论文部分内容阅读
地震灾害倒塌房屋的识别是地震灾害损失评价的重要环节,也是判断地震强度的指标之一.5.12汶川大地震发生后,中欧地震灾害评估项目组使用自动识别技术处理0.5m分辨率的ADS40航空遥感数据,需要克服航空遥感数据中未倒塌混凝土桥梁、滑坡体滚石与倒塌房屋反射光谱的相似性.经过多次实验改进后的技术,一次性识别的倒塌房屋面积覆盖率优于95%.介绍了这次实验过程和结果,实验表明,该方法也可以用于其他灾害造成的倒塌房屋的自动识别.
Earthquake disaster Identification of collapsed houses is an important link in the evaluation of earthquake disaster losses and an indicator of earthquake intensity 5. After the occurrence of the Wenchuan Earthquake, the Central European Earthquake Disaster Assessment project team used automatic identification technology to deal with ADS40 airborne remote sensing with a resolution of 0.5m Data, we need to overcome the similarities between the reflection spectra of unsinkable concrete bridges, landslide bodies and collapsed houses in aerial remote sensing data.After many experiments and improvements, the coverage of collapsed houses with one-time identification is better than 95% The experimental process and the results of experiments show that the method can also be used for automatic identification of collapsed houses caused by other disasters.