7386280.pdf (964.43 kB)
Download file

Group-based atrous convolution stereo matching network

Download (964.43 kB)
journal contribution
posted on 06.12.2021, 16:28 authored by Qijie Zou, Jing Yu, Hui FangHui Fang, Jing Qin, Jie Zhang, Shengkai Liu
Stereo matching, is the key technology in stereo vision. Given a pair of rectified images, stereo matching determines correspondences between the pair images and estimate depth by obtaining disparity between corresponding pixels. Current work has shown that depth estimation from a stereo pair of images can be formulated as a supervised learning task with an end-to-end frame based on Convolutional Neural Networks (CNNs). However, 3D CNN makes a great burden on memory storage and computation, which further leads to the significantly increased computation time. To alleviate this issue, atrous convolution was proposed to reduce the number of convolutional operations via a relatively sparse receptive field. However, this sparse receptive field makes it difficult to find reliable corresponding points in fuzzy areas, e.g., occluded areas and untextured areas, owning to the loss of rich contextual information. To address this problem, we propose Group-based Atrous Convolution Spatial Pyramid Pooling (GASPP) to robustly segment objects at multiple scales with affordable computing resources. The main feature of GASPP module is to set convolutional layers with continuous dilation rate in each group, so that it can reduce the impact of holes introduced by atrous convolution on network performance. Moreover, we introduce a tailored cascade cost volume in a pyramid form to reduce memory, so as to meet real-time performance. Group-based atrous convolution stereo matching network is evaluated on the street scene benchmark KITTI 2015 and Scene Flow and achieves state-of-the-art performance.

Funding

Dalian University Research Platform Project Funding: Dalian Wise Information Technology of Med and Health Key Laboratory

National Natural Science Foundation of China (No. 11701061): Research on SA algorithm for nonconvex stochastic semidefinite programming

History

School

  • Science

Department

  • Computer Science

Published in

Wireless Communications and Mobile Computing

Volume

2021

Publisher

Hindawi

Version

VoR (Version of Record)

Rights holder

© The Authors

Publisher statement

This is an Open Access Article. It is published by Hindawi under the Creative Commons Attribution 4.0 International Licence (CC BY 4.0). Full details of this licence are available at: https://creativecommons.org/licenses/by/4.0/

Acceptance date

02/11/2021

Publication date

2021-11-28

Copyright date

2021

ISSN

1530-8669

eISSN

1530-8677

Language

en

Depositor

Dr Hui Fang. Deposit date: 10 November 2021

Article number

7386280