Scribd Logo
Upload

Welcome to Scribd!

  • 22 views

    Real Time People Counter

    Uploaded by

    Prathik Vijaykumar
    This document proposes a real-time people counter using background subtraction, Gaussian blurring, thresholding, and contour detection to track the center of each object entering or exiting an area. The method achieved 87.5% accuracy in counting people, an improvement over previous experiments using face detection which rely on specific camera angles. While the results were good, the document concludes that segmentation could help improve the people counter.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Real Time People Counter

    Uploaded by

    Prathik Vijaykumar
    22 views6 pages
    This document proposes a real-time people counter using background subtraction, Gaussian blurring, thresholding, and contour detection to track the center of each object entering or exiting an area. The method achieved 87.5% accuracy in counting people, an improvement over previous experiments using face detection which rely on specific camera angles. While the results were good, the document concludes that segmentation could help improve the people counter.

    Original Title

    Real time People Counter

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document proposes a real-time people counter using background subtraction, Gaussian blurring, thresholding, and contour detection to track the center of each object entering or exiting an area. The method achieved 87.5% accuracy in counting people, an improvement over previous experiments using face detection which rely on specific camera angles. While the results were good, the document concludes that segmentation could help improve the people counter.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    22 views6 pages

    Real Time People Counter

    Uploaded by

    Prathik Vijaykumar
    This document proposes a real-time people counter using background subtraction, Gaussian blurring, thresholding, and contour detection to track the center of each object entering or exiting an area. The method achieved 87.5% accuracy in counting people, an improvement over previous experiments using face detection which rely on specific camera angles. While the results were good, the document concludes that segmentation could help improve the people counter.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 6

    Real time People Counter

    Dale Baker
    Goal/Problem
    Counting the number of people in a given area by watching the exit and counting
    people leave/enter
    Background research
    Face detection

    Edge detection/classifiers (histogram of gradients)

    Circle detection (circular hough transform)


    Method - background subtraction
    Gaussian blur/resizing

    Background subtraction

    Closing/thresholding

    Contours

    Track center of each object


    Results
    87.5% accuracy - similar to previous experiments

    Improvement on face detection as

    it doesn’t rely on specific camera

    angles
    Conclusion
    Pretty good

    Needs segmentation

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy