发明名称 |
Object detection using candidate object alignment |
摘要 |
Classification of an object in the field of view of a camera. A processor is configured to capture multiple image frames from the camera. A candidate image is detected in the image frames. Alignment of the candidate image is determined relative to at least one previously known training image by inputting the candidate image into a trained alignment classifier and outputting one or more alignment variables therefrom associated with the candidate image. The candidate image and the alignment variable(s) are input into a trained object classifier. The object is classified responsive to the alignment variable(s). |
申请公布号 |
US9183447(B1) |
申请公布日期 |
2015.11.10 |
申请号 |
US201213493136 |
申请日期 |
2012.06.11 |
申请人 |
MOBILEYE VISION TECHNOLOGIES LTD. |
发明人 |
Gdalyahu Yoram;Livyatan Harel;Schwarz Oded;Taieb Yoav;Stein Gideon P.;Viente Kfir |
分类号 |
G06K9/62;G06K9/00 |
主分类号 |
G06K9/62 |
代理机构 |
The Law Office of Michael E. Kondoudis |
代理人 |
The Law Office of Michael E. Kondoudis |
主权项 |
1. A method for classifying an object in the field of view of a camera, wherein a processor is configured to capture a plurality of image frames from the camera, the method comprising:
detecting a candidate image in the image frames; determining alignment of said candidate image relative to at least one previously known training image by inputting the candidate image into a trained alignment classifier and outputting a plurality of alignment variables therefrom associated with the candidate image by performing a separate regression for each of said alignment variables; inputting the candidate image and said alignment variables into a trained object classifier; and classifying the object by the trained object classifier responsive to said alignment variables. |
地址 |
Jerusalem IL |