Identification of Damaged Building Regions from High Resolution Images using Superpixel-based Gradient and Autocorrelation Analysis

An efficient and accurate identification of damaged buildings after earthquakes is critical for ensuring a quick response and efficient rescue operations. Considering the time pressure during disaster emergency response and the convenience of practical application, a new approach for identifying areas with damaged buildings is proposed in this study. The approach is validated on high–resolution images from areas impacted by the Haiti earthquake. The approach consists of the following steps. (i), the simple linear iterative clustering method is improved to segment the images into high-quality superpixels by combining both color and texture information; (ii) the characteristics of the damage in the area within the cluster and the difference between pre- and post-earthquake images are obtained at superpixel level using the Sobel gradient; and (iii) local indicators from the spatial association analysis are used to extract the result of the gradient clustering using the synthetic- damage index calculated by an improved relief algorithm; and (iv) vegetation and shadows are masked out to identify the damaged buildings. This framework achieved an overall accuracy of ∼90% in terms of visual interpretation, with precision and recall of ∼85% and ∼90%, respectively. Inaccuracies mainly occur around the boundaries of the damaged building regions. It is evaluated that the proposed framework is more convenient compared to other supervised and unsupervised methods. The successful application in different scenes demonstrates that the proposed framework has the ability to rapidly and accurately identify regions with damaged buildings, which is beneficial for post-disaster emergency assessment.