HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

Unsupervised learning-based long-term superpixel tracking

Abstract : 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.
Complete list of metadata

Contributor : Pierre-Henri Conze Connect in order to contact the contributor
Submitted on : Saturday, July 20, 2019 - 11:28:40 PM
Last modification on : Monday, April 4, 2022 - 9:28:20 AM

Links full text



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



Record views