Stereo matching algorithm based on multiscale fusion

被引：0

作者：

Xu X. ^{[1
]}

Wu J. ^{[1
]}

机构：

[1] School of Electrical and Automation Engineering, East China Jiaotong University, Nanchang

来源：

Moshi Shibie yu Rengong Zhineng/Pattern Recognition and Artificial Intelligence | 2020年 / 33卷 / 02期

基金：

中国国家自然科学基金;

关键词：

Convolutional Neural Network(CNN); Pyramid Transformation; Stereo Matching;

D O I：

10.16451/j.cnki.issn1003-6059.202002011

中图分类号：

学科分类号：

摘要：

Aiming at the problems of local stereo matching methods, such as difficulty in selecting sizes of matching windows and low accuracy of stereo matching in weak texture or highlight region, a multi-scale fusion stereo matching method is proposed by combining convolutional neural network model(CNN) and image pyramid method in this paper. By training CNN, image features of the matched image pairs are learned automatically to complete the calculation of matching cost. Based on the construction of image pyramids, the matched image pairs are expressed in multiple scale. Grounded on the template construction of weak texture region, the matching images of each layer are divided into weak texture region and rich texture region. The image of weak texture region is transformed into small-scale image to calculate the matching degree and reduce the mismatching rate of weak texture image. Then, the image is transformed back to large-scale images and fused with the matching results of rich texture regions to maintain the matching accuracy. Experiments on KITTI dataset indicate that the proposed algorithm yields a better image matching result. © 2020, Science Press. All right reserved.

引用

页码：182 / 187

页数：5

共 14 条

[1]

Liu J., Zhang J.X., Dai Y., Et al., Dense Stereo Matching Based on Cross-Scale Guided Image Filtering, Acta Optica Sinca, 38, 1, (2018)

[2]

Ma N., Meng Y.B., Meng C.G., Et al., A Small Baseline Stereo Matching Method Based on Extended Phase Correlation, Acta Electronica Sinica, 45, 8, pp. 1827-1835, (2017)

[3]

Geiger A., Roser M., Urtasun R., Efficient Large-Scale Stereo Matching, Proc of the Asian Conference on Computer Vision, pp. 25-38, (2010)

[4]

Boykov Y., Veksler O., Zabih R., Markov Random Fields with Efficient Approximations, Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 648-655, (1998)

[5]

Sun J., Zhang N.N., Shum H.Y., Stereo Matching Using Belief Propagation, IEEE Transactions on Pattern Analysis and Machine Intelligence, 25, 7, pp. 787-800, (2003)

[6]

Hirschmuller H., Accurate and Efficient Stereo Processing by Semi-global Matching and Mutual Information, Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Re-cognition, II, pp. 807-814, (2005)

[7]

Yao P., Zhang H., Xue Y.B., Et al., As-Global-As-Possible Stereo Matching with Adaptive Smoothness Prior, IET Image Processing, 13, 1, pp. 98-107, (2019)

[8]

Yin B.C., Wang W.T., Wang L.C., Review of Deep Learning, Journal of Beijing University of Technology, 41, 1, pp. 48-59, (2015)

[9]

Zhou F.Y., Jin L.P., Dong J., Review of Convolutional Neural Network, Chinese Journal of Computers, 40, 6, pp. 1229-1251, (2017)

[10]

Agoruyko S., Komodakis N., Learning to Compare Image Patches via Convolutional Neural Networks, Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Re-cognition, pp. 4353-4361, (2015)

← 1 2 →