Skip to main content

Crowd Management


What it is ?
Crowd Management deals with - How to come up with strategies to  better manage large gatherings

Why is it needed?

Many things can go wrong in large crowds 
  1. Outbreak
  2. Congestion
  3. Stampede
  4. Fights
  5. Disorder
  6. Missing People
How is it relevant now?

Big Data is being collected using UAVs, CCTVs etc.,
 Can we harness it to help solve some issues ?
Ex: Work by Prof. K.S. Rajan during Godavari Pushkaralu

Our Work

We took up one specific problem of Crowd Management which is Identification of Missing People. 
This is a very common issue that we observe in large gatherings. Here are some numbers that will justify this. 120,000,000 pilgrims attended the last Prayagraj Kumbh Mela in 2013, equivalent to the population of Japan. According to an official in charge of running the lost-found system, around 90% of the people who get lost are illiterate. He also adds that most people will spend only a few hours being lost. There's a 70% chance they get reunited with their families on the same day, 90% chance they get reunited within a few weeks and 99% chance they get reunited with their families by the end of the Kumbh Mela. Others go missing for dark reasons. Large events increase the risk of trafficking and in a place as crowded as the Mela, children go missing very easily. Traffickers see large events like these an opportunity. 

 How we did it ?

 2 step process

1. Identification
Given a photo of missing person, we ranked all the visible faces in the crowd based on a similarity score. 
The method first detects the faces and then using the features extracted it predicts the various landmarks on the face, which it uses to identifies the face.


 In the figure, we trained the model with the photo on the right. We then ranked each face in the photo on the right based on how close it is to the trained image. We can observe that it gave rank 1 to the person in the trained photo.
2. Tracking
Once we identify the face, we can select the face in the footage as a Region Of Interest . Then the algorithm tracks the path of  missing person.


Feature selection is done using discriminative correlation filter which supports channel and spatial reliability

Comments

Post a Comment

Popular posts from this blog

Human Trafficking dataset creation & analysis

Introduction The goal of this project is to create a Human Trafficking dataset from reliable sources such as news articles, Government agencies, etc and analyse the pain points in this area. Motivation   What is human trafficking? Human trafficking involves recruitment, harbouring or transporting people into a situation of exploitation through the use of violence, deception or coercion and forced to work against their will. In other words, trafficking is a process of enslaving people, coercing them into a situation with no way out, and exploiting them. What is it important?   Did you know that in 2015 alone, Human Trafficking generated $150 billion, more revenue  than Google, Nike, The NFL and Starbucks combined ?!?!   Sounds crazy right? Well there is more to this story than you know, that's why 18th of October is the EU Anti-Trafficking Day.According to a September 2017 report from the International Labor Organization (ILO) and Walk Free Fo...
Post a Comment
Read more

Traffic Violations in Metropolitan Cities

Introduction With the advent of the smartphone era and the availability of 4G internet across the country, police forces have begun to use electronic receipts of the traditional traffic challans. E-Challans are electronically generated penalty receipt that takes the place of the physical paper receipts and helps in digitizing the whole process of collecting challans and penalizing violations. In this project, we analyze the set of all unpaid E-Challans collected in metropolitan cities over a large span of time to gain unique insights about the nature of traffic violations in such cities. The problem is very relevant for a course on Big Data & Policing as it tries to answer the following important questions: How are traffic violations distributed spatially and temporally across the city boundaries? Can the most common violation types be characterized and be used for providing intervention insights? How can police leverage social media for increasing awareness and for targe...
Post a Comment
Read more