Volume 39, Number 4, August 2021
|Page(s)||876 - 882|
|Published online||23 September 2021|
Improved stereo matching algorithm based on multi-scale fusion
School of Intelligent Manufacturing, Chongqing University of Arts and Sciences, Chongqing 402160, China
2 School of Mechatronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing 400074, China
3 Special Vehicle Research Institute, Chongqing Changan Industry(Group) Co., Ltd., Chongqing 400023, China
Aiming at the low matching accuracy of local stereo matching algorithm in weak texture or discontinuous disparity areas, a stereo matching algorithm combining multi-scale fusion of convolutional neural network (CNN) and feature pyramid structure (FPN) is proposed. The feature pyramid is applied on the basis of the convolutional neural network to realize the multi-scale feature extraction and fusion of the image, which improves the matching similarity of the image blocks. The guide graph filter is used to quickly and effectively complete the cost aggregation. The disparity selection stage adapts the improvement dynamic programming algorithm to obtain the initial disparity map. The initial disparity map is refined so as to obtain the final disparity map. The algorithm is trained and tested on the image provided by Middlebury data set, and the result shows that the disparity map obtained by the algorithm has good effect.
Key words: stereo matching / neural network / feature pyramid / multi-scale / guided image filter / dynamic programming
关键字 : 立体匹配 / 神经网络 / 特征金字塔 / 多尺度 / 引导图滤波器 / 动态规划
© 2021 Journal of Northwestern Polytechnical University. All rights reserved.
This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.