Patent · US Active

Method, artificial neural network, device, computer program and machine-readable memory medium for the semantic segmentation of image data

US11113561B2 · kind B2 · utility

1Cited by

0References

15Claims

0Family size

Assignee

Robert Bosch GmbH · DE

Inventors

Ferran Diego Andilla · Barcelona, ES
Dimitrios Bariamis · Hildesheim, DE
Masato Takami · Uji, JP
Uwe Brosch · Hohenhameln, DE

Key dates

Filing date	Oct 2, 2019
Grant date	Sep 7, 2021
Priority date	—
Expiry date	Dec 31, 2039

Classification

Technology area (CPC G)Physics
CPC primaryG06V10/82
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Method for the calculation resource-saving semantic segmentation of image data of an imaging sensor with the aid of an artificial neural network, in particular, of a convolutional neural network, the artificial neural network including an encoder path, a decoder path, the encoder path transitioning into the decoder path, the transition taking place via a discriminative path, the following steps taking place in the discriminative path: dividing an input tensor as a function of a division function into at least one first slice tensor and at least one second slice tensor, the input tensor originating from the encoder path; connecting the at least one first slice tensor to the at least one second slice tensor as a function of a connection function in order to obtain a class tensor; and outputting the class tensor to the decoder path of the neural network.

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