Context based object categorization: A critical survey
Context based object categorization: A critical survey
复制标题
DOI：
10.1016/j.cviu.2010.02.004
复制
发表时间：
2010-06-01
影响因子：
4.5
通讯作者：
Belongie, Serge
中科院分区：
文献类型：
--
作者：
Galleguillos, Carolina;Belongie, Serge
对象分类的目标是在图像中定位和识别对象类别的实例。当图像包括遮挡、质量差、噪声或背景杂波时，识别图像中的对象是困难的，并且当许多对象存在于同一场景中时，该任务变得更具挑战性。几种用于对象分类的模型使用来自对象的外观和上下文信息来提高识别精度。基于视觉线索的外观信息可以在一定程度上成功地识别对象类别。基于场景中对象之间的交互或全局场景统计的上下文信息可以帮助成功地消除识别任务中的外观输入的歧义。在这项工作中，我们解决的问题，将不同类型的上下文信息的强大的对象分类在计算机视觉。我们审查不同的方式使用上下文信息的对象分类领域，考虑到最常见的水平提取的上下文和不同层次的上下文交互。我们还研究了将上下文信息集成到对象识别框架中的常见机器学习模型，并讨论了可扩展性，优化和未来可能的方法。(C)2010年爱思唯尔公司All rights reserved.
The goal of object categorization is to locate and identify instances of an object category within an image. Recognizing an object in an image is difficult when images include occlusion, poor quality, noise or background clutter, and this task becomes even more challenging when many objects are present in the same scene. Several models for object categorization use appearance and context information from objects to improve recognition accuracy. Appearance information, based on visual cues, can successfully identify object classes up to a certain extent. Context information, based on the interaction among objects in the scene or global scene statistics, can help successfully disambiguate appearance inputs in recognition tasks. In this work we address the problem of incorporating different types of contextual information for robust object categorization in computer vision. We review different ways of using contextual information in the field of object categorization, considering the most common levels of extraction of context and the different levels of contextual interactions. We also examine common machine learning models that integrate context information into object recognition frameworks and discuss scalability, optimizations and possible future approaches. (C) 2010 Elsevier Inc. All rights reserved.