Visionaire Documentation

Crowd Estimation

Nodeflux Crowd Estimation is a VisionAI analytics software which aims to measure the number of people at large in a crowd. While the common practice is to count each person manually, which requires more time to consume to get an insightful report, this analytic will provide you the estimated number of people in a particular area of interest.


Model Capability

  • Nodeflux Crowd Estimation is focused on cases for a dense crowd. Below are some cases that are expected to be estimated correctly.
Dense Crowd Condition
Dense Crowd Condition
Dense Crowd Condition
The Crowd Estimation models have limited capabilities for a low-density crowd as it focusses on dense-crowd cases. The Low Density CE is more suitable analytics for low-density crowd. Below are few examples of cases that our Low Density CE would perform better than the Crowd Estimation.
Low Density Crowd
Low Density Crowd
Low Density Crowd

Low Density Case

An improvement for Crowd Estimation model where we combine our People Dwelling and People Counting model to provide crowd estimation for density less than 100 people.

Result Interpretability

The Crowd Estimation model will produce two outputs which are heatmap density and estimation of the crowd.
An input image (left) will produce heatmap and density counts)
The estimation crowd counts will be in min-max range (example: 120 - 300 people) instead of actual head counts.