Crowd management can be critical in a fire emergency – or in almost any other emergency situation. The Fire Protection Research Foundation (FPRF) has undertaken a project to develop a computerized tool to provide data and situational awareness about crowds based on computer vision analysis of video.

Crowds have become an unusual occurrence during the COVID-19 pandemic, but sooner or later, life will be returning to normal. When it does, the safety consequences of poor crowd management will again become top-of-mind for many in the emergency response fields.

Preventing trampling incidents With AI

Crowds can change rapidly during an emergency, and emergency responders must act quickly to respond to changes in crowd density, movement and other behaviors. Crowd dynamics can have tragic consequences in cases such as trampling or crushing incidentsThe FPRF project has developed a proof-of-concept framework for “data-informed crowd management and support.” The low-cost, open-source framework highlights collection, analysis, visualization and reporting of crowd movement to inform and direct crowd and evacuation strategies in near-real-time.

Crowd dynamics can have tragic consequences in cases such as trampling or crushing incidents, violence, or if there are insufficient exits. In the worst cases, injuries and deaths can occur. A real-time crowd management tool can help to neutralize these potentially dangerous situations. 

Deep-learning computer vision and video image recognition (using artificial intelligence [AI]) are the technologies that enable the project. The tools can be applied to live video, to manage an event in real-time; or to recorded video to evaluate crowd activity as part of the event-planning process. The deep-learning capability is called congested scene recognition, or CSR, which both counts the number of individuals in a crowd and identifies their spatial distribution.

Algorithms evaluate crowd movement

Modern technologies and algorithms evaluate crowd movement over time in high-risk spaces. Users may upload a still image, and the tool will evaluate the crowd count in a given area. For a video feed, the system can capture individual frames at a user-defined interval (1 to 30 seconds) or manually. Crowd counts are then graphed and displayed to identify crowd density trendsThe model then evaluates the frame, predicts the count and provides a crowd density heat map within about 5 seconds. Crowd counts are then graphed and displayed to identify crowd density trends. Early trials have been promising, according to the researchers.

The research project is led by the FPRF and the National Fire Protection Association (NFPA) with funding through a U.S. National Institute of Standards and Technology (NIST) Fire Grant.

So far, the proof-of-concept tool has been created, and testing this fall will evaluate how well it works on an array of venues, how well it estimates crowd counts, and the feasibility of full-scale implementation. A final report will include the programming code associated with the tool and guidance on how it can be implemented. Use of open-source platforms and general-purpose programming languages ensures the source code for the crowd management tool is freely available, and thus inexpensive.

Anticipating behavior is crucial

Researchers on the project note that crowds are not the problem, but rather the problem is incomplete understanding of the anticipated behavior of crowds and the inability to respond quickly. There are many variables, including the venue itselfThere are many variables, including the venue itself, and internal and external factors such as the purpose, organization and emotional nature of the crowd.

The NFPA 101, Life Safety Code, includes regulatory requirement for managing large crowds. According to the code, crowd managers are responsible for understanding crowd dynamics, management techniques, and the venue’s emergency response plan, among other factors, according to NFPA. To prepare for large events, crowd managers must evaluate specific actions necessary for various situations, anticipated occupancy levels, the adequacy of ingress and egress, and expected human behavior.

Share with LinkedIn Share with Twitter Share with Facebook Share with Facebook
Download PDF version Download PDF version

Author profile

Larry Anderson Editor,, Notting Hill Media

In case you missed it

In A Busy Wildfire Season, Researchers Seek New Approaches
In A Busy Wildfire Season, Researchers Seek New Approaches

It makes perfect sense that a horrific wildfire season would come in the year 2020 on the heels of a pandemic. Dozens of major fires burned across North America in September, including 85 large uncontained fires and six contained fires across 12 states. Active fires have burned more than 3 million acres already, and 41,417 fires have burned almost 5 million acres year-to-date. The severity of the wildfire season is on track to surpass the 10-year average. Better understanding wildfires Global warming is often mentioned as a contributor to the wildfires, but there are other factors, too. Increasingly, researchers are looking to apply new approaches in address the risk of wildfires. They include tools such as deep learning and artificial intelligence (AI) to better understand wildfires and to control their intensity. The model could be used to reveal areas of greatest risk for wildfires A new deep learning model uses remote sensing and satellite data to trace fuel moisture levels across 12 Western states, in effect tracking the amount of easily burnable plant material and how dry it is. After additional testing is complete, the model could be used to reveal areas of greatest risk for wildfires and to plan the best areas for prescribed burns. Led by a Stanford University ecohydrologist, the research was published in the journal Remote Sensing of Environment. Recurrent neural network The model uses data from the U.S. Forest Service’s National Fuel Moisture Database, which amasses plant water content information from thousands of samples. Using a ‘recurrent neural network,’ the system leverages the fuel moisture data to corroborate measurements of visible light and microwave radar signals from spaceborne sensors that are tasked with estimating fuel moisture measurements. Newer satellites with longer wavelengths allow sensitive observations about moisture content deeper into the forest canopy. Estimates from the model are used to generate interactive maps that fire agencies may one day use to identify patterns and prioritize wildfire control estimates. Researchers are also working to analyze the impact of better and more efficient firefighting on the size and frequency of wildfires. The theory goes: When firefighters extinguish smaller vegetation fires, a consequence is the creation of an environment where wildfires are larger and/or more frequent. Natural cycle of regeneration Older woods will naturally catch fire from the sun’s heat to make way for fresh growth The theory is based on the premise that wildfires play an essential role in the periodic regeneration of forests. Older woods will naturally catch fire from the sun’s heat to make way for fresh growth. However, more efficient firefighting can disrupt the natural cycle and, along with global warming, aggravate the broader likelihood of larger and more frequent fires. Researchers at the WiFire Lab in California and the University of Alberta in Canada are using artificial intelligence (AI) to analyze the environment and provide recommendations for prescribed burns that can save some parts of the forest without interfering with the natural cycle of regeneration. Providing early warning of wildfires Equipment operated by Pacific Gas and Electric (PG&E) caused 2018’s Camp Fire, the most destructive wildfire in California history. Because of the threat of sparking a wildfire, PG&E this year shut off power to 172,000 customers in Northern California on Labor Day weekend, for example. A concern is the threat of winds tearing down power line or hurling debris into them. Southern California Edison (SCE), another utility, warned that about 55,000 customer accounts could lose power. California utilities SCE, PG&E and San Diego Gas and Electric are helping to fund a network of ALERTWildfire video cameras in California that will help to provide early warning of wildfires. Video cameras keep watch throughout five Western United States to provide early warning, and the number of cameras is growing fast.

Should Firefighters And First Responders Use Face Masks?
Should Firefighters And First Responders Use Face Masks?

Should firefighters and other first responders be exempt from requirements that they wear face masks to prevent spread of the novel coronavirus (COVID-19)? The City Council of Portsmouth, New Hampshire, seems to think so. They are proposing an amendment to exempt first responders from complying with the city’s face mask ordinance. Amendment to Exempt first responders from face mask rule Specifically, the proposed amendment states, “Exempted from the requirements of the ordinance requiring wearing of face coverings include law enforcement personnel, first responders or other workers, who are actively engaged in their tasks, if wearing a face covering may hinder their performance.” The Centers for Disease Control and Prevention (CDC) recommends that everyone wear masks in public settings The Centers for Disease Control and Prevention (CDC) recommends that everyone wear masks in public settings, especially when social distancing cannot be maintained. The CDC does not specify a need to exempt first responders. However, there is a possibility that a mask could interfere with the work of firefighters or first responders, especially when they are performing tasks that require physical exertion. Face masks can inhibit communication among first responders Face masks, covering the mouth and nose, could also inhibit communication by muffling sound and obstructing facial expressions. Obviously, communication is of paramount importance for firemen working as a team in an emergency, or when a first responder is seeking to give clear directions to the public. The issue of face masks has been inexorably entwined with the well-being of first responders, since the beginning of the COVID-19 pandemic. Early on during the infection spread, health officials dismissed face masks as a tool to avoid spread of the disease. They said that the masks were ineffective at preventing community spread and that, supplies of personal protective equipment (PPE) needed to be conserved for health professionals and first responders. Importance of face masks in controlling spread of COVID-19 However, the early advice was completely reversed in late March 2020 and masks have been advocated ever since. A mask, worn by an infected individual, reduces the dispersion of virus-laden droplets that spread the disease. Now, experts contend that any type of mask, including cloth or paper, can help to reduce spread of the COVID-19 virus. Expanding the use of masks to include those that are not conformant with the N-95 classification effectively eliminated any concerns about supply and helped to make the widespread use of masks the norm. To some extent, however, mask usage in the United States has been politicized and some see the requirements as an affront to liberty. Need for wearing face masks in public Masks are a useful preventative measure for firefighters working together in a communal area Fire and emergency departments face the same challenges as other businesses and institutions, as they seek to remain safe in a communal workspace. Masks are a useful preventative measure for firefighters working together in a communal area or when training or resting. Wearing masks in public also allows departments to model best practices and promote a positive perception of the department to the public. Disciplined use of face masks demonstrates unselfishness and respect for others. It communicates professionalism and concern for the greater good. Masks go a long way in saving lives of first responders Perception may also be an issue when it comes to the choice of masks, which become a de facto part of a uniform. Masks with political statements should be avoided, for example. Considering that dozens of American fire and EMS members have died of COVID-19 infection, since March 2020, the use of masks is another way that firefighters can work to save lives. However, sufficient flexibility is needed so that the use of masks does not interfere with other lifesaving duties.

What Are the New Trends in Firefighting Equipment?
What Are the New Trends in Firefighting Equipment?

Equipment is an important element in fighting fires, and in keeping firefighters safe. But what new needs are driving the development of equipment? How can equipment expand its role in fighting fires, or in managing building occupancy and traffic flow for that matter? We asked our Expert Panel Roundtable: What are the new trends and opportunities in firefighting equipment?