|
多视点立体视觉的概率论
Probabilistic account for multi-view stereo |
|
| |
| 课程网址: |
http://videolectures.net/lmcv04_fransens_pamvs/
|
| 主讲教师: |
Rik Fransens
|
| 开课单位: |
鲁汶大学
|
| 开课时间: |
2007-02-25
|
| 课程语种: |
英语
|
| 中文简介: |
本文介绍了一种从宽基线图像中进行密集深度重建的方法。在宽基线设置中, 使立体对应问题复杂化的固有困难是自遮挡。此外, 我们还必须考虑, 由于非兰伯蒂安效应或离散化错误, 不同图像中的图像像素 (即场景中同一点的投影) 可能会具有不同的颜色值。我们建议采用贝叶斯方法来解决这些问题。在这个框架中, 图像被视为底层 "真实" 图像函数的噪声测量。另外, 图像数据被认为是不完整的, 因为我们不知道特定图像中的哪些像素被排除在其他图像中。我们描述了一个 em 算法, 它在估计所有隐藏数量的值和优化当前深度估计之间迭代。该算法自由参数少, 表现出稳定的收敛行为, 并产生准确的深度估计。
|
| 课程简介: |
This paper describes a method for dense depth reconstruction from wide-baseline images. In a wide-baseline setting an inherent difficulty which complicates the stereo correspondence problem is self-occlusion. Also, we have to consider the possibility that image pixels in different images, which are projections of the same point in the scene, will have different colour values due to non-Lambertian effects or discretization errors. We propose a Bayesian approach to tackle these problems. In this framework, the images are regarded as noisy measurements of an underlying 'true' image-function. Also, the image data is considered incomplete, in the sense that we do not know which pixels from a particular image are occluded in the other images. We describe an EM-algorithm, which iterates between estimating values for all hidden quantities, and optimising the current depth estimates. The algorithm has few free parameters, displays a stable convergence behaviour and generates accurate depth estimates.
|
| 关 键 词: |
计算机科学; 计算机视觉; 离散; 图像数据
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2021-02-04：nkq
|
| 阅读次数: |
31
|
|
图 书 馆