A Visual Analytics Multimedia Mobile System for Emergency Response

Abstract

Abstract-We present a novel visual analytics system and multimedia enabled mobile application that allows emergency management (EM) personnel access to timely and relevant disaster situation information. The system is able to semantically integrate text-based emergency management disaster situation reports with related disaster imagery taken in the field by EM responders and community residents. In addition, through an intuitive and seamless Apple iPad application, users are able to interact with the system in diverse places and conditions and thus provide a more effective response. The system is demonstrated via its iPad application which aims at providing relevant and actionable information.Keywords-disaster situations; mobile computing; iPad applications I. MOTIVATION Natural and man-made disasters can cause significant damage both in terms of property loss and human lives; which is why preparedness and rapid response activities are performed by highly trained emergency managers around the world. During a disaster event, Emergency Management Offices execute their disaster response plans by integrating jurisdictional resources, coordinating multi-agency response, and establishing management processes among the various government, non-government, and private sector entities involved in recovery.However, command personnel commonly rely on situation reports that only provide a textual description of the disaster scenario, which makes the task of assessing the disaster situation difficult since often these textual reports are unable to describe the situation at the desired level of detail. The work of emergency management (EM) personnel could be enhanced if they could analyze situation reports along with images and videos taken at the disaster scene by emergency first responders and community residents as well. A system able to combine both textual reports and multimedia data taken at the disaster scene would add potentially new insights to the command personnel in assessing the situation in the field. Furthermore, EM responders and command personnel would need to be able to access reports and multimedia information at any place at any time, a requirement that prompts mobility as a must-have feature for such system. This demo paper presents a system that integrates situation reports and disaster-related multimedia data and provides EM personnel with an iPad application that conveys all the information via a unified and intuitive graphical interface. Moreover, since the front-end interface of the system is an iPad application, EM personnel can take advantage of the mobility offered by iPads and thus be able to interact with the system both at command centers and at the actual disaster area. II. SYSTEM ARCHITECTUREThe system follows a three-tier architecture. The front-end tier consists of an iPad application; the logic tier provides a RESTful, JSP-based API; and the data tier runs a database server.The database stores all the data related to the situation reports and related multimedia data as well as user-account ...

Disaster Image Filtering and Summarization Based on Multi-layered Affinity Propagation

“…In our previous work [2], [3], we presented a hierarchical disaster image categorization framework, which classifies images in a supervised manner. In this paper, we focused on the unsupervised filtering and summarization of disaster images collected from Flickr [1].…”

MADIS: A Multimedia-Aided Disaster Information Integration System for Emergency Management

“…In this paper, built on our previous work [3], [4], we have designed and developed a Multimedia-Aided Disaster information Integration System (MADIS) that semantically associates situation reports with disaster-related multimedia data and is implemented within an iPad-specific application that conveys all such information via a unified and intuitive graphical interface. The mobility of the iPad device provides the EM personnel with free and fast interaction in communicating between both the command centers and the actual disaster sites.…”

Exploring Hidden Coherent Feature Groups and Temporal Semantics for Multimedia Big Data Analysis

“…In this paper, built on our previous work [14,203], we have designed and developed a Multimedia-Aided Disaster information Integration System (MADIS) that semantically associates situation reports with disaster-related multimedia data and is implemented within an iPad-specific application that conveys all such information via a unified and intuitive graphical interface [181]. The mobility of the iPad device provides the EM personnel with free and fast interaction in communicating between both the command centers and the actual disaster sites.…”

“…In our previous work [14,203], we presented a hierarchical disaster image categorization framework, which classifies images in a supervised manner. In this paper, we focused on the unsupervised filtering and summarization of disaster images collected from Flickr [198].…”