Localised Mixture Models in Region-Based Tracking

Localised Mixture Models in Region-Based Tracking
复制标题

基于区域的跟踪中的局部混合模型

DOI:
10.1007/978-3-642-03798-6_3
复制
发表时间:
2009
期刊:
影响因子:
--
通讯作者:
J. Weickert
J. Weickert
中科院分区:
--
文献类型:
--
作者:
C. Schmaltz;B. Rosenhahn;T. Brox;J. Weickert

文献摘要

参考文献

被引文献

相似文献

许多计算机视觉任务中的一个重要问题是将对象与其背景分离。一种常见的策略是估计对象和背景区域的外观模型。然而,如果外观在空间上变化,简单的同质模型通常是不准确的。高斯混合模型可以考虑多峰分布,但它们仍然忽略位置信息。在本文中,我们提出了局部混合模型(LMM),并通过自动将前景和背景划分为几个子区域,在基于模型的跟踪范围内评估了这一想法。与背景扣除方法相比,此方法还允许移动背景。刚性物体和 HumanEva-II 基准测试表明,新模型的跟踪显着稳定。
An important problem in many computer vision tasks is the separation of an object from its background. One common strategy is to estimate appearance models of the object and background region. However, if the appearance is spatially varying, simple homogeneous models are often inaccurate. Gaussian mixture models can take multimodal distributions into account, yet they still neglect the positional information. In this paper, we propose localised mixture models (LMMs) and evaluate this idea in the scope of model-based tracking by automatically partitioning the fore- and background into several subregions. In contrast to background subtraction methods, this approach also allows for moving backgrounds. Experiments with a rigid object and the HumanEva-II benchmark show that tracking is remarkably stabilised by the new model.
利用人工智能(AI)技术和电磁学的优化设计[I]-拓扑优化
DOI: --
发表时间: 2022
期刊: 電子情報通信学会誌
影响因子: --
作者:
青柳誠司,上田忠;高橋智一;鈴木昌人;伊藤亘輝,中村健二;五十嵐,伊藤
通讯作者: 五十嵐,伊藤
通过内部区域处理基于区域的运动捕捉中的自遮挡
DOI: --
发表时间: 2008
期刊: Articulated Motion and Deformable Objects
影响因子: --
作者:
Christian Schmaltz;B. Rosenhahn;T. Brox;J. Weickert;Lennart Wietzke;G. Sommer
通讯作者: G. Sommer