Patent · US Active

Stereo depth estimation using deep neural networks

US11080590B2 · kind B2 · utility

21Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMar 18, 2019
Grant dateAug 3, 2021
Priority date
Expiry dateAug 21, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06T2207/20084
  • WIPO fieldMeasurement
  • WIPO sectorInstruments

Abstract

Various examples of the present disclosure include a stereoscopic deep neural network (DNN) that produces accurate and reliable results in real-time. Both LIDAR data (supervised training) and photometric error (unsupervised training) may be used to train the DNN in a semi-supervised manner. The stereoscopic DNN may use an exponential linear unit (ELU) activation function to increase processing speeds, as well as a machine learned argmax function that may include a plurality of convolutional layers having trainable parameters to account for context. The stereoscopic DNN may further include layers having an encoder/decoder architecture, where the encoder portion of the layers may include a combination of three-dimensional convolutional layers followed by two-dimensional convolutional layers.

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