This paper described a fast and automatic method for segmenting fiducial marks in an image taken by a metric camera. These marks could be at the four corners, four middle sides, or even inside (for those réseau marks) of an image. The segmentation was realized by using attribute-based mathematical morphology techniques. The attributes that we used in the morphology processing step were the area, aspect ratio and orientation of the best fitted ellipse of an object. The algorithm took about 1 second in the automatic segmentation stage. The positions of these automaticly segmented fiducial marks were then refined to sub-pixel accuracy. Dozens of real images with different shapes of fiducial marks were tested and reliable results were obtained. Comparisons were also made about the accuracy using our method and previously published methods.
Fiducial marks segmentation, mathematical morphology, sub-pixel accuracy, shape attributes, interior orientation, aerial images, digital photogrammetry.
International Workshop on Image Analysis and Information Fusion (H. Pan, M. Brooks, D. McMichael, and G. Newsam, editors), pp.43-49, 6-8 November 1997, Adelaide, Australia