When an earthquake occurs, promptly identifying the presence or absence of damage is crucial. This study developed a real-time building-damageextraction technique using ground-based imagery and evaluated its effectiveness. The technique applies the redness index (RI) (which was previously used in remote-sensing corrections for vegetation in arid regions) to identify “building damage” in those cases where buildings are partially or completely destroyed by earthquakes or tsunamis. To capture near-field and distant perspectives in the images, each image was divided into four quadrants (upper-left, upper-right, lower-left, and lowerright). The lower-left and lower-right quadrants were analyzed to assess the conditions on either side of a road in the near field using image recognition. Since the images contain latitudinal and longitudinal information, mapping the damage along the road can be automated by recording the route. Finally, a comparative analysis with other indices was conducted in order to evaluate RI’s superiority in damage mapping. The EMS-98 damage scale was used for damage assessment, classifying D5 (RI ≥ 0.08) as “building-collapse damage” and D0–D4 as “no building-collapse damage.” The average damage values for D5-classified buildings were significantly higher than others, thus demonstrating that RI provides practical and reliable results. Additionally, the study discussed comparisons with other indices and real-time evaluation methods. The authors sincerely hope this research contributes to life-saving efforts and deliveries of relief supplies in the aftermaths of earthquakes, ultimately saving many lives.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.