Patent · US Active

Apparatus and method for detecting keypoint based on deep learning using information change across receptive fields

US11989927B2 · kind B2 · utility

0Cited by
2References
17Claims
0Family size

Assignees

Inventors

Key dates

Filing dateDec 30, 2021
Grant dateMay 21, 2024
Priority date
Expiry dateJul 22, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/82
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Disclosed herein are an apparatus and method for detecting a keypoint based on deep learning robust to scale changes based on information change across receptive fields. The apparatus for detecting a keypoint based on deep learning robust to scale changes based on information change across receptive fields includes a feature extractor for extracting a feature from an input image based on a pre-trained deep learning neural network, an information accumulation pyramid module for outputting, from the feature, at least two filter responses corresponding to receptive fields having different scales, an information change detection module for calculating an information change between the at least two filter responses, a keypoint detection module for creating a score map having a keypoint probability of each pixel based on the information change, and a continuous scale estimation module for estimating a scale of a receptive field having a biggest information change for each pixel.

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