Cross-domain image processing for object re-identification
AssigneeNVIDIA Corporation
InventorsXiaodong Yang, Yang Zou, Zhiding Yu, Jan Kautz
Life of this patent
Estimating the term…
Loading patent…
AssigneeNVIDIA Corporation
InventorsXiaodong Yang, Yang Zou, Zhiding Yu, Jan Kautz
Estimating the term…
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.
A method, comprising:
A neural network, comprising:
A non-transitory computer-readable media storing computer instructions that, when executed by one or more processors, cause the one or more processors to perform a method comprising:
Dependencies are inferred from the claim text.