• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>European Conference on Computer Vision(ECCV 2006) pt.1; 20060507-13; Graz(AT) >TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation
【24h】

TextonBoost: Joint Appearance, Shape and Context Modeling for Multi-class Object Recognition and Segmentation

机译：TextonBoost：用于多类对象识别和分割的联合外观，形状和上下文建模

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper proposes a new approach to learning a discriminative model of object classes, incorporating appearance, shape and context information efficiently. The learned model is used for automatic visual recognition and semantic segmentation of photographs. Our discriminative model exploits novel features, based on textons, which jointly model shape and texture. Unary classification and feature selection is achieved using shared boosting to give an efficient classifier which can be applied to a large number of classes. Accurate image segmentation is achieved by incorporating these classifiers in a conditional random field. Efficient training of the model on very large datasets is achieved by exploiting both random feature selection and piecewise training methods. High classification and segmentation accuracy are demonstrated on three different databases: ⅰ) our own 21-object class database of photographs of real objects viewed under general lighting conditions, poses and viewpoints, ⅱ) the 7-class Corel subset and ⅲ) the 7-class Sowerby database used in [1]. The proposed algorithm gives competitive results both for highly textured (e.g. grass, trees), highly structured (e.g. cars, faces, bikes, aeroplanes) and articulated objects (e.g. body, cow).
机译：本文提出了一种新的方法来学习对象类的判别模型，有效地合并外观，形状和上下文信息。学习的模型用于照片的自动视觉识别和语义分割。我们的判别模型利用基于Texton的新颖特征，共同对形状和纹理进行建模。一元分类和特征选择是使用共享提升实现的，可以提供可应用于大量类的高效分类器。通过将这些分类器合并到条件随机字段中，可以实现准确的图像分割。通过利用随机特征选择和分段训练方法，可以在非常大的数据集上对模型进行有效的训练。在三个不同的数据库上证明了较高的分类和分割精度：ⅰ）我们自己的21对象类数据库，其中包含在一般光照条件，姿势和视点下查看的真实对象的照片，ⅱ）7类Corel子集，ⅲ）7- [1]中使用的Sowerby类数据库。所提出的算法对于高纹理（例如草，树），高结构（例如汽车，人脸，自行车，飞机）和铰接物体（例如身体，牛）都给出了竞争结果。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号