.png){kind=icon}
.png){kind=icon}
Return
Automatic shadow detection in high-resolution multispectral remote sensing images
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compeleceng.2022.108557.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Shadows in high-resolution remote sensing satellite images distort both apparent shapes hues leading to lost features and difficult object analysis when processing these images. This negatively affects image color correction, recognition, classification, and urban reconstruction uses for these images. Although many shadow detection methods have been developed, there are still cases of missing detection of small shadows and misclassification of blue, green, and dark areas. We propose a novel logarithmic normalized mixed property-based shadow index (LNMPSI) for shadow detection in high resolution images using analysis of multispectral characteristics to improve on existing methods. Using color images from WorldView-3 and Gaofen-1, our method outperforms existing methods in both quantitative and qualitative terms. With good visual results and average accuracy in excess of 91%, our method is feasible, stable, and effective in detecting shadow regions and further reduces false positives caused by the loss of small details and misclassification of difficult areas.
Keywords:
Multispectral remote sensing images
Shadow detection
High-resolution
Shadow omission
Shadow commission
Journal
C
IF:
4.9
Papers:
6.7K
Citations:
1.3W