Mathematical morphology applied to shadows and clouds detection in high resolution images

• Autor(a) principal: Statella, Thiago
• Data de Publicação: 2008
• Outros Autores: Silva, Erivaldo Antônio da
• Tipo de documento: Artigo
• Idioma: por
• Título da fonte: Boletim de Ciências Geodésicas
• Texto Completo: https://revistas.ufpr.br/bcg/article/view/11819
• topic: Morfologia Matemática; Detecção de Sombras; Detecção de Nuvens; Imagem de Alta Resolução; Mathematical Morphology; Shadows detection; Cloud Detection; High Resolution Imagery

The spatial resolution improvement of orbital sensors has broadened considerablythe applicability of their images in solving urban areas problems. But as the spatialresolution improves, the shadows become even a more serious problem especiallywhen detailed information (under the shadows) is required. Besides those shadowscaused by buildings and houses, clouds projected shadows are likely to occur. Inthis case there is information occlusion by the cloud in association with lowillumination and contrast areas caused by the cloud shadow on the ground. Thus,it’s important to use efficient methods to detect shadows and clouds areas in digitalimages taking in count that these areas care for especial processing. This paperproposes the application of Mathematical Morphology (MM) in shadow and cloudsdetection. Two parts of a panchromatic QuickBird image of Cuiabá-MT urban areawere used. The proposed method takes advantage of the fact that shadows (lowintensity – dark areas) and clouds (high intensity – bright areas) represent thebottom and top, respectively, of the image as it is thought to be a topographicsurface. This characteristic allowed MM area opening and closing operations to beapplied to reduce or eliminate the bottom and top of the topographic surface.