×

Subcategory-aware convolutional neural networks for object detection

  • US 9,965,719 B2
  • Filed: 11/03/2016
  • Issued: 05/08/2018
  • Est. Priority Date: 11/04/2015
  • Status: Active Grant
First Claim
Patent Images

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,wherein the RPN and the ODN each include a feature extrapolating layer to detect object categories with scale variations among the objects.

View all claims
  • 2 Assignments
Timeline View
Assignment View
    ×
    ×