Abstract : This paper presents a clustering-based color segmentation method where the desired object is focused on. As classical methods suffer from a lack of robustness, salient colors appearing in the object are used to intuitively tune the algorithm. These salient colors are extracted according to a psychovisual scheme and a peak-finding step. Results on various test sequences, covering a representative set of outdoor real videos, show the improvement when compared to a simple implementation of the same K-means oriented segmentation algorithm with ad hoc parameter setting strategy and with the well-known mean-shift algorithm.
https://hal-ujm.archives-ouvertes.fr/ujm-00322113 Contributor : Hubert KonikConnect in order to contact the contributor Submitted on : Tuesday, September 16, 2008 - 4:42:50 PM Last modification on : Saturday, June 25, 2022 - 10:49:56 AM
Hubert Konik, Jérôme da Rugna. A Robust Approach to Segment Desired Object Based on Salient Colors. EURASIP Journal on Image and Video Processing, Springer, 2007, 2008, Article ID 489202, 11 p. ⟨10.1155/2008/489202⟩. ⟨ujm-00322113⟩