← 返回刚才阅读的位置

知识卡片

普通读书笔记卡 · 9161.c · 生成模型:GPT-6

结构光用已知图案帮助对应

理解等级:中级

投射条纹或散斑给表面增加可识别编码,利用图案的观测位置与已知投影几何推断深度。它减轻自然纹理不足,却仍需解决标定、遮挡和图案歧义;不是找大小相近且距离近的斑点就一定匹配成功。

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

      Instead of using line patterns, infrared-based depth image sensors use a speckle pattern (a collection of randomly distributed dots with varying distances). Identifying identical points in two images simply requires one to search for blobs with similar size that are close to each other.

    参考来源

    - 位置:《Introduction to Autonomous Robots Mechanisms, Sensors, Actuators, and Algorithms (Nikolaus Correll, Bradley Hayes etc.)》第08章《视觉》(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_8.xhtml) - 结论依据:摘录中关于结构光用已知图案帮助对应的定义、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:Instead of using line patterns, infrared-based depth image sensors use a speckle pattern (a collection of randomly distributed dots with varying distances). Identifying identical points in two images simply requires one to search for blobs with similar size that are close to each other.