ADS-40數值航照影像中雲蔽區多重階層式資訊還原模式之研究－以濁水溪農業區為例

Abstract

Generally, atmospheric haze has important ramifications in remote sensing data. In this work, the aerial photographs of ADS-40 image at Choshui River agricultural areas are divided into 4 regions which are thick clouds region, haze region, shadow region and normal region through a hybrid region detect model of ATSA (Automated Threshold Selection Algorithm) and MLC (Maximum Likelihood Classification) methods, respectively. In addition, for the different regions of atmospheric haze effects, this work will also develop an efficient hierarchical algorithm for mixed modes which are correct and verifies the image properly. These modes are as below: 1. Mosaic thick cloud region: prophase images provides new information for thick cloud region; 2. Restore haze region: spectral information was invested by DCPA (Dark Channel Prior Algorithm) method, and 3. Enhance shadow region: the Retinex algorithms were applied to enhance these shadow regions. After that, this work check the original and processed image quality assessments of this research processing with RMSE (Root Mean Square Error), PSNR (Peak Signal to Noise Ratio) and SSIM (Structure Similarity Image Measurement) indicators, respectively. It shows that the processed image with this hierarchical mixed mode of this study is better than those of the original image of ADS-40 aerial photographs. The index of RMSE reduced from 88.02 (original image) to 17.63 (processed image), PSNR index value improved from 9.24 (original image) to 23.20 (processed image) and SSIM value upgraded from 0.74 (original image) to 0.97 (processed image), respectively. Finally, in this study, the outcomes showed that the hierarchical mixed mode for image processing procedure exceeds that of the original image of agricultural areas evaluation from ADS-40 image.