期刊
REMOTE SENSING
卷 13, 期 2, 页码 -出版社
MDPI
DOI: 10.3390/rs13020274
关键词
large baseline; oblique stereo images; affine invariant features; convolutional neural network; deep learning; least square matching
类别
资金
- National Natural Science Foundation of China [41601489]
- Shandong Provincial Natural Science Foundation [ZR2015DQ007]
- Postgraduate Education and Teaching Reform Foundation of Shandong Province [SDYJG19115]
The study introduces an affine invariant feature matching algorithm based on deep learning framework, which achieves high quality descriptor generation and corresponding feature matching by modifying the Hessian affine network and introducing an empirical weighted loss function. Experimental results demonstrate the method's superior performance in accuracy of matching across oblique stereo images.
The available stereo matching algorithms produce large number of false positive matches or only produce a few true-positives across oblique stereo images with large baseline. This undesired result happens due to the complex perspective deformation and radiometric distortion across the images. To address this problem, we propose a novel affine invariant feature matching algorithm with subpixel accuracy based on an end-to-end convolutional neural network (CNN). In our method, we adopt and modify a Hessian affine network, which we refer to as IHesAffNet, to obtain affine invariant Hessian regions using deep learning framework. To improve the correlation between corresponding features, we introduce an empirical weighted loss function (EWLF) based on the negative samples using K nearest neighbors, and then generate deep learning-based descriptors with high discrimination that is realized with our multiple hard network structure (MTHardNets). Following this step, the conjugate features are produced by using the Euclidean distance ratio as the matching metric, and the accuracy of matches are optimized through the deep learning transform based least square matching (DLT-LSM). Finally, experiments on Large baseline oblique stereo images acquired by ground close-range and unmanned aerial vehicle (UAV) verify the effectiveness of the proposed approach, and comprehensive comparisons demonstrate that our matching algorithm outperforms the state-of-art methods in terms of accuracy, distribution and correct ratio. The main contributions of this article are: (i) our proposed MTHardNets can generate high quality descriptors; and (ii) the IHesAffNet can produce substantial affine invariant corresponding features with reliable transform parameters.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据