Proceedings of the AAAI Conference on Artificial Intelligence
Formal response organizations perform rapid damage assessments after natural and human-induced di... more Formal response organizations perform rapid damage assessments after natural and human-induced disasters to measure the extent of damage to infrastructures such as roads, bridges, and buildings. This time-critical task, when performed using traditional approaches such as experts surveying the disaster areas, poses serious challenges and delays response. This paper presents an AI-based system that leverages citizen science to collect damage images reported on social media and perform rapid damage assessment in real-time. Several image processing models in the system tackle non-trivial challenges posed by social media as a data source, such as high-volume of redundant and irrelevant content. The system determines the severity of damage using a state-of-the-art computer vision model. Together with a response organization in the US, we deployed the system to identify damage reports during a major real-world disaster. We observe that almost 42% of the images are unique, 28% relevant, and...
During large-scale disasters it is not uncommon for Public Safety Answering Points (e.g., 9-1-1) ... more During large-scale disasters it is not uncommon for Public Safety Answering Points (e.g., 9-1-1) to encounter service disruptions or become overloaded due to call volume. As observed in the two past United States hurricane seasons, citizens are increasingly turning to social media whether as a consequence of their inability to reach 9-1-1, or as a preferential means of communications. Relying on past research that has examined social media use in disasters, combined with the practical knowledge of the first-hand disaster response experiences, this paper develops a knowledge-driven framework containing parameters useful in identifying patterns of shared information on social media when citizens need help. This effort explores the feasibility of determining differences, similarities, common themes, and time-specific discoveries of social media calls for help associated with hurricane evacuations. At a future date, validation of this framework will be demonstrated using datasets from m...
This abstract highlights research challenges to improving effectiveness of integrating informatio... more This abstract highlights research challenges to improving effectiveness of integrating information and communication technologies during emergencies. Proposed as a research focus is the integration of proven virtual activation processes with an unobtrusive research presence. This positions the research presence during a real-time emergency to glean previously unknown information/rationales on how decision-makers decide and take action. Establishing a collaborative partnership by combining a “research presence” with the “virtual operation capability,” is essential. Mutual understanding must embrace the precept of no disruption to first responders in actual response and recovery efforts. Consensus should be reached in identifying measurable outcomes for the research. The collaborative effort opens a groundbreaking area for consideration of study in crisis response and management. It would shed new light on an underexplored, critical area of emergency management and has the potential t...
Rapid damage assessment is one of the core tasks that response organizations perform at the onset... more Rapid damage assessment is one of the core tasks that response organizations perform at the onset of a disaster to understand the scale of damage to infrastructures such as roads, bridges, and buildings. This work analyzes the usefulness of social media imagery content to perform rapid damage assessment during a real-world disaster. An automatic image processing system, which was activated in collaboration with a volunteer response organization, processed ~280K images to understand the extent of damage caused by the disaster. The system achieved an accuracy of 76% computed based on the feedback received from the domain experts who analyzed ~29K system-processed images during the disaster. An extensive error analysis reveals several insights and challenges faced by the system, which are vital for the research community to advance this line of research.
Rapid damage assessment is one of the core tasks that response organizations perform at the onset... more Rapid damage assessment is one of the core tasks that response organizations perform at the onset of a disaster to understand the scale of damage to infrastructures such as roads, bridges, and buildings. This work analyzes the usefulness of social media imagery content to perform rapid damage assessment during a real-world disaster. An automatic image processing system, which was activated in collaboration with a volunteer response organization, processed ⇠280K images to understand the extent of damage caused by the disaster. The system achieved an accuracy of 76% computed based on the feedback received from the domain experts who analyzed ⇠29K system-processed images during the disaster. An extensive error analysis reveals several insights and challenges faced by the system, which are vital for the research community to advance this line of research.
Proceedings of the AAAI Conference on Artificial Intelligence
Formal response organizations perform rapid damage assessments after natural and human-induced di... more Formal response organizations perform rapid damage assessments after natural and human-induced disasters to measure the extent of damage to infrastructures such as roads, bridges, and buildings. This time-critical task, when performed using traditional approaches such as experts surveying the disaster areas, poses serious challenges and delays response. This paper presents an AI-based system that leverages citizen science to collect damage images reported on social media and perform rapid damage assessment in real-time. Several image processing models in the system tackle non-trivial challenges posed by social media as a data source, such as high-volume of redundant and irrelevant content. The system determines the severity of damage using a state-of-the-art computer vision model. Together with a response organization in the US, we deployed the system to identify damage reports during a major real-world disaster. We observe that almost 42% of the images are unique, 28% relevant, and...
During large-scale disasters it is not uncommon for Public Safety Answering Points (e.g., 9-1-1) ... more During large-scale disasters it is not uncommon for Public Safety Answering Points (e.g., 9-1-1) to encounter service disruptions or become overloaded due to call volume. As observed in the two past United States hurricane seasons, citizens are increasingly turning to social media whether as a consequence of their inability to reach 9-1-1, or as a preferential means of communications. Relying on past research that has examined social media use in disasters, combined with the practical knowledge of the first-hand disaster response experiences, this paper develops a knowledge-driven framework containing parameters useful in identifying patterns of shared information on social media when citizens need help. This effort explores the feasibility of determining differences, similarities, common themes, and time-specific discoveries of social media calls for help associated with hurricane evacuations. At a future date, validation of this framework will be demonstrated using datasets from m...
This abstract highlights research challenges to improving effectiveness of integrating informatio... more This abstract highlights research challenges to improving effectiveness of integrating information and communication technologies during emergencies. Proposed as a research focus is the integration of proven virtual activation processes with an unobtrusive research presence. This positions the research presence during a real-time emergency to glean previously unknown information/rationales on how decision-makers decide and take action. Establishing a collaborative partnership by combining a “research presence” with the “virtual operation capability,” is essential. Mutual understanding must embrace the precept of no disruption to first responders in actual response and recovery efforts. Consensus should be reached in identifying measurable outcomes for the research. The collaborative effort opens a groundbreaking area for consideration of study in crisis response and management. It would shed new light on an underexplored, critical area of emergency management and has the potential t...
Rapid damage assessment is one of the core tasks that response organizations perform at the onset... more Rapid damage assessment is one of the core tasks that response organizations perform at the onset of a disaster to understand the scale of damage to infrastructures such as roads, bridges, and buildings. This work analyzes the usefulness of social media imagery content to perform rapid damage assessment during a real-world disaster. An automatic image processing system, which was activated in collaboration with a volunteer response organization, processed ~280K images to understand the extent of damage caused by the disaster. The system achieved an accuracy of 76% computed based on the feedback received from the domain experts who analyzed ~29K system-processed images during the disaster. An extensive error analysis reveals several insights and challenges faced by the system, which are vital for the research community to advance this line of research.
Rapid damage assessment is one of the core tasks that response organizations perform at the onset... more Rapid damage assessment is one of the core tasks that response organizations perform at the onset of a disaster to understand the scale of damage to infrastructures such as roads, bridges, and buildings. This work analyzes the usefulness of social media imagery content to perform rapid damage assessment during a real-world disaster. An automatic image processing system, which was activated in collaboration with a volunteer response organization, processed ⇠280K images to understand the extent of damage caused by the disaster. The system achieved an accuracy of 76% computed based on the feedback received from the domain experts who analyzed ⇠29K system-processed images during the disaster. An extensive error analysis reveals several insights and challenges faced by the system, which are vital for the research community to advance this line of research.
Uploads
Papers by Steve Peterson