Patent · US Active

Subcategory-aware convolutional neural networks for object detection

US9965719B2 · kind B2 · utility

24Cited by
1References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 3, 2016
Grant dateMay 8, 2018
Priority date
Expiry dateNov 3, 2036

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/30261
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.