A fast method for computing principal curvatures from range images

Andrew Tristan Spek, Wai Ho Li, Thomas William Drummond

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

4 Citations (Scopus)


Estimation of surface curvature from range data is important for a range of tasks in computer vision and robotics, object segmentation, object recognition and robotic grasping estimation. This work presents a fast method of robustly computing accurate metric principal curvature values from noisy point clouds which was implemented on GPU. In contrast to existing readily available solutions which first differentiate the surface to estimate surface normals and then differentiate these to obtain curvature, amplifying noise, our method iteratively fits parabolic quadric surface patches to the data. Additionally previous methods with a similar formulation use less robust techniques less applicable to a high noise sensor. We demonstrate that our method is fast and provides better curvature estimates than existing techniques. In particular we compare our method to several alternatives to demonstrate the improvement.

Original languageEnglish
Title of host publicationAustralasian Conference on Robotics and Automation, ACRA 2015
Subtitle of host publication2-4 December 2015; Canberra, Australia
EditorsRobert Mahony, Jonghyuk Kim, Hongdong Li
Place of PublicationCanberra ACT Australia
PublisherAustralian Robotics and Automation Association (ARAA)
Number of pages9
ISBN (Electronic)9780980740462
ISBN (Print)9781510819269
Publication statusPublished - 2015
EventAustralasian Conference on Robotics and Automation 2015 - Australian National University (ANU), Canberra, Australia
Duration: 2 Dec 20154 Dec 2015


ConferenceAustralasian Conference on Robotics and Automation 2015
Abbreviated titleACRA 2015
Internet address

Cite this