科研之友
微信
新浪微博
Facebook
分享链接
摘要
The extraction, refinement and verification of intact and damaged infrastructure are important issues for the management of civil crises, e. g., caused by flooding or earthquakes. In this paper, the development of a system for the automated detection of roads, their geometric and semantic refinement as well as classification into different states of accessibility from multi-sensorial imagery is presented. The system is intended to supply information being required for the coordination of rescue teams and the implementation of emergency actions. It is the result of long-term research on different aspects of road extraction, which has been extended and adapted in the context of the bundle project DeSecure to build up a framework providing all relevant information regarding the extent and impact of crises scenarios within shortest time-frames. The results of classification system show the improvement of the fast interpretation of road networks after natural disasters using automatic approaches.
- 出版日期2010
