公开(公告)号：US11004234B2

公开(公告)日：2021-05-11

申请号：US15410704

申请日：2017-01-19

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Jun Zhan ,  Houchang Lv ,  Xu Han

IPC: G06T7/73 ,  G06K9/46 ,  G06K9/00 ,  G01S7/48 ,  G01S17/86 ,  G01S17/931 ,  G06T7/246 ,  G01S17/66 ,  G06T7/11

Abstract: The present application discloses a method and apparatus for annotating point cloud data. A specific implementation of the method includes: collecting data in a given scenario by using a laser radar and a non-laser radar sensor to respectively obtain point cloud data and sensor data; segmenting and tracking the point cloud data to obtain point cloud segmentation and tracking results; recognizing and tracking feature objects in the sensor data to obtain feature object recognition and tracking results; correcting the point cloud segmentation and tracking results by using the feature object recognition and tracking results, to obtain confidence levels of the point cloud recognition and tracking results; and determining a point cloud segmentation and tracking result whose confidence level is greater than a confidence level threshold as a point cloud annotation result. This implementation reduces the amount of manual work required for annotating point cloud data, thereby reducing the annotation costs.

公开(公告)号：US20180108146A1

公开(公告)日：2018-04-19

申请号：US15410704

申请日：2017-01-19

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Jun Zhan ,  Houchang Lv ,  Xu Han

IPC: G06T7/73 ,  G01S17/66 ,  G01S17/02 ,  G06K9/46 ,  G06T7/246

CPC classification number: G06T7/73 ,  G01S7/4808 ,  G01S17/023 ,  G01S17/66 ,  G01S17/936 ,  G06K9/00228 ,  G06K9/00664 ,  G06K9/00805 ,  G06K9/46 ,  G06K9/4604 ,  G06T7/11 ,  G06T7/246 ,  G06T2207/10004 ,  G06T2207/10016

Abstract: The present application discloses a method and apparatus for annotating point cloud data. A specific implementation of the method includes: collecting data in a given scenario by using a laser radar and a non-laser radar sensor to respectively obtain point cloud data and sensor data; segmenting and tracking the point cloud data to obtain point cloud segmentation and tracking results; recognizing and tracking feature objects in the sensor data to obtain feature object recognition and tracking results; correcting the point cloud segmentation and tracking results by using the feature object recognition and tracking results, to obtain confidence levels of the point cloud recognition and tracking results; and determining a point cloud segmentation and tracking result whose confidence level is greater than a confidence level threshold as a point cloud annotation result. This implementation reduces the amount of manual work required for annotating point cloud data, thereby reducing the annotation costs.