Patent · US Active

Combining convolution and deconvolution for object detection

US10628705B2 · kind B2 · utility

1Cited by
3References
30Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 29, 2018
Grant dateApr 21, 2020
Priority date
Expiry dateAug 4, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V40/16
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Provided are systems, methods, and computer-readable medium for operating a neural network. In various implementations, the neural network can receive an input image that includes an object to be identified. The neural network can generate a plurality of initial feature maps using a convolution layers, wherein a first initial feature maps is generated using the input image. The neural network can generate an up-sampled feature map using a de-convolution layer that takes an initial feature map as input, where the up-sampled feature map has a same resolution as the previous initial feature map. The neural network can combine the up-sampled feature map and the previous initial feature map, and use the combined feature map to more accurate identify the object.

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