发明授权
- 专利标题: Machine-learning framework for detecting defects or conditions of railcar systems
-
申请号: US17549499申请日: 2021-12-13
-
公开(公告)号: US11468551B1公开(公告)日: 2022-10-11
- 发明人: Mahbod Amouie , Evan T. Gebhardt , Gongli Duan , Myles Grayson Akin , Wei Liu , Tianchen Wang , Mayuresh Manoj Sardesai , Ilya A. Lavrik
- 申请人: Norfolk Southern Corporation
- 申请人地址: US VA Norfolk
- 专利权人: Norfolk Southern Corporation
- 当前专利权人: Norfolk Southern Corporation
- 当前专利权人地址: US VA Norfolk
- 代理机构: Morris, Manning & Martin, LLP
- 代理商 Daniel E. Sineway, Esq.; Micah B. Hensley, Esq.
- 主分类号: G06T7/00
- IPC分类号: G06T7/00 ; G06K9/62 ; B61L27/57
摘要:
A computer-implemented method in which one or more processing devices perform operations may include obtaining a field image of a railcar collected from a field camera system and applying a machine-learning algorithm to the field image to generate a machine-learning algorithm output. The method may also include performing a post-processing operation on the machine-learning algorithm output to generate a filtered machine-learning algorithm output. Further, the method may include detecting a defect of the railcar using the filtered machine-learning algorithm output.
信息查询