Estimating the density of the people and counting the number of people in a crowd environment for human safety

Karpagavalli, P.; Ramprasad, A. V.

doi:10.1109/iccsp.2013.6577138

Cited by 30 publications

(14 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…more than 4 persons per square meter. Such densities are however difficult to obtain from real life scenarios; moreover, if we use video data as ground truth, the latter is inaccurate at high densities [6]. On the other hand, controlled experiments with thousands of participants and high induced crowd density are beyond the scope of a research paper because of security risks.…”

Section: (8)mentioning

confidence: 99%

Detecting high indoor crowd density with Wi-Fi localization: a statistical mechanics approach

et al. 2019

View full text Add to dashboard Cite

Crowd disasters have taken many human lives. The Love Parade disaster in Duisburg, 2010, the Ellis Park Stadium disaster in Johannesburg, 2001, the PhilSports Stadium stampede in Manila, 2006, are just a few examples. One of the major factors contributing to crowd disasters are critically dense spots [1-3], which are difficult to detect due to lack of macroscopic overview of the crowd [1]. In this paper we address the problem of estimating the crowd density distribution in situations such as indoor dance events, to enable prevention of crowd disasters. A lot of research on estimating crowd density concerns processing video records from security cameras [4, 5]. However, this approach does not suffice to detect critically raised crowd density. Firstly, as mentioned before, it is difficult to obtain macroscopic overview of the crowd. Secondly, the lighting conditions at a concert might not be sufficient for video-based crowd analysis. Finally, the error of counting people increases with the increase of the actual crowd density [6] due to the so-called occlusion effects. Another way to monitor the crowd density is by using RFID technology [3]. Each participant is asked to wear a tag, and RFID readers are distributed across the venue. This approach, however, requires participation from the crowd and deployment costs.

show abstract

Section: (8)mentioning

confidence: 99%

Detecting high indoor crowd density with Wi-Fi localization: a statistical mechanics approach

et al. 2019

View full text Add to dashboard Cite

show abstract

“…So in the proposed system, GMM is selected as the basic step that was performed before further processing of the image frames [6].…”

Section: A Object Detectionmentioning

confidence: 99%

“…Gaussian mixture model is widely used approach for background modeling to detect moving objects from fixed stationary camera. This model is more robust than other models and in this method, all objects can be filtered out and each pixel location is represented as a mixture of Gaussian functions to form a probability distribution function [6]. In this method, Gaussians are calculated and decide which Gaussians matches up to the background based on the resolution and the variance of all Gaussians.…”

Section: A Earlier Crowd Detection In Three Levelsmentioning

confidence: 99%

Prediction of Crowd in Three Levels: a Foot Step to Anomalies Prevention

P*¹,

Krishnakumar²

2019

IJITEE

View full text Add to dashboard Cite

Crowd is a huge number of people meet jointly in a disorganized or unmanageable way. Crowd in any atmosphere may leads to suspicious events. Nobody can predict the crowd and some anomalies might happen in the presence of crowd. So prevention of crowd well in advance is the only remedy to tackle the situation. Advance crowd detection is an important subfield in video surveillance. Prior detection or prevention of crowd has so much of importance while we are considering the present scenarios all over the world. So now-days, an automatic crowd prevention technique is needed for all the countries to protect their land, provide safety for their citizens and law enforcement. Crowd prevention system using manual operators are weak due to many physiological and non-physiological factors but it will provide better performance than automatic system in case of decision making. Many models have been developed so far to detect the crowd automatically. Our system aims to predict the crowd well in advance in three levels and so the automatic system or the operator will get enough time to respond or take a decision. To detect the formation of crowd well in advance, all the human objects in a frame was identified by Gaussian mixture model and object classification, shadow was eliminated and crowd was predicted using the object rectangle model and center vertical line model. The pixel distance between the each rectangles and center line is used to predict the formation of crowd. This paper also gives some suggestions to crowd modelling.

show abstract

“…Secondly, the lighting conditions at a concert might not be sufficient for video-based crowd analysis. Finally, the error of counting people increases with the increase of the actual crowd density [6] due to the so-called occlusion effects. Another way to monitor the crowd density is by using RFID technology [3].…”

Section: Introductionmentioning

confidence: 99%

Detecting high indoor crowd density with Wi-Fi localization: A statistical mechanics approach

Georgievska¹,

Rutten²,

Amoraal³

et al. 2019

Preprint

View full text Add to dashboard Cite

We address the problem of detecting highly raised crowd density in situations such as indoor dance events.We propose a new method for estimating crowd density by anonymous, non-participatory, indoor Wi-Fi localization of smart phones. Using a probabilistic model inspired by statistical mechanics, and relying only on big data analytics, we tackle three challenges: (1) the ambiguity of Wi-Fi based indoor positioning, which appears regardless of whether the latter is performed with machine learning or with optimization, (2) the MAC address randomization when a device is not connected, and (3) the volatility of packet interarrival times. The main result is that our estimation becomes more -- rather than less -- accurate when the crowd size increases. This property is crucial for detection of dangerous crowd density.

show abstract

Estimating the density of the people and counting the number of people in a crowd environment for human safety

Cited by 30 publications

References 10 publications

Detecting high indoor crowd density with Wi-Fi localization: a statistical mechanics approach

Detecting high indoor crowd density with Wi-Fi localization: a statistical mechanics approach

Prediction of Crowd in Three Levels: a Foot Step to Anomalies Prevention

Detecting high indoor crowd density with Wi-Fi localization: A statistical mechanics approach

Contact Info

Product

Resources

About