An Automatic Shadow Detection Method for VHR Remote Sensing Orthoimagery

Abstract

Abstract:The application potential of very high resolution (VHR) remote sensing imagery has been boosted by recent developments in the data acquisition and processing ability of aerial photogrammetry. However, shadows in images contribute to problems such as incomplete spectral information, lower intensity brightness, and fuzzy boundaries, which seriously affect the efficiency of the image interpretation. In this paper, to address these issues, a simple and automatic method of shadow detection is presented. The proposed method combines the advantages of the property-based and geometric-based methods to automatically detect the shadowed areas in VHR imagery. A geometric model of the scene and the solar position are used to delineate the shadowed and non-shadowed areas in the VHR image. A matting method is then applied to the image to refine the shadow mask. Different types of shadowed aerial orthoimages were used to verify the effectiveness of the proposed shadow detection method, and the results were compared with the results obtained by two state-of-the-art methods. The overall accuracy of the proposed method on the three tests was around 90%, confirming the effectiveness and robustness of the new method for detecting fine shadows, without any human input. The proposed method also performs better in detecting shadows in areas with water than the other two methods.

A Mixed Property-Based Automatic Shadow Detection Approach for VHR Multispectral Remote Sensing Images

“…The model-based methods require prior knowledge about the scene, the sun, and sensors, such as the geometry of the scene, solar elevation and azimuth, the altitude and acquisition parameters of sensors, etc. [21][22][23][24]. Though the model-based technique usually presents desirable performance in shadow detection in specific applications, it is limited by the unavailability of some required prior information.…”

“…This SDI-based approach performs well in classifying shadow pixels from vegetation pixels, and achieves high shadow detection accuracies, except for the shortcomings of omitting some small shadow areas and misclassifying some dull red roof pixels as shadow pixels. Wang et al [23] proposed a simple and automatic shadow detection method. In this method, a shadow mask was achieved by delineating shadow and nonshadow regions in the VHR image with a geometric model of the scene and the solar position.…”

Extraction of Urban Objects in Cloud Shadows on the basis of Fusion of Airborne LiDAR and Hyperspectral Data

“…In recent years, many scholars have proposed a variety of shadow detection methods, such as model based and shadow attribute-based detection methods [41,[50][51][52][53]. Because the cloud shadow area is very large in our study, and the derivation of the shadow area is not the primary goal of this work, a simple shadow detection method based on area attribute filters was employed [50].…”

Shadow detection using object area-based and morphological filtering for very high-resolution satellite imagery of urban areas

“…4,6,22,23 Detecting shadows in VHR images is a challenging task and it remains an open problem for dense environments where the discrimination of the objects from the scene is very critical and difficult to be performed in practice, especially by nonsupervised paradigms. 4,12 A robust method should guarantee independency of the material reflectance and a low necessity of additional input data, being also capable of handling spectral features and contextual information simultaneously. Bearing this in mind, in this study, an automatic shadow detection method is presented.…”