Patent · US Active

Method, computer program product and device for training a neural network

US10956781B2 · kind B2 · utility

0Cited by

4References

9Claims

0Family size

Assignee

Axis AB · SE

Inventors

Markus Skans · Lund, SE
Niclas Danielsson · Lund, SE

Key dates

Filing date	Dec 13, 2017
Grant date	Mar 23, 2021
Priority date	—
Expiry date	May 4, 2038

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/09
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method, device and computer program product for training neural networks being adapted to process image data and output a vector of values forming a feature vector for the processed image data. The training is performed using feature vectors from a reference neural network as ground truth. A system of devices for tracking an object using feature vectors outputted by neural networks running on the devices.

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