| Open achives Hal IMT Atlantique |
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.
https://hal-imt-atlantique.archives-ouvertes.fr/hal-02189986
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, October 11, 2021 - 2:23:59 PM
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, October 11, 2021 - 2:23:59 PM
Links full text
