Measurement Types and Accuracy
A table with a summary of the accuracy and speed of the services offered by AISP.
Traffic measurement (basic)
3.00%
x5
Speed measurement
5-10%
x5
ALPR measurement + Traffic
10.00%
x3
Parking ALPR (50-60FPS FHD video)
10.00%
x1-x2
Anonymization of video
1.00%
x5
Notes on the above table and results
*processing speed calculated for a 20fps video,
** measurement error determined on the basis of a test set of 70 films,
*** the measurement error for intersections is greater due to the large number of intersecting vehicle trajectories,
*** the measurement error for pedestrians is larger, more intersections of traffic trajectories and greater similarity of objects
Traffic measurement cross-sections/intersections
The basic measurement of road traffic is the counting of vehicles and pedestrians in cross-sections and intersections. Historically, the first service offered by our company, derived from General Traffic Measurements.
For detailed information about traffic counting capabilities, see Traffic Counting Service.
Speed measurement
For each tracked object in the video, we know its location in each image frame (motion trajectory). By defining a 4-point polygon that maps to known real-world dimensions (width and length in meters), AITracker calculates the speed of each vehicle using homography transformation. The obtained results are saved in the result sheet Velocity.csv and in the form of graphs. It is also possible to receive data in the format used by SCPR.
For detailed configuration and technical information, see Speed Measurement Service.
Speed and Weight Limits
AITracker can also analyze speed limit compliance and weight restrictions. You can configure day/night speed limits and weight thresholds to identify vehicles exceeding these limits. Note that these are estimations for statistical analysis - not certified for legal enforcement.
For limit configuration details, see Speed and Weight Limits.
Pedestrian measurement
Pedestrian measurement is included in the Traffic Counting Service. While pedestrians are more difficult to count than vehicles due to frequent trajectory intersections, occlusions, and high similarity between tracked objects, AITracker handles them within the same unified counting framework.
Types of pedestrian categories recognized by AI:
Pedestrians
Bikers
People riding a scooter (TODO)
Persons driving a baby stroller (TODO)
ALPR Services
From 2022, we introduced the license plate recognition service (ALPR). For each counted vehicle we are able to recognize the license plate. We offer two specialized ALPR services depending on your camera setup:
For fixed/stationary cameras mounted on poles, bridges, or permanent structures. Combines traffic counting with license plate recognition. Ideal for:
Origin-Destination studies
Toll road analysis
Traffic pattern research
For mobile cameras mounted inside moving vehicles (behind windshield). Designed for parking zone monitoring. Ideal for:
Parking zone enforcement
Parking lot management
Time-limited parking monitoring
Requirements: 50-60 FPS video, vehicle speed < 30 km/h.
Video Anonymization
For privacy compliance and GDPR requirements, see our Video Anonymization Service.
Last updated
Was this helpful?