Stereo depth estimation using deep neural networks

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 ster...

Full description

Saved in:
Bibliographic Details
Main Authors Kamenev, Alexey, Birchfield, Stan, Smolyanskiy, Nikolai
Format Patent
LanguageEnglish
Published 16.07.2024
Subjects
ANALOGOUS ARRANGEMENTS USING OTHER WAVES
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES
ELECTRIC DIGITAL DATA PROCESSING
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION ORRERADIATION OF RADIO WAVES
MEASURING
PHYSICS
RADIO DIRECTION-FINDING
RADIO NAVIGATION
TESTING
Online AccessGet full text

Cover

More Information
Summary: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.
Bibliography:Application Number: US202318160694