Constrained Superpixel Tracking.

IEEE Transactions on Cybernetics(2018)

引用 44|浏览56
暂无评分
摘要
In this paper, we propose a constrained graph labeling algorithm for visual tracking where nodes denote superpixels and edges encode the underlying spatial, temporal, and appearance fitness constraints. First, the spatial smoothness constraint, based on a transductive learning method, is enforced to leverage the latent manifold structure in feature space by investigating unlabeled superpixels in t...
更多
查看译文
关键词
Target tracking,Training,Labeling,Adaptation models,Manifolds,Noise measurement,Visualization
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要