Patent · US Active

Object counting and instance segmentation using neural network architectures with image-level supervision

US10453197B1 · kind B1 · utility

33Cited by
0References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateFeb 18, 2019
Grant dateOct 22, 2019
Priority date
Expiry dateFeb 18, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/30242
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

This disclosure relates to improved techniques for performing computer vision functions including common object counting and instance segmentation. The techniques described herein utilize a neural network architecture to perform these functions. The neural network architecture can be trained using image-level supervision techniques that utilize a loss function to jointly train an image classification branch and a density branch of the neural network architecture. The neural network architecture constructs per-category density maps that can be used to generate analysis information comprising global object counts and locations of objects in images.

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