People flow
Detect people in a camera view, track movement, and measure activity in a defined queue region. Build the metric around the layout and the decision the operator needs to make.
Choose the measurement
Track people and count crossings at a defined line or queue boundary.
Explore the workflow →Measure occupancy or tracked time inside a region, then compare with observations at the site.
Explore measurement →Run the video workflow locally and tune it for the camera view and target hardware.
Explore deployment →01 · Tracking and measurement
A typical pipeline reads a video or camera stream, detects people, associates detections across frames, and checks which tracks enter a defined region. A line counter measures crossings; a region timer measures how long tracked objects remain inside a polygon. Vision Studio can configure and preview these stages, and the Python integration supports custom applications.
Region dwell time is not automatically the same as actual wait time. The metric depends on camera geometry, track continuity, the queue boundary, and how passers-by are excluded. Validate counts and timing against observations at the site before using them for staffing or alerts.
02 · Local deployment
A local deployment can keep the processing pipeline close to the camera. Model choice, resolution, frame rate, hardware, and privacy requirements are selected for each installation.
See embedded vision solutions for the broader deployment approach.
03 · Project evaluation
Prepare representative footage, camera placement details, queue boundaries, and observations to compare against. Check track continuity, false counts, and timing behavior before using the result for staffing or alerts.
Tell us about the camera view, queue layout, metric you need, and operating environment. We can identify a practical first evaluation.