Title:
STEREO CAMERA DEPTH DETERMINATION USING HARDWARE ACCELERATOR
Document Type and Number:
WIPO Patent Application WO/2019/109336
Kind Code:
A1
Abstract:
Described herein are systems and methods that allow for dense depth map estimation given input images. In one or more embodiments, a neural network model was developed that significantly differs from prior approaches. Embodiments of the deep neural network model comprises more computationally efficient structures and fewer layers but still produces good quality results. Also, in one or more embodiments, the deep neural network model may be specially configured and trained to operate using a hardware accelerator component or components that can speed computation and produce good results, even if lower precision bit representations are used during computation at the hardware accelerator component.
Inventors:
KANG LE (US)
LI YUPENG (CN)
QI WEI (CN)
BAO YINGZE (CN)
LI YUPENG (CN)
QI WEI (CN)
BAO YINGZE (CN)
Application Number:
PCT/CN2017/115228
Publication Date:
June 13, 2019
Filing Date:
December 08, 2017
Export Citation:
Assignee:
BAIDU COM TIMES TECH BEIJING CO LTD (CN)
BAIDU USA LLC (US)
BAIDU USA LLC (US)
International Classes:
H04N13/204
Foreign References:
| US20130156278A1 | 2013-06-20 | |||
| US20140064608A1 | 2014-03-06 | |||
| US20150170371A1 | 2015-06-18 | |||
| JP2012029169A | 2012-02-09 | |||
| TW550519B | 2003-09-01 |
Other References:
POGGI MATTEO ET AL., EFFICIENT CONFIDENCE MEASURES FOR EMBEDDED STEREO
DIAZ J ET AL., HIGH PERFORMANCE STEREO COMPUTATION ARCHITECTURE
MAYER ET AL.: "A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation", IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016
See also references of EP 3607744A4
DIAZ J ET AL., HIGH PERFORMANCE STEREO COMPUTATION ARCHITECTURE
MAYER ET AL.: "A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation", IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016
See also references of EP 3607744A4
Attorney, Agent or Firm:
INSIGHT INTELLECTUAL PROPERTY LIMITED (CN)
Download PDF:
Previous Patent: MULTI-MODE RESONATOR
Next Patent: GRAPHITE-LIKE MICROCRYSTAL CARBON NANOMATERIAL, PREPARATION METHOD THEREFOR AND USE THEREOF
Next Patent: GRAPHITE-LIKE MICROCRYSTAL CARBON NANOMATERIAL, PREPARATION METHOD THEREFOR AND USE THEREOF