知识卡片
背景去除只保留变化部分
转角例先减均值背景,针对随时间改变的隐藏目标恢复信号;静态成分可能同时被去除。这个步骤降低稳定照明干扰,也改变可恢复对象。不能把动态实验的结果推广为无需运动或校准就重建完整静态场景。
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
原书出处 · 1 处
- · 查看原书依据
we will subtract a mean image from our observations of the ground plane, so in the rendering equation below, we will only consider components of the scene that may change over time, under the assumption that what we want to image behind the corner (e.g., a person) is moving. We will call these intensities S(ϕ, θ) (S for the subject), where ϕ measures vertical inclination
参考来源
- 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第07章《作为线性系统的相机》(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/c007.xhtml)
- 结论依据:摘录中关于背景去除只保留变化部分的定义、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:we will subtract a mean image from our observations of the ground plane, so in the rendering equation below, we will only consider components of the scene that may change over time, under the assumption that what we want to image behind the corner (e.g., a person) is moving. We will call these intensities S(ϕ, θ) (S for the subject), where ϕ measures vertical inclination