Scan Context: Egocentric Spatial Descriptor for Place Recognition within 3D Point Cloud Map

1、摘要

https://mp.weixin.qq.com/s/J1pVixk0rY_hxtDq4ry1JQ

2、步驟

2.1 以激光原點爲中心，均勻劃分周圍空間

we first divide a 3D scan into azimuthal(方位的) and radial(徑向的) bins in the sensor coordinate, but in an equally spaced manner as shown in Fig. 1(a).
Ns and Nr are the number of sectors and rings, respectively.