知识卡片

普通读书笔记卡 · 9160.a · 生成模型:GPT-6

视觉语义和度量信息需要分辨

理解等级:中级

语义回答场景里是什么,度量回答位置、尺寸与距离。学习可帮助识别与匹配,几何关系则约束三维重建;同一流水线可以结合两者,但识别出了对象名称不自动等于已经知道其真实尺度。

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

      A remarkable property of vision is the ability to provide both semantic (qualities of the scene, such as what is in it) and metric (quantities of the scene, such as sizes and distances) information. Extracting semantic information is nowadays heavily reliant on machine learning, which is explained at a high level in section 8.5. The extraction of metric information, however, can be accomplished by leveraging

    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:摘录中关于视觉语义和度量信息需要分辨的定义、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:A remarkable property of vision is the ability to provide both semantic (qualities of the scene, such as what is in it) and metric (quantities of the scene, such as sizes and distances) information. Extracting semantic information is nowadays heavily reliant on machine learning, which is explained at a high level in section 8.5. The extraction of metric information, however, can be accomplished by leveraging