Periodic Reporting for period 1 - ADDABU (Automated detection of damage to buildings)
Okres sprawozdawczy: 2017-09-01 do 2018-08-31
ADDABU originates from ERC Project VarCity. VarCity aims at generating 3D city models that include a detailed semantic understanding of the city. The VarCity project produced methods to automatically parse facades into such structures, and to select the best way to describe their textures among a set of alternatives. These findings and technologies are used to offer automation in claims management of building damages.
Hail and storm damages represent the most often occurring cases for building insurance companies. Currently, the damage is estimated by an insurance expert, visiting the damaged building and drafting a report. Researchers at the Computer Vision Lab at ETH Zurich joined forces with business and sales people to reduce such costs via automated image analysis. The idea is that the insurers’ clients upload photos of the damages, which will then be analyzed automatically by computer. This involves the aforementioned computer vision technologies to recognize the damaged building structures and to analyze the corresponding textures as to assess the extent of the damage and the estimated costs for its repair. Cutting costs is not the only consideration, as the fast assessment of damages improves customer satisfaction and prevents the occurrence of additional damages because of a delayed repair (like water leaking before repair).
This Proof-of-Concept project did focus on a thorough investigation of the freedom to operate, a exploration of the market and the development of a corporate identity and graphical house style for the envisioned spinoff Casalva.
Our key findings support a freedom to operate, since many publications in this field are available and no direct patents exist which could limit the progress. Our intensive research and talks with insurance companies confirmed the old and slow processes with none or only minor process automation and predictive analysis from historical data. Our new process is of high interest, however, a few major hurdles still need to be taken.
Hail and storm damages represent the most often occurring cases for building insurance companies. Currently, the damage is estimated by an insurance expert, visiting the damaged building and drafting a report. Researchers at the Computer Vision Lab at ETH Zurich joined forces with business and sales people to reduce such costs via automated image analysis. The idea is that the insurers’ clients upload photos of the damages, which will then be analyzed automatically by computer. This involves the aforementioned computer vision technologies to recognize the damaged building structures and to analyze the corresponding textures as to assess the extent of the damage and the estimated costs for its repair. Cutting costs is not the only consideration, as the fast assessment of damages improves customer satisfaction and prevents the occurrence of additional damages because of a delayed repair (like water leaking before repair).
This Proof-of-Concept project did focus on a thorough investigation of the freedom to operate, a exploration of the market and the development of a corporate identity and graphical house style for the envisioned spinoff Casalva.
Our key findings support a freedom to operate, since many publications in this field are available and no direct patents exist which could limit the progress. Our intensive research and talks with insurance companies confirmed the old and slow processes with none or only minor process automation and predictive analysis from historical data. Our new process is of high interest, however, a few major hurdles still need to be taken.