Land Cover Classification Using RapidEye Data to Estimate the Amount of Disaster Waste

Abstract

To draw reconstruction plans following great earthquakes, it is necessary to quickly estimate the amount of disaster waste, with the use of remote sensing data affecting all subsequent processing. However, the digital number (DN) of each pixel represents the average land cover conditions, i.e., the information provided by a pixel should be represented as a one-pixel mixed-class ("mixel") instead of a one-pixel one-class. In a previous study, we proposed a method for unmixing mixels using the DNs and texture features from THEOS data. In this paper, we propose a method of land cover classification using RapidEye data, whose effectiveness was confirmed by our results.

Estimating the amount of disaster waste using RapidEye data

“…Figure 1 shows a flowchart of the proposed method. The methods for land cover classification and estimating disaster building numbers were previously proposed in Refs [3][4][5]. In this letter, we propose a method for estimating the amount of disaster waste using the disaster building number estimation results.…”

“…The land cover classification method proposed in Ref. [3] consists of five steps, shown in the blue box in Fig. 1.…”

“…However, the ground resolution of THEOS data was not sufficiently improved to detect collapsed buildings. Therefore, with RapidEye data, which has a higher ground resolution than THEOS data, we proposed methods to extract detailed information buried in the mixel and classify land cover information [3]. Moreover, we proposed methods of estimating disaster building domain and disaster building numbers [4,5].…”

Estimation of the disaster building domain using RapidEye data to estimate the amount of disaster waste

“…In this paper, the method of land cover classification that had applied to the post‐earthquake data described in Ref. was applied also to the pre‐earthquake data.…”

“…THEOS panchromatic data with 2‐m ground resolution also exists, but since it is a single‐band information, it is difficult to analyze the difference in the reflective characteristic of land cover conditions. Therefore, we additionally proposed a method of land cover classification using RapidEye data, which has a higher ground resolution than THEOS data . The ground resolution of RapidEye data was improved to 2‐m from 6.5‐m by the proposed method.…”