知识卡片
视觉词袋压缩特征的分布
词袋把相近局部描述子归入视觉词,统计其出现以比较图像或对象。它能减少匹配负担,却可能丢失精确空间布局;词频相似不是对象存在的校准概率,也不直接给出三维位置。
这张卡片看不懂?
这张卡片已通过人工审查,不再接受失败反馈。
已有反馈 · 0 条
还没有人提交反馈。
在整书笔记中的位置
- · 特征提取
原书出处 · 1 处
- · 查看原书依据
Scale-invariant features of training images can be stored in a database and used to identify these objects in the future. One approach is to find all features in an image and compare them with those in the database. This comparison is done by using the Euclidian distance as metric and searching a k-d tree (with d = 128). In order to make this approach robust,
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:摘录中关于视觉词袋压缩特征的分布的定义、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:Scale-invariant features of training images can be stored in a database and used to identify these objects in the future. One approach is to find all features in an image and compare them with those in the database. This comparison is done by using the Euclidian distance as metric and searching a k-d tree (with d = 128). In order to make this approach robust,