Cluster-Based Point Set Saliency

Flora Ponjou Tasse, Jiri Kosinka, Neil Dodgson; Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2015, pp. 163-171


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.

Related Material

author = {Tasse, Flora Ponjou and Kosinka, Jiri and Dodgson, Neil},
title = {Cluster-Based Point Set Saliency},
booktitle = {Proceedings of the IEEE International Conference on Computer Vision (ICCV)},
month = {December},
year = {2015}