知识卡片
相同标签偏好不禁止边界
示例Potts相容势对相同状态赋1、不同状态赋δ,0<δ时鼓励相邻标签一致,同时仍允许观测支持的跃变。δ很小会加强平滑倾向,也可能抹去真实边界。书中的0.001是特定例子,不是适合所有视差分箱或图像的通用设置。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 概率图模型
原书出处 · 1 处
- · 查看原书依据
The prior probability of any configuration of pixel disparity states is described by setting the compatibility matrices, ϕ[si, si+1] of the Markov chain of figure 29.20. For this example, we use a compatibility matrix referred to as the Potts Model [510]:
参考来源
- 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第29章《概率图模型》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c029.xhtml)
- 结论依据:摘录中关于相同标签偏好不禁止边界的定义、比较或条件支撑卡片;原书表述不严谨的范围已在覆盖记录逐项限定,不把案例结果外推为普遍结论。
- 原始内容:The prior probability of any configuration of pixel disparity states is described by setting the compatibility matrices, ϕ[si, si+1] of the Markov chain of figure 29.20. For this example, we use a compatibility matrix referred to as the Potts Model [510]: