← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9076.c · 生成模型:GPT-6

角点提供两个方向的信息

理解等级:中级

直边中段只支持法向速度,角点周围有不同方向的梯度,通常可更稳定地估计二维流。A与Harris检测共用局部结构信息,但“角点可跟踪”是条件性判断,仍会受到遮挡、运动模糊与重复图案影响。

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

      We can see that the result seems to be wrong for the motion estimated near the center of the side of each square. The inverse can only be computed in image regions with sufficient texture variations (i.e., near the corners). As in the Harris corner detector (see section 40.3.2.1), the eigenvector with the smallest eigenvalue indicates the direction in which the image has the smallest

    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:摘录中关于角点提供两个方向的信息的定义、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 can see that the result seems to be wrong for the motion estimated near the center of the side of each square. The inverse can only be computed in image regions with sufficient texture variations (i.e., near the corners). As in the Harris corner detector (see section 40.3.2.1), the eigenvector with the smallest eigenvalue indicates the direction in which the image has the smallest