首页概率论
0


一个对象共生辅助分层模型的场景理解

An Object Co-occurrence Assisted Hierarchical Model for Scene Understanding
课程网址: http://videolectures.net/bmvc2012_li_scene_understanding/  
主讲教师: Xin Li
开课单位: 天普大学
开课时间: 2012-10-09
课程语种: 英语
中文简介:
层次方法已经被广泛地用于对象识别,这是场景理解的关键组成部分。然而,很少有现有作品能够在用于场景理解的单个相干框架内明确地对上下文信息(例如,对象共现)进行建模。为了实现这一目标,在本文中,我们提出了一种新颖的三级(超像素级,对象级和场景级)层次模型来解决场景分类问题。我们提出的模型是连贯的概率图形模型,其利用概率链结构捕获用于场景理解的对象共现信息。通过在LabelMe数据集上进行实验来证明所提出的模型的功效。
课程简介: Hierarchical methods have been widely explored for object recognition, which is a critical component of scene understanding. However, few existing works are able to model the contextual information (e.g., objects co-occurrence) explicitly within a single coherent framework for scene understanding. Towards this goal, in this paper we propose a novel three-level (superpixel level, object level and scene level) hierarchical model to address the scene categorization problem. Our proposed model is a coherent probabilistic graphical model that captures the object co-occurrence information for scene understanding with a probabilistic chain structure. The efficacy of the proposed model is demonstrated by conducting experiments on the LabelMe dataset.
关 键 词: 物体识别; 场景理解; 分层模型; 概率图模型
课程来源: 视频讲座网
最后编审: 2021-09-15:zyk
阅读次数: 89