Patent · US Active

Method and apparatus for neural network training and construction and method and apparatus for object detection

US10769493B2 · kind B2 · utility

36Cited by
2References
7Claims
0Family size

Assignees

Inventors

Key dates

Filing dateJul 26, 2017
Grant dateSep 8, 2020
Priority date
Expiry dateJun 1, 2038

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V40/168
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The embodiments of the present invention provide training and construction methods and apparatus of a neural network for object detection, an object detection method and apparatus based on a neural network and a neural network. The training method of the neural network for object detection, comprises: inputting a training image including a training object to the neural network to obtain a predicted bounding box of the training object; acquiring a first loss function according to a ratio of the intersection area to the union area of the predicted bounding box and a true bounding box, the true bounding box being a bounding box of the training object marked in advance in the training image; and adjusting parameters of the neural network by utilizing at least the first loss function to train the neural network.

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