VisionAIre
  • About Nodeflux
  • Visionaire Stream
    • Overview
    • Requirements
      • Credential Keys
      • Tested Hardware
      • Bandwith Requirements
    • Installation Guide
      • Dependencies
      • Simple Installation
      • Advanced Installation
      • Clustering Installation
      • Add-ons Analytics Installation
        • People Attributes Installation
        • Vehicle Attributes Installation
        • OVOD Installation
        • OVIC Installation
        • VM Installation
        • VLM Installation
    • Analytics
      • Face Recognition
        • Additional Information
          • Overview
          • Disclaimer
          • Metrics
          • Testing
      • People Analytics
      • Crowd Estimation
      • PPE Detection
      • License Plate Recognition
      • Vehicle Analytics
      • Water Level Monitoring
        • Camera Guideline
      • Pre-Flood Monitoring
      • Person Smoking Detection
      • Person with Handphone Detection
      • Smoke and Fire Detection
      • Person Using Firearms Detection
      • Vandalism Attempt Recognition
      • ATM Burglary Incident Recognition
      • Road Crash Monitoring
      • People Fighting Recognition
      • Riot Recognition
    • Developer Guide
      • How our APIs work
      • HTTP APIs
      • Websocket
      • Database Structure
    • Changelogs
  • Visionaire Snapshot
    • Overview
    • Requirements
    • Installation Guide
      • Face Searching & Matching
        • Single Node
        • Clustering
      • Helmet Detection
      • Chicken Estimation
      • Face Detection
      • Over Dimension Over Load
      • Frontal License Plate Recognition
    • Analytics
      • Face Searching & Matching
        • Face Enrollment
          • Image Guideline
          • Face and Image Quality Assessment
            • Setup On Premise
            • API
          • Insert / Update / Delete Enrollment
          • Batch Enrollment
      • Helmet Detection
      • Chicken Estimation
      • People Demography
      • Face Detection
      • Over Dimension Over Load
      • License Plate Recognition -Frontal
    • Developer Guide
      • APIs
        • Face Searching & Matching
        • Helmet Detection
        • Chicken Estimation
        • People Demography
        • Face Detection
        • Over Dimension Over Load
        • Frontal License Plate Recognition
      • Vanilla APIs for Face Enrollment
      • Porting Enrollment Database Cluster to Docker
    • Changelogs
  • VisionAIre Dashboard
    • Introduction
    • Add Analytic Assignment
    • Accessing Vanilla Database
    • Connect to Vanilla Websocket
    • Create your own visualization
      • Migration from Old Streamer to New Streamer
      • Drawing Region of Interest
      • Additional Visualization Query
Powered by GitBook
On this page
  • Camera Specification
  • Camera Specification
  • Disclaimer
  • Model Capability
  • Result Interpretability

Was this helpful?

Export as PDF
  1. Visionaire Stream
  2. Analytics

Crowd Estimation

PreviousPeople AnalyticsNextPPE Detection

Last updated 9 months ago

Was this helpful?

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 automatically like People Density analytics, 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.

Camera Specification

Camera Settings
Face Recognition
License Plate Recognition
General Analytics

Frame Resolution

1080p - 4K

1080p - 4K

720p - 1080p

Codec

H.264

H.264

H.264

Codec Profile

High

Main

Baseline

Bit Rate Mode

Variable (VBR)

Constant (CBR)

Variable (VBR)

Target Bitrate

2 - 6 Mbps

4 - 10 Mbps

1 - 4 Mbps

FPS Rate

25 - 30

30

15 - 30

Bandwidth

4 Mbps

6 Mbps

4 Mbps

Exposure Time/Shutter Speed

1/60s - 1/250s

1/1000s - 1/2000s

1/30s - 1/120s

Camera Specification

1. Crowd Estimation Extended References

In terms of Crowd Estimation, the resolution does affect accuracy. High resolution (e.g. HD 720p or Full-HD 1280p) is recommended for high density of crowd (>300 people in a frame) whilst smaller resolution (i.e.480p) is enough for low or moderate density of the crowd. Below is the table of recommendations for camera resolution, height, and installation angle.

Camera Recommendations
High Density Crowd
Low to Moderate Density Crowd

Resolution

720p(1280x720)

min 480p (640x480)

Height

8-12m

6-8m

Angle

30° - 40°

30° - 40°

Disclaimer

Model Capability

  • Nodeflux Crowd Estimation is focused on cases for a dense crowd. Below are some cases that are expected to be estimated correctly.

Currently, we also support low dense crowd similar to images below:

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 points and estimation range.

The estimation crowd counts will be in min-max range (example: 120 - 300 people) instead of actual head counts.

Crowd Estimation Camera Installation
Camera Placement
Low Density Crowd
Dense Crowd Condition
Dense Crowd Condition
Dense Crowd Condition
Low Density Crowd
Low Density Crowd
Crowd Estimation