图 书 馆
基于点态互信息的清晰边界检测Crisp Boundary Detection Using Pointwise Mutual Information |
|
| 课程网址: | http://videolectures.net/eccv2014_isola_mutual_information/ |
| 主讲教师: | Phillip Isola |
| 开课单位: | 麻省理工学院 |
| 开课时间: | 2014-10-29 |
| 课程语种: | 英语 |
| 中文简介: |  在视觉场景中检测语义上有意义的对象之间的边界是许多视觉算法的重要组成部分。在本文中，我们基于一种简单的基本原理提出了一种检测此类边界的新颖方法：与属于不同对象的像素相比，属于同一对象的像素显示出更高的统计依赖性。我们展示了如何使用逐点互信息基于此原理导出亲和力度量，并且我们表明该度量确实可以很好地预测两个像素是否位于同一对象上。利用这种亲和力和光谱聚类，我们可以在图像中找到对象边界，从而在BSDS500数据集上获得最新的结果。我们的方法可产生像素级的精确边界，同时需要最少的特征工程。 |
| 课程简介: | Detecting boundaries between semantically meaningful objects in visual scenes is an important component of many vision algorithms. In this paper, we propose a novel method for detecting such boundaries based on a simple underlying principle: pixels belonging to the same object exhibit higher statistical dependencies than pixels belonging to different objects. We show how to derive an affinity measure based on this principle using pointwise mutual information, and we show that this measure is indeed a good predictor of whether or not two pixels reside on the same object. Using this affinity with spectral clustering, we can find object boundaries in the image – achieving state-of-the-art results on the BSDS500 dataset. Our method produces pixel-level accurate boundaries while requiring minimal feature engineering. |
| 关 键 词: | 视觉场景; 视觉算法; 算法视觉 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-04-07：zyk |
| 最后编审: | 2021-04-07：zyk |
| 阅读次数: | 60 |