Advanced search
Start date
Betweenand
Related content
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

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

Full text
Author(s):
Azevedo, Samara [1] ; Silva, Erivaldo [2] ; Colnago, Marilaine [3] ; Negri, Rogerio [4] ; Casaca, Wallace [3]
Total Authors: 5
Affiliation:
[1] Univ Fed Itajuba, Nat Resources Inst, Geomat, Itajuba, MG - Brazil
[2] Sao Paulo State Univ, Dept Cartog, Sao Paulo - Brazil
[3] Sao Paulo State Univ, Dept Energy Engn, Sao Paulo - Brazil
[4] Sao Paulo State Univ, Dept Environm Engn, Sao Jose Dos Campos - Brazil
Total Affiliations: 4
Document type: Journal article
Source: JOURNAL OF APPLIED REMOTE SENSING; v. 13, n. 3 AUG 9 2019.
Web of Science Citations: 0
Abstract

The presence of shadows in remote sensing images leads to misinterpretation of objects and a wrong discrimination of the targets of interest, therefore, limiting the use of several imaging applications. An automatic area-based approach for shadow detection is proposed, which combines spatial and spectral features into a unified and flexible approach. Potential shadow-pixels candidates are identified using morphological-based operators, in particular, black-top-hat transformations as well as area injunction strategies as computed by the well-established normalized saturation-value difference index. The obtained output is a shadow mask, refined in the last step of our method in order to reduce misclassified pixels. Experiments over a large dataset formed by more than 200 scenes of very high-resolution images covering the metropolitan urban area of Sao Paulo city are performed, where the images are collected from the WorldView-2 (WV-2) and Pleiades-1B (PL-1B) sensors. As verified by an extensive battery of tests, the proposed method provides a good level of discrimination between shadow and non-shadow pixels, with an overall accuracy up to 94.2%, for WV-2, and 90.84%, for PL-1B. Comparative results also attested that the designed approach is very competitive against representative state-of-the-art methods and it can be used for further shadow removal-dependent applications. (C) 2019 Society of Photo-Optical Instrumentation Engineers (SPIE) (AU)

FAPESP's process: 13/25257-4 - AUTOMATIC DETECTION AND REMOVAL OF SHADOWS OF ITS EFFECTS ON SPATIAL HIGH RESOLUTION DIGITAL IMAGES
Grantee:Samara Calçado de Azevedo
Support Opportunities: Scholarships in Brazil - Doctorate