An Improved Real-time Method for Counting People in Crowded Scenes Based on a Statistical Approach

Riachi, Shirine; Karam, Walid; Greige, Hanna

doi:10.5220/0005108002030212

Cited by 6 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section various existing people counting techniques have been discussed. The indirect feature based approach adopted by Riachi et al [1] for people detection uses a Hessian matrix based SURF algorithm. After acquiring the frames from the video the computation was made faster by converting the original images into integral ones using box type convolution filters for pre-processing.…”

Section: Literature Surveymentioning

confidence: 99%

Vision Based Algorithm for People Counting Using Deep Learning

Padmashini¹,

Manjusha²,

Parameswaran³

2018

IJET

View full text Add to dashboard Cite

Estimating the number of people in a particular scene has always been an important topic of research in computer vision and digital image processing. People counting has wide applications in scenario ranging from analyzing the customer's choice and improving the quality of service in retail stores, supermarkets and shopping malls to managing human resources and optimizing the energy usage in office buildings. While there exists algorithms for counting people in a scene, some algorithm have set their benchmark in performance with respect to efficiency, flexibility and accuracy. In this paper, an attempt has been made to perform people counting using Deep Neural Networks (DNN) on comparison with existing image processing based algorithms like Histogram of Oriented Gradients with Support Vector Machine (HoG with SVM), Local Binary Pattern (LBP) based Adaboost classifier and contour based people detection. The proposed DNN based approach has higher accuracy at 90% and less false negatives.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Vision Based Algorithm for People Counting Using Deep Learning

Padmashini¹,

Manjusha²,

Parameswaran³

2018

IJET

View full text Add to dashboard Cite

show abstract

“…The beam transmits to a reflector across the desired path of measurement, and whenever the connection is broken, the counter records a new visitor. This is a popular method of counting but accuracy suffers when more than one person passes through the laser at the same time (Riachi, Karam, & Greige, 2014). Additionally, problems occur from obstructions (Dotson & Garris, 2008) and the inability to distinguish between objects and humans, thus mistakenly counting shopping carts, luggage, and other objects as patrons (Kryjak & Komorkiewicz, 2013).…”

Section: Literature Reviewmentioning

confidence: 99%

Determining Gate Count Reliability in a Library Setting

Phillips¹

2016

EBLIP

View full text Add to dashboard Cite

2016 Phillips. This is an Open Access article distributed under the terms of the Creative Commons-AttributionNoncommercial-Share Alike License 4.0 International (http://creativecommons.org/licenses/by-nc-sa/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly attributed, not used for commercial purposes, and, if transformed, the resulting work is redistributed under the same or similar license to this one. AbstractObjective -Patron counts are a common form of measurement for library assessment. To develop accurate library statistics, it is necessary to determine any differences between various counting devices. A yearlong comparison between card reader turnstiles and laser gate counters in a university library sought to offer a standard percentage of variance and provide suggestions to increase the precision of counts.Methods -The collection of library exit counts identified the differences between turnstile and laser gate counter data. Statistical software helped to eliminate any inaccuracies in the collection of turnstile data, allowing this data set to be the base for comparison. Collection intervals were randomly determined and demonstrated periods of slow, average, and heavy traffic.Results -After analyzing 1,039,766 patron visits throughout a year, the final totals only showed a difference of .43% (.0043) between the two devices. The majority of collection periods did not exceed a difference of 3% between the counting instruments.

show abstract

Design of an Image Skeletonization Based Algorithm for Overcrowd Detection in Smart Building

Manjusha

Parameswaran

2019

Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2018 (ISMAC-CVB)

View full text Add to dashboard Cite

An Improved Real-time Method for Counting People in Crowded Scenes Based on a Statistical Approach

Cited by 6 publications

References 17 publications

Vision Based Algorithm for People Counting Using Deep Learning

Vision Based Algorithm for People Counting Using Deep Learning

Determining Gate Count Reliability in a Library Setting

Design of an Image Skeletonization Based Algorithm for Overcrowd Detection in Smart Building

Contact Info

Product

Resources

About