Alive Fishes Species Characterization from Video Sequences
Alive Fishes Species Characterization from Video Sequences
复制标题
视频序列中的活鱼物种表征
DOI：
10.1007/3-540-70659-3_72
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
P. Courtellemont
中科院分区：
文献类型：
--
作者：
D. Semani;C. Saint;C. Frélicot;T. Bouwmans;P. Courtellemont
本文提出了一种适合于流域鱼类演化特征描述的方法。它是基于从一个固定的摄像机获得的视频序列的分析。分析从水环境中获取的自然场景的主要困难之一是光照的可变性。这影响了整个过程的每一个阶段。我们建议使每项任务更加强大。特别是，我们建议使用聚类方法，允许提供物种参数估计，不太敏感的离群值。
This article presents a method suitable for the characterization of fishes evolving in a basin. It is based on the analysis of video sequences obtained from a fixed camera. One of the main difficulties of analyzing natural scenes acquired from an aquatic environment is the variability of illumination. This disturbs every phase of the whole process. We propose to make each task more robust. In particular, we propose to use a clustering method allowing to provide species parameters estimates that are less sensitive to outliers.