| 发明名称 |
SUBCATEGORY-AWARE CONVOLUTIONAL NEURAL NETWORKS FOR OBJECT DETECTION |
| 摘要 |
A computer-implemented method for detecting objects by using subcategory-aware convolutional neural networks (CNNs) is presented. The method includes generating object region proposals from an image by a region proposal network (RPN) which utilizes subcategory information, and classifying and refining the object region proposals by an object detection network (ODN) that simultaneously performs object category classification, subcategory classification, and bounding box regression. The image is an image pyramid used as input to the RPN and the ODN. The RPN and the ODN each include a feature extrapolating layer to detect object categories with scale variations among the objects. |
| 申请公布号 |
US2017124415(A1) |
申请公布日期 |
2017.05.04 |
| 申请号 |
US201615342823 |
申请日期 |
2016.11.03 |
| 申请人 |
NEC Laboratories America, Inc. |
发明人 |
Choi Wongun;Lin Yuanqing;Xiang Yu;Savarese Silvio |
| 分类号 |
G06K9/46;G06N3/08;G06T7/00 |
主分类号 |
G06K9/46 |
| 代理机构 |
|
代理人 |
|
| 主权项 |
1. A computer-implemented method for detecting objects by using subcategory-aware convolutional neural networks (CNNs), the method comprising:
generating object region proposals from an image by a region proposal network (RPN) which utilizes subcategory information; and classifying and refining the object region proposals by an object detection network (ODN) that simultaneously performs object category classification, subcategory classification, and bounding box regression. |
| 地址 |
Princeton NJ US |
