← 返回起始笔记位置

知识卡片

普通读书笔记卡 · 9165 · 生成模型:GPT-6

霍夫变换让数据投票给参数

理解等级:中级

每个边缘点给所有可能通过它的候选线投票,来自同一直线的点在参数空间形成集中峰。峰值表示被较多观测支持的参数,而不是直接在原图寻找某个亮像素;噪声和量化会使峰变宽或出现伪峰。

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 Hough transform can best be understood as a voting scheme to guess the parameterization of a feature such as a line, circle, or other curve (Duda and Hart 1972). For example, a line might be represented by y = mx + c, where m and c are the gradient and offset. A point in this parameter space (or “Hough-space”) then corresponds to a specific

    参考来源

    - 位置:《Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)》第09章《特征提取》(来源项目:a19c7933-4eda-4176-aebd-30fe7e1ad292;源文件:extracted/Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)/_epub-src/OEBPS/xhtml/chapter_9.xhtml) - 结论依据:摘录中关于霍夫变换让数据投票给参数的定义、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 Hough transform can best be understood as a voting scheme to guess the parameterization of a feature such as a line, circle, or other curve (Duda and Hart 1972). For example, a line might be represented by y = mx + c, where m and c are the gradient and offset. A point in this parameter space (or “Hough-space”) then corresponds to a specific