Cluster-based point set saliency

Flora Ponjou Tasse, Jiri Kosinka, Neil Dodgson

OnderzoeksoutputAcademicpeer review

40 Citaten (Scopus)


We propose a cluster-based approach to point set saliency detection, a challenge since point sets lack topological information. A point set is first decomposed into small clusters, using fuzzy clustering. We evaluate cluster uniqueness and spatial distribution of each cluster and combine these values into a cluster saliency function. Finally, the probabilities of points belonging to each cluster are used to assign a saliency to each point. Our approach detects fine-scale salient features and uninteresting regions consistently have lower saliency values. We evaluate the proposed saliency model by testing our saliency-based keypoint detection against a 3D interest point detection benchmark. The evaluation shows that our method achieves a good balance between false positive and false negative error rates, without using any topological information.
Originele taal-2English
Titel2015 IEEE International Conference on Computer Vision (ICCV)
Aantal pagina's9
ISBN van elektronische versie978-1-4673-8391-2
StatusPublished - 2015
Extern gepubliceerdJa
Evenement2015 IEEE International Conference on Computer Vision (ICCV) - Los Alamitos, United States
Duur: 7-dec.-201513-dec.-2015


Conference2015 IEEE International Conference on Computer Vision (ICCV)
Land/RegioUnited States
StadLos Alamitos

Citeer dit