知识卡片

普通读书笔记卡 · 9042.b · 生成模型:GPT-6

单点定位先找参考面垂足

理解等级:中级

若已知像点P与它在参考面上的垂直投影G的像位置,便增加了射线之外的结构约束。可将G沿两地面消失方向连接到已标定X、Z轴,读出平面坐标;再用PG与参考竖轴的关系获得高度。G需要对象几何或接触信息提供,不能由P任意猜出。

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 basic procedure is illustrated in figure 42.20(b). The trick consists in using context (what object is the point part of, where is the horizon line of the scene and where are the vanishing points) to estimate 3D from a single image. It suffices to know that the point P belongs to an object that is in contact with the ground and the geometry of

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第42章《单视图测量》(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/c042.xhtml) - 结论依据:摘录中关于单点定位先找参考面垂足的定义、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 basic procedure is illustrated in figure 42.20(b). The trick consists in using context (what object is the point part of, where is the horizon line of the scene and where are the vanishing points) to estimate 3D from a single image. It suffices to know that the point P belongs to an object that is in contact with the ground and the geometry of