.png){kind=icon}
.png){kind=icon}
Return
Unsupervised learning-based long-term superpixel tracking
.png){kind=icon}
OA
AI
DOI：10.1016/j.imavis.2019.06.011.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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. (C) 2019 Elsevier B.V. All rights reserved.
Keywords:
Superpixel matching
Unsupervised learning
Superpixel tracking
Multi-step integration
Random forests
Forward-backward consistency
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
4.2
Papers:
4.0K
Citations:
6.7K
Organization
View more organizations