A technique for representing a scene or map based on statistics of captured environmental data is discussed herein. In some cases, data, such as covariance data, mean data, etc., may be stored as a multi-resolution voxel space that includes multiple semantic layers. In some cases, individual semantic layers may include multiple voxel grids having different resolutions. Based on voxel covariance detected at one or more resolutions, a plurality of multi-resolution voxel spaces may be merged to generate a combined scene.
本文讨论了一种用于基于捕获的环境数据的统计数据来表示场景或地图的技术。在一些情况下,数据(诸如协方差数据、均值数据等)可以被存储作为包括多个语义层的多分辨率体素空间。在一些情况下,单独的语义层可以包括具有不同分辨率的多个体素网格。基于在一个或多个分辨率下检测到的体素协方差,可以合并多个多分辨率体素空间以生成组合场景。
Map including covariance in multi-resolution voxels
包括多分辨率体素中的协方差的地图
2022-08-05
Patent
Electronic Resource
Chinese
Efficient linear octree generation from voxels
British Library Online Contents | 1994
|Real time simulation of manufacturing processes using voxels
Automotive engineering | 1999
|