• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Models for object detection, recognition, and shape alignment.
【24h】

Models for object detection, recognition, and shape alignment.

机译：用于对象检测，识别和形状对齐的模型。

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

The grand goal of computer vision is to provide a complete semantic interpretation of an input image by reasoning about the 3d scene that generated it. Object detection, recognition, and alignment are three fundamental vision tasks towards this goal. In this thesis, we develop a series of efficient algorithms to address these problems. The contributions are summarized as follows. (1) We present a two-step algorithm for specific object detection in cluttered background with a few example images and unknown camera poses. Instead of enforcing metric constraints on the local features, we utilize a set of ordering constraints which are powerful enough for the detection task. At the core of this algorithm is a qualitative feature matching scheme which includes an angular ordering constraint in local scale and a graph planarity constraint in global scale. (2) We present a part-based model for object categorization and part localization. The spatial interactions among parts are modeled by Factor Analysis which can be learned from the data. Constrained by the shape prior, part localization proceeds in the image space by using a triangulated Markov random field (TMRF) model. We propose an iterative shape estimation and regularization approach for efficient computation. (3) We propose a boosting procedure for simultaneous multi-view car detection . By combining the multi-class LogitBoost and AdaBoost detectors, we decompose the original problem to view classification and view-specific detection, which can be solved independently. We study various feature representations and weak learners for the boosting algorithms. Extensive experiments demonstrate improved accuracy and detection rate over the traditional algorithms. (4) We propose a Bayesian framework for robust shape alignment. Prior models assume Gaussian observation noise and attempt to fit a regularized shape using all the observed data, such an assumption is vulnerable to outrageous local features and occlusions. We address this problem by using a hypothesis-and-test approach. A Bayesian inference algorithm is developed to generate a large number of shape hypotheses from randomly sampled partial shapes. The hypotheses are then evaluated in the robust estimation framework to find the optimal one. Our model can effectively handle outliers and recover the underlying object shape. The proposed approach is evaluated on a very challenging dataset which spans a wide variety of car types, viewpoints, background scenes, and occlusion patterns.
机译：计算机视觉的主要目标是通过推理生成输入图像的3d场景来提供输入图像的完整语义解释。目标检测，识别和对准是实现该目标的三个基本视觉任务。在本文中，我们开发了一系列有效的算法来解决这些问题。贡献概述如下。 （1）我们提出了一种用于在杂乱背景中检测特定对象的两步算法，其中包含一些示例图像和未知的相机姿势。代替对本地特征强制执行度量约束，我们利用一组足以执行检测任务的排序约束。该算法的核心是定性特征匹配方案，该方案包括局部尺度的角度排序约束和全局尺度的图形平面约束。 （2）我们提出了一种基于零件的模型，用于对象分类和零件本地化。零件之间的空间相互作用通过因素分析建模，可以从数据中学习。受形状先验的约束，通过使用三角马尔可夫随机场（TMRF）模型在图像空间中进行零件定位。我们提出了一种迭代形状估计和正则化方法，以进行有效的计算。 （3）我们提出了一种同时进行多视点汽车检测的增强程序。通过组合多类LogitBoost和AdaBoost检测器，我们将原始问题分解为视图分类和特定于视图的检测，可以独立解决。我们研究了各种特征表示和弱学习者的增强算法。大量实验表明，与传统算法相比，该算法具有更高的准确性和检测率。 （4）我们提出了一种用于稳健形状对齐的贝叶斯框架。先前的模型假设高斯观测噪声，并尝试使用所有观测数据拟合正则形状，这样的假设很容易受到残酷的局部特征和遮挡的影响。我们通过使用假设和检验的方法来解决这个问题。贝叶斯推理算法被开发为从随机采样的局部形状中生成大量形状假设。然后在稳健的估计框架中对假设进行评估，以找到最佳假设。我们的模型可以有效地处理离群值并恢复基础对象的形状。所提出的方法是在一个非常具有挑战性的数据集上进行评估的，该数据集涵盖了各种各样的汽车类型，视点，背景场景和遮挡模式。

著录项

  • 作者

    Li, Yan.;

  • 作者单位

    Carnegie Mellon University.;

  • 授予单位 Carnegie Mellon University.;
  • 学科 Computer Science.
  • 学位 Ph.D.
  • 年度 2009
  • 页码 177 p.
  • 总页数 177
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 自动化技术、计算机技术;
  • 关键词

  • 入库时间 2022-08-17 11:38:26

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