Press Esc to close

IISc develops model to predict headcount in crowds

September 18, 2016, Bengaluru, DHNS 1:54 IST

Technology will help in averting disasters

 Researchers at the Indian Institute of Science (IISc). DH File Photo.
Researchers at the Indian Institute of Science (IISc) have developed a model that can help gauge the crowd density simply through a picture of a gathering of people.

The technology could lead to better crowd management and avert disasters like the ones that take place during the Kumbh Melas in North India.

Prof R Venkatesh Babu, assistant professor, Department of Computational and Data Sciences (CDS) at IISc, and his team from the Video Analytics Lab at the institute use neural networks and deep learning models. Neural networks are the core blocks of the machine -learning paradigm — deep learning.

Deep learning involves algorithms that attempt to model high-level abstractions in data by using a deep graph with multiple processing layers and the ability to handle unknown inputs and learn from observational data.

The research team applied these techniques to estimate the headcount in a set of images with dense crowds. While there are methods that use videos and images to estimate the crowd count, the one used by IISc scientists can estimate a crowd ranging from 100 to 2,000 people using simple static images, ratherthan videos, with better accuracy.

They used about 50 grey scale images from a wide range of scenarios such as concerts, political rallies, religious gatherings, stadia among others, with the number of people per image varying between 94 and 4,543. In most of the cases, the predicted count was close to the actual count. To quantify the performance of the model, the scientists compared their method with other existing models and found that their method was more accurate, said a release from the IISc.

Prof Babu explained that an extension of the current method, incorporating temporal crowd dynamics, can be used to analyse video streams, typically from surveillance cameras and drones.

“This analysis can aid civic planners and event organisers to predict anomalous crowd patterns leading to scenarios such as stampedes,” he said.

Go to Top

Photo Gallery
Rashtriya Swayamsevak Sangh (RSS) volunteers taking...

Rashtriya Swayamsevak Sangh (RSS) volunteers taking...

Air Chief Marshal BS Dhanoa, Chief of the Air Staff...

Air Chief Marshal BS Dhanoa, Chief of the Air Staff...

SUCI activists stage a protest rally against State...

SUCI activists stage a protest rally against State...

Mick Jagger of the Rolling Stones performs during the...

Mick Jagger of the Rolling Stones performs during the...

Mime artist Ujjal Kar gets ready to perform as Charlie Chaplin...

Mime artist Ujjal Kar gets ready to perform as Charlie Chaplin...

Acid attack survivor Mohi walks the ramp along with...

Acid attack survivor Mohi walks the ramp along with...

People buying Sugar Canes in a market for upcoming...

People buying Sugar Canes in a market for upcoming...

Britain's Foreign Secretary, Boris Johnson, arrives to speak at the Chatham...

Britain's Foreign Secretary, Boris Johnson, arrives to speak at the Chatham...

Actress Katerina Lehou as high priestess, passes the Olympic Flame onto...

Actress Katerina Lehou as high priestess, passes the Olympic Flame onto...

Tamil Nadu coach L Balaji with R Ashwin at BKC...

Tamil Nadu coach L Balaji with R Ashwin at BKC...

Like us on Facebook

Copyright 2017, The Printers (Mysore) Private Ltd., 75, M.G Road, Post Box 5331, Bengaluru - 560001
Tel: +91 (80) 25880000 Fax No. +91 (80) 25880523
Powered by Yodasoft Technologies Pvt. Ltd.