Matching method of heterologous stereo image pairs based on deep learning

doi:10.13474/j.cnki.11-2246.2022.0369

Abstract

Abstract: Compared with stereo matching of homologous images, there are great differences in spatial features, field angle and resolution between the heterogenous images acquired by UAV tilt photography and close-range photography, which bring difficulties to image matching. In this paper, the feature points are extracted by using the convolutional neural network based on homography transformation, and the graph neural network with cross-attention mechanism is used to match the feature points in the matching stage. It overcomes the problem of poor matching effect caused by large disparity and distorted transformation between different images. In this paper, Ma jiacitang in Dacheng county, Langfang city, Hebei province is taken as the experimental data, and the matching effect of traditional SURF (accelerated robust feature) algorithm and deep learning algorithm is compared. The results show that the algorithm based on deep learning has a higher matching rate for heterologous images with large perspective differences.

Key words: SURF algorithm, heterologous images, homography matrix, figure neural network, feature matching

CLC Number:

P237

DUAN Yunshan, WU Xianwen, WANG Ruirui, SHI Wei, LI Yiran. Matching method of heterologous stereo image pairs based on deep learning[J]. Bulletin of Surveying and Mapping, 2022, 0(12): 131-135.

References

[1] 吕倩利, 邵永社. 基于SIFT特征的异源遥感影像匹配方法研究[J]. 计算机工程与应用, 2012, 48(36):171-176.
[2] 戴激光, 宋伟东, 贾永红, 等. 一种新的异源高分辨率光学卫星遥感影像自动匹配算法[J]. 测绘学报, 2013, 42(1):80-86.
[3] 王瑞琛. 基于深层神经网络的异源图像特征学习及块匹配[D]. 北京:北京邮电大学, 2018.
[4] 付宇光, 唐焕文, 计明军, 等. 模拟退火算法在图像配准中的应用[J]. 中国生物医学工程学报, 2004, 23(5):405-409.
[5] 严春满, 王铖. 卷积神经网络模型发展及应用[J]. 计算机科学与探索, 2021, 15(1):27-46.
[6] 常亮, 邓小明, 周明全, 等. 图像理解中的卷积神经网络[J]. 自动化学报, 2016, 42(9):1300-1312.
[7] 刘非凡, 张爽, 罗双玲, 等. 基于深度图神经网络方法的领域知识结构探测[J]. 情报学报, 2021, 40(11):1209-1220.
[8] 白铂, 刘玉婷, 马驰骋, 等. 图神经网络[J]. 中国科学:数学, 2020, 50(3):367-384.
[9] BAY H, TUYTELAARS T, VAN GOOL L. SURF:speeded up robust features[C]//Proceedings of Computer Vision-ECCV 2006. Berlin, Heidelberg:Springer Berlin Heidelberg, 2006:404-417.
[10] DETONE D, MALISIEWICZ T, RABINOVICH A. Toward geometric deep SLAM[EB/OL].[2021-10-30]. https://arxiv.org/abs/1707.07410.
[11] AMINTABAR A, BOUFAMA B. Homography-based plane identification and matching[C]//Proceedings of IEEE International Conference on Image Processing. San Diego:IEEE, 2008:297-300.
[12] DETONE D, MALISIEWICZ T, RABINOVICH A. Deep image homography estimation[EB/OL].[2021-10-30] https://arxiv.org/abs/1606.03798.
[13] THEKUMPARAMPIL K K, WANG CHONG, OH S, et al. Attention-based graph neural network for semi-supervised learning[EB/OL].[2021-10-30]. https://arxiv.org/abs/1803.03735.
[14] 车令夫, 田宇坤, 朱海平, 等. 基于最优输运的迁移学习[J]. 模式识别与人工智能, 2019, 32(6):481-493.