Precise Euclidean distance transforms in 3D from voxel coverage representation
2015 (English)In: Pattern Recognition Letters, ISSN 0167-8655, E-ISSN 1872-7344, Vol. 65, 184-191 p.Article in journal (Refereed) Published
Distance transforms (DTs) are, usually, defined on a binary image as a mapping from each background element to the distance between its centre and the centre of the closest object element. However, due to discretization effects, such DTs have limited precision, including reduced rotational and translational invariance. We show in this paper that a significant improvement in performance of Euclidean DTs can be achieved if voxel coverage values are utilized and the position of an object boundary is estimated with sub-voxel precision. We propose two algorithms of linear time complexity for estimating Euclidean DT with sub-voxel precision. The evaluation confirms that both algorithms provide 4-14 times increased accuracy compared to what is achievable from a binary object representation.
Place, publisher, year, edition, pages
2015. Vol. 65, 184-191 p.
Distance transform, Precision, Coverage representation, Vector propagation DT algorithm, Sub-voxel accuracy
Computer Vision and Robotics (Autonomous Systems)
Research subject Computerized Image Processing
IdentifiersURN: urn:nbn:se:uu:diva-265668DOI: 10.1016/j.patrec.2015.07.035ISI: 000362187000027OAI: oai:DiVA.org:uu-265668DiVA: diva2:867014