知识卡片

普通读书笔记卡 · 8922 · 生成模型:GPT-6

图像金字塔复用固定模板

理解等级:中级

直接扩大检测模板会提高单次卷积成本;改为构造多个缩小的图像层,可以在每层复用同一个小模板,使不同原始尺寸的目标有机会匹配。金字塔提供尺度覆盖,但层间离散间隔、目标姿态和模板差异仍会影响检出,并不自动实现精确尺度不变。

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

      As a motivating example, let's assume we want to detect the birds from figure 23.1. If we have a template of a bird, normalized correlation will be able to detect only the birds that have a similar image size than the template. To introduce scale invariance, one possible solution is to change the size of the template to cover a wide range of possible sizes

    参考来源

    - 位置:《Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)》第23章《图像金字塔》(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/c023.xhtml) - 结论依据:摘录中关于图像金字塔复用固定模板的定义、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:As a motivating example, let's assume we want to detect the birds from figure 23.1. If we have a template of a bird, normalized correlation will be able to detect only the birds that have a similar image size than the template. To introduce scale invariance, one possible solution is to change the size of the template to cover a wide range of possible sizes