公开(公告)号：US20210027055A1

公开(公告)日：2021-01-28

申请号：US16934361

申请日：2020-07-21

申请人： Ordnance Survey Limited

发明人： Jacob Guy Rainbow

IPC分类号： G06K9/00 ,  G01V9/00 ,  G06K9/62 ,  G06K9/46

摘要： Computer-implemented methods and systems for identifying topographic features that optimises and subsequently implements a machine learning model to automatically classify and extract topographic features from a set of target imagery are described herein. In particular, the optimised machine learning model creates heat maps from the target imagery corresponding to each class of feature, wherein the intensity of each pixel indicates whether a certain type of feature is present. The resulting heat maps are then processed to transform each pixel, specifically those identifying a topographic feature, into a geospatial vector.

公开(公告)号：US11804025B2

公开(公告)日：2023-10-31

申请号：US16934361

申请日：2020-07-21

申请人： Ordnance Survey Limited

发明人： Jacob Guy Rainbow

IPC分类号： G01V9/00 ,  G06V20/10 ,  G06V10/44 ,  G06F18/21 ,  G06V10/764 ,  G06V10/82

CPC分类号： G06V10/454 ,  G01V9/005 ,  G06F18/2163 ,  G06V10/764 ,  G06V10/82 ,  G06V20/176 ,  G06V20/182

摘要： Computer-implemented methods and systems for identifying topographic features that optimises and subsequently implements a machine learning model to automatically classify and extract topographic features from a set of target imagery are described herein. In particular, the optimised machine learning model creates heat maps from the target imagery corresponding to each class of feature, wherein the intensity of each pixel indicates whether a certain type of feature is present. The resulting heat maps are then processed to transform each pixel, specifically those identifying a topographic feature, into a geospatial vector.