The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLIII-B2-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 163–167, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-163-2020
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLIII-B2-2020, 163–167, 2020
https://doi.org/10.5194/isprs-archives-XLIII-B2-2020-163-2020

  12 Aug 2020

12 Aug 2020

UNSUPERVISED MULTI-CONSTRAINT DEEP NEURAL NETWORK FOR DENSE IMAGE MATCHING

W. Yuan1,2, Z. Fan2, X. Yuan1, J. Gong1, and R. Shibasaki2 W. Yuan et al.
  • 1Center for Spatial Information Science, University of Tokyo, 5-1-5, Kashiwa, Chiba, Japan
  • 2Wuhan University, School of Remote Sensing and Information Engineering, 129 Luoyu Road Wuhan, Hubei, China

Keywords: Multi-Constraint, Unsupervised Learning, Dense Image Matching, Deep Neural Network, Photo Consistency, Matching Accuracy

Abstract. Dense image matching is essential to photogrammetry applications, including Digital Surface Model (DSM) generation, three dimensional (3D) reconstruction, and object detection and recognition. The development of an efficient and robust method for dense image matching has been one of the technical challenges due to high variations in illumination and ground features of aerial images of large areas. Nowadays, due to the development of deep learning technology, deep neural network-based algorithms outperform traditional methods on a variety of tasks such as object detection, semantic segmentation and stereo matching. The proposed network includes cost-volume computation, cost-volume aggregation, and disparity prediction. It starts with a pre-trained VGG-16 network as a backend and using the U-net architecture with nine layers for feature map extraction and a correlation layer for cost volume calculation, after that a guided filter based cost aggregation is adopted for cost volume filtering and finally the soft Argmax function is utilized for disparity prediction. The experimental conducted on a UAV dataset demonstrated that the proposed method achieved the RMSE (root mean square error) of the reprojection error better than 1 pixel in image coordinate and in-ground positioning accuracy within 2.5 ground sample distance. The comparison experiments on KITTI 2015 dataset shows the proposed unsupervised method even comparably with other supervised methods.