Estimation of crowd density using image processing

Marana, Aparecido Nilceu; Velastín, Sergio A.; Costa, L.F.; Lotufo, Roberto de Alencar

doi:10.1049/ic:19970387

Cited by 114 publications

(86 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Typical solutions are based on the analysis of stationary scenes from the video sequences. Estimation of crowd density is provided in [11] with the use of the texture information based on grey level transition probabilities. People detection in [10] is based on the Haar wavelet transform (used for the head detection) and on the support vector machine classifier.…”

Section: Related Workmentioning

confidence: 99%

New Approach To Traffic Density Estimation Based On Indoor And Outdoor Scenes From CCTV

Chmielewska

Parzych

Marciniak

et al. 2015

Foundations of Computing and Decision Sciences

View full text Add to dashboard Cite

Abstract. In this paper we present an algorithm for precise estimation of moving objects density (typically people and vehicles) in indoor and outdoor scenes. Automatic generation of the so-called density maps is based on video sequences acquired by surveillance systems. Our approach offers two types of solutions. The first one increments the accumulation table when a moving object is detected in a location of interest, delivering a density map of the presence of moving objects. The second algorithm increments the accumulation table only in cases of detecting a new moving object, resulting in a density map of the count of moving objects. The proposed algorithms were tested with the use of PETS 2009 database and with our own database of long-term video recordings. Finally, results of the density maps visualization and determination of the "busy hours" are presented.

show abstract

Section: Related Workmentioning

confidence: 99%

New Approach To Traffic Density Estimation Based On Indoor And Outdoor Scenes From CCTV

Chmielewska

Parzych

Marciniak

et al. 2015

Foundations of Computing and Decision Sciences

View full text Add to dashboard Cite

show abstract

“…This first paper presenting GLDM discussed also a set of features for characterising it, and consequently measure image texture. The proposed feature set is quite large, but only few of the features were exploited when the co-occurrence matrix was employed for detecting crowds: for example in [1] four features called contrast, homogeneity, energy, and entropy were used as input to a neural network, developed for classifying crowd density. In [7] the same indicators were exploited, again for measuring crowd density.…”

Section: Texture Analysismentioning

confidence: 99%

“…Other indicators measure how even the distribution among the bins is, as it is the case of energy and entropy. These four features were exploited in [1].…”

Section: Gldm Indicatorsmentioning

confidence: 99%

“…The core of our approach is based on a machine learning classifier which can categorise texture features extracted from image regions into a set of classes corresponding to different crowd density. We extend the feature set proposed by [1] to improve the classification performance in small image areas, demonstrate the ability of the method to localise the crowd and present a thorough evaluation of the system on a challenging data set acquired during a real crowded event. We first present state of the art in the area of crowd monitoring, then describe different components of our system, followed by experiments and finally briefly conclude and discuss possible future work.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Texture-Based Crowd Detection and Localisation

Ghidoni¹,

Cielniak

Menegatti³

2013

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

This paper presents a crowd detection system based on texture analysis. The state-of-the-art techniques based on co-occurrence matrix have been revisited and a novel set of features proposed. These features provide a richer description of the co-occurrence matrix, and can be exploited to obtain stronger classification results, especially when smaller portions of the image are considered. This is extremely useful for crowd localisation: acquired images are divided into smaller regions in order to perform a classification on each one. A thorough evaluation of the proposed system on a real world data set is also presented: this validates the improvements in reliability of the crowd detection and localisation.

show abstract

“…Generally, there are two main targets when estimating crowd's density: 1) providing an approximate number of how many people are in the target scene [16,1,18,5,13]; and 2) providing a range of people in the crowd i.e. determining the density in broad classes [2,3,4]. The second target has been selected since it is more appropriate to general use.…”

Section: Introductionmentioning

confidence: 99%

On crowd density estimation for surveillance

Rahmalan

Nixon

Carter

2006

IET Conference on Crime and Security

144

View full text Add to dashboard Cite

The goal of this work is to use computer vision to measure crowd density in outdoor scenes. Crowd density estimation is an important task in crowd monitoring. The assessment is carried out using images of a graduation scene which illustrated variation of illumination due to textured brick surface, clothing and changes of weather. Image features were extracted using Grey Level Dependency Matrix, Minkowski Fractal Dimension and a new method called Translation Invariant Orthonormal Chebyshev Moments. The features were then classified into a range of density by using a Self Organizing Map. Three different techniques were used and a comparison on the classification results investigates the best performance for measuring crowd density by vision.

show abstract

Estimation of crowd density using image processing

Cited by 114 publications

References 0 publications

New Approach To Traffic Density Estimation Based On Indoor And Outdoor Scenes From CCTV

New Approach To Traffic Density Estimation Based On Indoor And Outdoor Scenes From CCTV

Texture-Based Crowd Detection and Localisation

On crowd density estimation for surveillance

Contact Info

Product

Resources

About