Region-based particle filter for video object segmentation
Document typeConference report
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Rights accessRestricted access - publisher's policy
We present a video object segmentation approach that extends the particle filter to a region-based image representation. Image partition is considered part of the particle filter measurement, which enriches the available information and leads to a re-formulation of the particle filter. The prediction step uses a co-clustering between the previous image object partition and a partition of the current one, which allows us to tackle the evolution of non-rigid structures. Particles are defined as unions of regions in the current image partition and their propagation is computed through a single co-clustering. The proposed technique is assessed on the SegTrack dataset, leading to satisfactory perceptual results and obtaining very competitive pixel error rates compared with the state-of-the-art methods.
CitationVaras, D.; Marques, F. Region-based particle filter for video object segmentation. A: IEEE Conference on Computer Vision and Pattern Recognition. "2014 IEEE Conference on Computer Vision and Pattern Recognition, 23-28 June 2014, Columbus, Ohio: proceedings". Columbus, Ohio: Institute of Electrical and Electronics Engineers (IEEE), 2014, p. 3470-3477.