in each zone.
Flagged violations and bottlenecks
Dashboards showed dwell time, zone use and wrong-zone stops by hour, setting baselines for curb policy and enforcement.
Note: Illustrative data
Faster turnover at the curb, fewer blocked lanes.
Every pickup and drop-off was counted and timed as it happened, so manual curb surveys are no longer needed.
Rideshare, taxis, shuttles and private cars were told apart, so each zone is checked against the vehicles it is meant for.
Dwell time was measured by zone and hour, showing where the curb backs up and setting a baseline for every policy change.
Action Center: From Insight to Action.
Measurements like these feed Safari AI's Action Center, which flags an overstaying vehicle or a backed-up zone while there is still time to clear it.
- 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 at your own stations.
Brightline measured curbside activity around its stations from existing cameras. We'll walk through which zones and approaches are the best fit for a pilot on your cameras.
