知识卡片

普通读书笔记卡 · 9074.c · 生成模型:GPT-6

亮度恒常约束跟随对应点

理解等级:中级

亮度恒常写为I₂(x+u(x,y),y+v(x,y))=I₁(x,y),表示沿对应运动追踪的场景元素亮度不变。它不是说每个固定像素数值不变,也只在有效可见对应处有意义;变化曝光和光照等会造成模型误差。

这张卡片看不懂?

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

      The brightness constancy assumption says that as a scene element moves in the world, the brightness captured by the camera from that element does not change over time. Mathematically, this assumption translates into the following relationship, given a sequence ℓ(x, y, t):

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第48章《光流估计》(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/c048.xhtml) - 结论依据:摘录中关于亮度恒常约束跟随对应点的定义、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 brightness constancy assumption says that as a scene element moves in the world, the brightness captured by the camera from that element does not change over time. Mathematically, this assumption translates into the following relationship, given a sequence ℓ(x, y, t):