Transit Entrances
Place the prompt on approaches where curb geometry makes the pedestrian route clear.
Motorcycle on Sidewalk Detection for Pedestrian Zones
A motorbike on a sidewalk can disrupt a pedestrian route. StreamVLM™ lets an operator describe that visible condition and review the matching frame.
The Visible Condition
Give the Operator a Frame to Review
The condition in scope is a motorbike or scooter moving or standing on a sidewalk, plaza, or other pedestrian-only route. It is a visible scene detail, not a diagnosis, a conclusion about intent, or an automatic decision.
In StreamVLM™, an authorized operator writes a prompt such as “Alert on a motorcycle riding on the sidewalk.” The model evaluates selected live frames against that prompt and sends a match, camera, location, and time into the IREX event workflow for human review.
StreamVLM™ runs on a GPU node in the customer instance. Each prompt has its own confidence threshold, alert cooldown, event type, and camera selection.
This prompt-defined detector can be evaluated alongside the Two-Wheeler Detection trained-module workflow. The two approaches have different frame-rate and operational-fit considerations, so a pilot should establish which is appropriate for the site.
Explore StreamVLM Prompt DetectorsWhere It Helps
Set the Prompt Where the Condition Matters
Pedestrian Plazas
Let traffic staff open the live view before treating the route as obstructed.
Downtown Sidewalks
Record recurring locations so the city can review signs, barriers, or delivery access.
Illustrative Camera Frames
What the Operator Reviews
These illustrative frames show the kind of visible condition a prompt can surface. They are not real incidents, deployments, or proof of detection accuracy.
Motorbike on sidewalk
Along a Storefront
The operator checks whether the route is pedestrian-only and whether the vehicle is moving through it.
Motorbike on sidewalk
At a Pedestrian Crossing
A curb and crossing geometry help a reviewer distinguish the sidewalk from the road.
Motorbike on sidewalk
Near Foot Traffic
The prompt brings the visible condition to the screen; the operator decides what response is appropriate.
From Prompt to Action
A Review Workflow for This Condition
- 01
Mark Pedestrian-Only Views
Write a concise prompt for a motorbike or scooter moving or standing on a sidewalk, plaza, or other pedestrian-only route, then select the cameras and times where the condition warrants attention.
- 02
Review the Vehicle Path against the Curb and Local Access Rules
Open the event with its camera, location, time, and available video context. Confirm what is visible before treating the match as actionable.
- 03
Route Repeated Locations to the Street-Operations Team
The authorized team applies the local procedure. StreamVLM supplies a review cue; it does not decide the response.
Limits to Test
Validate It on the Actual Cameras
- Scene Context
- A bicycle, mobility scooter, or permitted service vehicle can look similar at distance.
- Camera Fit
- The camera needs a clear view of the curb, sidewalk, and vehicle path.
- Human Decision
- A match does not establish a traffic offense or identify the rider.
- Timing
- StreamVLM evaluates sampled frames. A fast-moving motorbike can cross a short sidewalk segment between samples, so validate the view and response expectation during the pilot.
FAQ
Can this distinguish motorcycles from bicycles?
The prompt can be written for a motorcycle or scooter, but the operator should confirm the vehicle type in the frame. Distance, angle, and an obscured vehicle can make that distinction unreliable.
Can StreamVLM confirm motorbike on sidewalk?
No. It reports a match to the visible condition in the prompt. An operator reviews the frame and local context before deciding what it means.
How should a team tune the prompt?
Start with representative cameras, define what makes a useful alert, then adjust the camera selection, confidence threshold, and alert cooldown during a camera-specific pilot.
Is there a published accuracy figure for this use case?
IREX does not publish a universal accuracy figure for this prompt. Image quality, camera angle, lighting, occlusion, and the local definition of a useful alert all affect results.
Review Pedestrian Routes on Camera
Start with the sidewalks where motor traffic creates the greatest operational concern, then tune the prompt around the actual curb and access layout.