The aim of the project is to use current and highly detailed three-dimensional city models to automatically simulate and represent the damage potential of explosive devices in the urban area.
Recent international incidents suggest an increasing threat-level originating from improvised explosive devices. On the one hand, this is caused by the easy accessibility of construction plans on the internet, on the other hand the fairly easy access to raw materials required to build a simple explosive device. This easy availability is complemented with new levels of information which are available to potential attackers. Online maps make it possible to remotely select locations to maximize damage and visibility. Online communication channels allow concerted attacks at multiple locations, taking into account reaction times of relief units and the general public at mass events.
Once an increased threat-level for a specific city is imminent, local disaster management units face three fundamental challenges:
- Precaution: how to realistically simulate and train for a specific incident? What actions need to be taken at specific locations (evacuation, blocking, guarding, etc.).
- Prevention: how to prevent a threat, or minimize its impact? Which locations are especially vulnerable and need protection?
- Handling: is an actual threat accessible? How to evacuate people? What is the actual danger radius?
A proper reaction needs to be based on information which is recent, detailed, complete and easily accessible. More precisely, in order to perform a proper explosion simulation at arbitrary places, a complete city should be available as a semantic 3D model, at an accuracy of few centimeters. The 3D model should be fairly recent to resemble the current state of buildings, and include meta-information like surface material, vegetation and window locations. This is far beyond the standard information content of traditional GIS-databases. Our project goal is to generate exactly this information from aerial images. Based on an automatically generated 3D city model we perform a semantic segmentation of the image data to automatically detect object classes like roofs, windows, vegetation, etc. We will fuse the geometric content and semantic content into a common representation and perform a detailed simulation of explosive expansion in the model.
Finally, we embed the 3D map and the simulation results into a highly efficient visualization system to visualize even terabytes of data quickly and fluently on consumer laptops. For the first time, a photorealistic and intuitive visualization of threat scenarios will be available for training, planning and even rapid reaction on-site.
Prof. Dr. Horst Bischof
Institut for Computer Graphics and Vision
Graz University of Technology
Institut for Sociology, University Graz (SOZ)
Meixner Surveying (Meixner)
Bionic Surface Technologies (Bionic)
Professional Fire Brigade and Civil Protection Graz (BFG)
Security management u. Civil protection, City of Graz (SG) BMLVS, Demining Service (BMLVS)