Stereo Matching Method Based on Space-Aware Network Model  

作　　者：Jilong Bian Jinfeng Li 

机构地区：[1]College of Information&Computer Engineering,Northeast Forestry University,Harbin,150040,China [2]College of Computer&Information Technology,Mudanjiang Normal University,Mudanjiang,157011,China

出　　处：《Computer Modeling in Engineering & Sciences》2021年第4期175-189,共15页工程与科学中的计算机建模（英文）

基　　金：This work was supported in part by the Heilongjiang Provincial Natural Science Foundation of China under Grant F2018002;the Research Funds for the Central Universities under Grants 2572016BB11 and 2572016BB12;the Foundation of Heilongjiang Education Department under Grant 1354MSYYB003.

摘　　要：The stereo matching method based on a space-aware network is proposed, which divides the network into threesections: Basic layer, scale layer, and decision layer. This division is beneficial to integrate residue network and densenetwork into the space-aware network model. The vertical splitting method for computing matching cost by usingthe space-aware network is proposed for solving the limitation of GPU RAM. Moreover, a hybrid loss is broughtforward to boost the performance of the proposed deep network. In the proposed stereo matching method, thespace-aware network is used to calculate the matching cost and then cross-based cost aggregation and semi-globalmatching are employed to compute a disparity map. Finally, a disparity-post processing method is utilized suchas subpixel interpolation, median filter, and bilateral filter. The experimental results show this method has a goodperformance on running time and accuracy, with a percentage of erroneous pixels of 1.23% on KITTI 2012 and1.94% on KITTI 2015.

关 键 词：Deep learning stereo matching space-aware network hybrid loss 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]