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
  • How it Works
  • People Counting
  • People Dwelling
  • People Density
  • People Analytics with Attributes
  • Architecture
  • Camera Specification
  • Camera Placement
  • Sample View
  • View to Avoid
  • Deployment Schema

Was this helpful?

Export as PDF
  1. Visionaire Stream
  2. Analytics

People Analytics

PreviousTestingNextCrowd Estimation

Last updated 8 months ago

Was this helpful?

How it Works

People Counting

Nodeflux People Counting is a Vision Artificial Intelligence Analytics Software that allows you to know the number of people in a particular area with multiple regions of interest. This can be done to capture people traffic, like at the front door, gate, elevator, lift, lobby, etc. Using Nodeflux People Counting, organizations can seamlessly gather the number of visitor data and analyze peak hours in each respective area.

To verify that your camera can work with our People Counting analytic, try performing a test. Make sure that our analytic can detect people (you can see a bounding box around that person) and the bounding box can follow the person till crossing the counter line.

Our model requires to detect person with height above 200 pixels on frame or the a quarter from height your display if the frame is 1080p. Less than that, the result might varies depends on the how the person visually presented.

People Dwelling

Nodeflux People Dwelling is a Vision Artificial Intelligence Analytics Software that allows you to know the number of people in a particular area and how long they stay at the same position. This can be used to capture people's traffic, like at the front door, gate, elevator, lift, lobby, in front of shelves, and etc. Using Nodeflux People Dwelling, organizations can seamlessly gather the number of visitor data, how long they stay at the same position and analyze their behavior in each respective area.

People Density

Nodeflux People Density is a Vision AI analytics software which aims to measure the number of people at small to low medium density in an area of interest. The analytics work within the common practice is to count each person automatically to get an insightful report. The inference result will provide you the exact number of people in a particular area of interest at small to low medium density.

People Analytics with Attributes

Nodeflux People Analytics with Attributes is same as the People Analytics only explained above excluding the logic of People Density. The Vision AI analytics software provides the enrichment data of person attributes within the person detection in People Counting and People Dwelling.

The attributes data includes the broad range of enrichment data which are:

  1. Age: Teenager, Adult, Elderly

  2. Gender: Female, Male

  3. Bags: HandBad, ShoulderBag, Backpack

  4. Hat: Hat and No Hat

  5. Glasses: Glasses and No Glasses

  6. Upper Wear: UpperStride, UpperLogo, UpperPlaid, UpperSplice

  7. Lower Wear: LowerStripe, LowerPattern, LongCoat, Trousers, Shorts, Skirt&Dress

Since Nodeflux People Analytics with Attributes utilizes the snapshot platform, an additional docker-compose.yml file needs to be deployed alongside the other below services. The following directive link outlines the installation process for deploying the docker-compose.yml file specific to the people attribute pipeline of snapshot platform:

Architecture

Visionaire People Analytics utilizes a combination of other services:

  1. Postgres - For database,

  2. Docker Snapshot - For People Analytics with Attributes related,

  3. Visionaire Docker Stream - For video stream processing,

  4. Visionaire Dashboard (Optional) - Built-in dashboard for visualization.

Camera Specification

Camera Settings
People Analytics
General Analytics

Frame Resolution

1 - 4K

720p - 1080p

Codec

H.264

H.264

Codec Profile

Baseline

Baseline

Bit Rate Mode

Variable (VBR)

Variable (VBR)

Target Bitrate

2 - 6 Mbps

1 - 4 Mbps

FPS Rate

25 - 30

15 - 30

Bandwidth

4 Mbps

4 Mbps

Exposure Time/Shutter Speed

1/30 - 1/120s

1/30s - 1/120s

Camera Placement

1. Short Range View (Up to 5 meters)

  • Camera Placement: Ideal height is around 2 to 2.5 meters except for crowd estimation around 5 m - 10 m. Place cameras to capture areas like entrances, counters, or specific zones where individuals will be in close proximity.

  • Camera Type and Specs: Use wide-angle lenses for a broader field of view. A resolution of 1080p or higher ensures detailed images.

  • Lighting: Uniform, soft lighting to minimize shadows and glare. Artificial lighting should complement natural light.

  • Analytics Focus: Ideal for detailed behavioral analysis and individual interactions.

2. Medium Range View (5 - 15 meters)

  • Camera Placement: Height around 3 to 4 meters except for crowd estimation around 5 m - 10 m. Cameras should overlook areas like lobbies, hallways, or open office spaces.

  • Camera Type and Specs: Standard lenses are suitable. A resolution of 1080p to 4K is recommended to maintain detail at this range.

  • Lighting: Balanced lighting is crucial. Avoid areas with significant light variation (like directly under skylights).

  • Analytics Focus: Suited for tracking movement patterns, group interactions, and general behavior analysis.

3. Additional Considerations

  • Angle of Capture: Should be as direct as possible. Avoid steep angles to prevent distortion and loss of detail.

  • Data Privacy: Ensure compliance with privacy laws and regulations. Inform individuals about surveillance and data usage.

  • Environmental Factors: Outdoor cameras need to be weatherproof and capable of adjusting to changing light conditions.

  • Integration with Analytics Software: Ensure cameras are compatible with your analytics software for seamless data processing and analysis.

Sample View

View to Avoid

Please avoid a CCTV view when there are a lot of mannequins, banner/digital ads which shows a person or hanged clothes in monitored area to prevent false detection.

Deployment Schema

Architecture
People Counting, Dwelling, Density Camera Installation
Assigning crowd estimation into the camera that not suitable
People Attributes Installation
People Analytics - People Counting
People Analytics - People Dwelling
People Analytics - People Density
People Analytics (Counting) with Attributes
Detailed person size from previous image. Both person height is more than 200 pixels.
Recommended person vs screen proportion
People Counting
People Counting
People Dwelling
Camera placement is not suitable to implement counter line or region of the interest