-
1.发明申请公开(公告)号：US20220245825A1
公开(公告)日：2022-08-04
申请号：US17725582
申请日：2022-04-21
发明人： Bo Han , Cheuk Yiu Ip , Eric Zavesky , Huanle Zhang
摘要： Aspects of the subject disclosure may include, for example, a device that has a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, including downsampling a full point cloud to obtain a downsampled point cloud, wherein the downsampling reduces a data size of the full point cloud; and using a machine-learning model to assign labels for segmentation and object identification to points in the downsampled point cloud, wherein the machine-learning model is trained on the full point cloud. Other embodiments are disclosed.
-
2.发明授权公开(公告)号：US11341650B2
公开(公告)日：2022-05-24
申请号：US16824023
申请日：2020-03-19
发明人： Bo Han , Cheuk Yiu Ip , Eric Zavesky , Huanle Zhang
摘要： Aspects of the subject disclosure may include, for example, a device that has a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, including downsampling a full point cloud to obtain a downsampled point cloud, wherein the downsampling reduces a data size of the full point cloud; and using a machine-learning model to assign labels for segmentation and object identification to points in the downsampled point cloud, wherein the machine-learning model is trained on the full point cloud. Other embodiments are disclosed.
-
3.发明公开公开(公告)号：US20230252641A1
公开(公告)日：2023-08-10
申请号：US18297053
申请日：2023-04-07
发明人： Bo Han , Cheuk Yiu Ip , Huanle Zhang , Eric Zavesky
IPC分类号： G06T7/11 , G06T1/60 , G06N3/08 , G06T3/40 , G06F18/214 , G06V10/764 , G06V10/82
CPC分类号： G06T7/11 , G06T1/60 , G06N3/08 , G06T3/40 , G06F18/2148 , G06V10/764 , G06V10/82 , G06T2207/20084 , G06T2207/10028 , G06T2207/20081
摘要： Aspects of the subject disclosure may include, for example, a device that has a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, including downsampling a full point cloud to obtain a downsampled point cloud, wherein the downsampling reduces a data size of the full point cloud; and using a machine-learning model to assign labels for segmentation and object identification to points in the downsampled point cloud, wherein the machine-learning model is trained on the full point cloud. Other embodiments are disclosed.
-
4.发明授权公开(公告)号：US11651498B2
公开(公告)日：2023-05-16
申请号：US17725582
申请日：2022-04-21
发明人： Bo Han , Cheuk Yiu Ip , Eric Zavesky , Huanle Zhang
CPC分类号： G06T7/11 , G06K9/6257 , G06N3/08 , G06T1/60 , G06T3/40 , G06T2207/10028 , G06T2207/20081 , G06T2207/20084
摘要： Aspects of the subject disclosure may include, for example, a device that has a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, including downsampling a full point cloud to obtain a downsampled point cloud, wherein the downsampling reduces a data size of the full point cloud; and using a machine-learning model to assign labels for segmentation and object identification to points in the downsampled point cloud, wherein the machine-learning model is trained on the full point cloud. Other embodiments are disclosed.
-
5.发明申请公开(公告)号：US20210295522A1
公开(公告)日：2021-09-23
申请号：US16824023
申请日：2020-03-19
发明人： Bo Han , Cheuk Yiu Ip , Eric Zavesky , Huanle Zhang
摘要： Aspects of the subject disclosure may include, for example, a device that has a processing system including a processor; and a memory that stores executable instructions that, when executed by the processing system, facilitate performance of operations, including downsampling a full point cloud to obtain a downsampled point cloud, wherein the downsampling reduces a data size of the full point cloud; and using a machine-learning model to assign labels for segmentation and object identification to points in the downsampled point cloud, wherein the machine-learning model is trained on the full point cloud. Other embodiments are disclosed.
-
-
-
-
搜索结果
5 条记录 (耗时 0.026 秒)
