Unsupervised learning-based long-term superpixel tracking - IMT Atlantique Access content directly
Journal Articles Image and Vision Computing Year : 2019

Unsupervised learning-based long-term superpixel tracking


Finding correspondences between structural entities decomposing images is of high interest for computer vision applications. In particular, we analyze how to accurately track superpixels - visual primitives generated by aggregating adjacent pixels sharing similar characteristics - over extended time periods relying on unsupervised learning and temporal integration. A two-step video processing pipeline dedicated to long-term superpixel tracking is proposed. First, unsupervised learning-based superpixel matching provides correspondences between consecutive and distant frames using new context-rich features extended from greyscale to multi-channel and forward-backward consistency constraints. Resulting elementary matches are then combined along multi-step paths running through the whole sequence with various inter-frame distances. This produces a large set of candidate long-term superpixel pairings upon which majority voting is performed. Video object tracking experiments demonstrate the accuracy of our elementary estimator against state-of-the-art methods and proves the ability of multi-step integration to provide accurate long-term superpixel matches compared to usual direct and sequential integration.
Fichier principal
Vignette du fichier
S0262885619300940.pdf (22.2 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-02189986 , version 1 (20-07-2022)


Attribution - NonCommercial



Pierre-Henri Conze, Florian Tilquin, Mathieu Lamard, Fabrice Heitz, Gwénolé Quellec. Unsupervised learning-based long-term superpixel tracking. Image and Vision Computing, 2019, 89, pp.289-301. ⟨10.1016/j.imavis.2019.06.011⟩. ⟨hal-02189986⟩
64 View
25 Download



Gmail Facebook Twitter LinkedIn More