Abstract
Abstract. Large-scale Digital Surface Model (DSM) generated with high-resolution satellite images (HRSI) are comparable, cheaper, and more accessible when comparing to Light Detection and Ranging (LiDAR) data and aerial remotely sensed images. Several photogrammetric commercial/open-source software packages are being developed for satellite image-based 3D reconstruction, in which, most of them adopt a modified version of Semi-Global Matching (SGM) algorithm for dense image matching. With the continuous development of matching cost computation methods, the existing methods can be divided into classical (low-level) and learning-based algorithms (non-end-to-end learning and end-to-end learning methods). On Middlebury and KITTI datasets, learning-based algorithms has shown their superiority compared to SGM derived methods. In this context, we assume that matching cost is the key factor of DIM. This paper reviews and evaluates Census Transform, and MC-CNN on a WorldView-3 typical city scene satellite stereo images on the premise that the overall SGM framework remains unchanged, providing a preliminary comparison for academic and industrial. We first compute the cost valume of these two methods, obtains the final DSM after semi-global optimization, and compares their gemetric accuracy with the corresponding LiDAR derived ground truth. We presented our comparison and findings in the experimental section.
Highlights
An algorithm computing Matching Cost based on Convolutional Neural Networks (MC-CNN) is proposed recently (Zbontar & Lecun, 2015, 2016), based on the appearance similarity of stereo image patches and outperforms many previous methods on KITTI2012 (Geiger et al, 2013), KITTI 2015 (Menze and Geiger, 2015), and Middlebury (Scharstein and Szeliski, 2002, 2003; Scharstein and Pal, 2007; Hirschmueller and Scharstein, 2009; Scharstein et al, 2014) stereo datasets
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLIII-B2-2021 XXIV ISPRS Congress (2021 edition). This paper reviewed both classical and learning based matching cost computation methods for dense image matching with highresolution satellite images
We summarised the matching cost computation method based on Census transform as Figure 1
Summary
The orientation parameters are provided as Rational Polynomial Coefficients (RPC) files by different satellite image vendors, which helps both in hiding the physical sensor model and allowing high accurate mapping and surveying (Gong, 2003; Gong et al, 2020). This paper reviewed both classical and learning based matching cost computation methods for dense image matching with highresolution satellite images.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have