Object counting
Counting objects on the road or in the adjacent area is one of the important tasks for optimizing traffic in a modern city. It involves comparing the throughput capacity of road sections, traffic lights, pedestrian crossings, and subsequently making adjustments.
Solution metrics
98%
Recognition accuracy
Accuracy measured on test videos in the daytime
- < 1
Number of false positives per day per camera
≥ 10 FPS
Frames per second
camera requirement
≥ HD
Recommended video stream quality
20 px
Object size requirements in the frame
per vehicle
25 px
Object size requirements in the frame
per person
Technology Description
The Roadly video analytics system allows for counting the number of objects (vehicles and pedestrians) crossing the "boundary."
The "Object Counting" analytics provides information about objects that have crossed the boundary in either the forward or reverse direction.
The "Object Counting" analytics provides information about objects that have crossed the boundary in either the forward or reverse direction.
Screenshots and demo videos
Features of the technology
Traffic flow speed drop detection
Traffic flow densification detection
Traffic flow density accounting
Customizable reaction time