.png){kind=icon}
返回
Component trees for image sequences and streams
.png){kind=icon}
OA
AI
DOI：10.1016/j.patrec.2019.11.038.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Morphological hierarchies now form a well-established framework for (still) image modeling and processing. However, their extension to time-related data remains largely unexplored. In this paper, we address such a topic and show how to analyze image sequences with tree-based representations. To do so, we distinguish between three kinds of models, namely spatial, temporal and spatial-temporal hierarchies. For each of them, we review different strategies to build the hierarchy from an image sequence. We also propose some algorithms to update such trees when new images are appended to the series and we compared the time complexity with tree building from scratch. We illustrate our findings with the max and min-tree structures built on grayscale data provided by Satellite Image Time Series that are gathering a growing interest in Earth Observation. Besides, we provide a comparative study for different hierarchies with classification experiments. (C) 2019 Elsevier B.V. All rights reserved.
Keyword:
Hierarchical representation
Max-tree
Satellite image time series
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.3
论文数:
7.9K
被引数:
1.6W
机构
引用论文
.png){kind=icon}
分享收藏分享收藏分享收藏
查看更多内容