Abstract
Abstract. Dense matching plays an important role in many fields, such as DEM (digital evaluation model) producing, robot navigation and 3D environment reconstruction. Traditional approaches may meet the demand of accuracy. But the calculation time and out puts density is hardly be accepted. Focus on the matching efficiency and complex terrain surface matching feasibility an aerial image dense matching method based on optical flow field is proposed in this paper. First, some high accurate and uniformed control points are extracted by using the feature based matching method. Then the optical flow is calculated by using these control points, so as to determine the similar region between two images. Second, the optical flow field is interpolated by using the multi-level B-spline interpolation in the similar region and accomplished the pixel by pixel coarse matching. Final, the results related to the coarse matching refinement based on the combined constraint, which recognizes the same points between images. The experimental results have shown that our method can achieve per-pixel dense matching points, the matching accuracy achieves sub-pixel level, and fully meet the three-dimensional reconstruction and automatic generation of DSM-intensive matching’s requirements. The comparison experiments demonstrated that our approach’s matching efficiency is higher than semi-global matching (SGM) and Patch-based multi-view stereo matching (PMVS) which verifies the feasibility and effectiveness of the algorithm.
Highlights
Dense matching is a key ingredient in automated acquisition of geometric models and 3D scenes from image sequence or videos, a process known as image-based 3D reconstruction
Methods based on deformable polygonal meshes demand a high quality start point, such as a visual hull model (Laurentini, 1994), they use this kind of start point to initialized the corresponding optimization process
semiglobal matching (SGM) and its acceleration algorithms are widely used in digital evaluation model (DEM) generation and 3D scene reconstructions (Halaa, 2012). SGM is more flexible than voxel-based and polygonal mesh-based approaches, it require fusing individual depth map into a single 3D model
Summary
Dense matching is a key ingredient in automated acquisition of geometric models and 3D scenes from image sequence or videos, a process known as image-based 3D reconstruction. Methods based on deformable polygonal meshes demand a high quality start point, such as a visual hull model (Laurentini, 1994), they use this kind of start point to initialized the corresponding optimization process Those two kinds of approaches are often limited to the datasets quality and initial processing quality, which are not flexible. Xiongwu Xiao proposed a self-adaptive patch and image grouping PMVS approach to improve the matching efficiency (Xiao, 2016) These two developed PMVS methods improved the processing efficiency. In order to deal with aerial images and improve the matching accuracy a novel optical flow field based dense matching methods for aerial image is proposed in this paper, which is characterized by large scale aerial images, complex surface terrain. The experimental results demonstrate that the proposed method is feasible and meet the demand of the DEM generation, while the matching accuracy is at the same level as PMVS and SGM, the matching efficiency is higher than PMVS and SGM
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
