Patent · US Active

Cross-domain image processing for object re-identification

US11367268B2 · kind B2 · utility

2Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateAug 20, 2020
Grant dateJun 21, 2022
Priority date
Expiry dateNov 29, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06V10/62
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Object re-identification refers to a process by which images that contain an object of interest are retrieved from a set of images captured using disparate cameras or in disparate environments. Object re-identification has many useful applications, particularly as it is applied to people (e.g. person tracking). Current re-identification processes rely on convolutional neural networks (CNNs) that learn re-identification for a particular object class from labeled training data specific to a certain domain (e.g. environment), but that do not apply well in other domains. The present disclosure provides cross-domain disentanglement of id-related and id-unrelated factors. In particular, the disentanglement is performed using a labeled image set and an unlabeled image set, respectively captured from different domains but for a same object class. The identification-related features may then be used to train a neural network to perform re-identification of objects in that object class from images captured from the second domain.

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