Abstract
Robust and rapid image dense matching is the key to large-scale three-dimensional (3D) reconstruction for multiple Unmanned Aerial Vehicle (UAV) images. However, the following problems must be addressed: (1) the amount of UAV image data is very large, but ordinary computer memory is limited; (2) the patch-based multi-view stereo-matching algorithm (PMVS) does not work well for narrow-baseline cases, and its computing efficiency is relatively low, and thus, it is difficult to meet the UAV photogrammetry’s requirements of convenience and speed. This paper proposes an Image-grouping and Self-Adaptive Patch-based Multi-View Stereo-matching algorithm (IG-SAPMVS) for multiple UAV imagery. First, multiple UAV images were grouped reasonably by a certain grouping strategy. Second, image dense matching was performed in each group and included three processes. (1) Initial feature-matching consists of two steps: The first was feature point detection and matching, which made some improvements to PMVS, according to the characteristics of UAV imagery. The second was edge point detection and matching, which aimed to control matching propagation during the expansion process; (2) The second process was matching propagation based on the self-adaptive patch. Initial patches were built that were centered by the obtained 3D seed points, and these were repeatedly expanded. The patches were prevented from crossing the discontinuous terrain by using the edge constraint, and the extent size and shape of the patches could automatically adapt to the terrain relief; (3) The third process was filtering the erroneous matching points. Taken the overlap problem between each group of 3D dense point clouds into account, the matching results were merged into a whole. Experiments conducted on three sets of typical UAV images with different texture features demonstrate that the proposed algorithm can address a large amount of UAV image data almost without computer memory restrictions, and the processing efficiency is significantly better than that of the PMVS algorithm and the matching accuracy is equal to that of the state-of-the-art PMVS algorithm.
Highlights
The image sequences of Unmanned Aerial Vehicle (UAV) low-altitude photogrammetry are characterized by large scale, high resolution and rich texture information, which make it suitable for three-dimensional (3D) observation and its role as a primary source of fine 3D data [1,2]
Self-Adaptive Patch-based Multi-View Stereo-matching algorithm (SAPMVS) is partitioned into three parts: (1) multi-view initial feature-matching, which is introduced in Section 2.3.1; (2) matching propagation based on the self-adaptive patch, which is introduced in Section 2.3.3; (3) filtering the erroneous matching points following the patch-based multi-view stereo-matching algorithm (PMVS) filtering method
We can compare them in the following aspects [58]: (1) accuracy, which indicates the degree of correct matching quantitatively; (2) reliability, which represents the degree of precluding overall classification error; (3) versatility, the ability to apply the algorithm to different image scenes; (4) complexity, the cost of equipment and calculation
Summary
The image sequences of UAV low-altitude photogrammetry are characterized by large scale, high resolution and rich texture information, which make it suitable for three-dimensional (3D) observation and its role as a primary source of fine 3D data [1,2]. As light and small low-altitude remote sensing aircraft, UAVs offer advantages such as flexibility, ease of operation, convenience, safety and reliability, and low costs [3,5,6] They can be widely used in many applications such as large-scale mapping [7], true orthophoto generation [8], environmental surveying [9], archaeology and cultural heritage [10], traffic monitoring [11], 3D city modeling [12], and especially emergency response [13]; each field contributes to the rapid development of the technology and offers extensive markets [2,14]. Reconstructing 3D models of objects based on large-scale and high-resolution image sequences obtained by UAV low-altitude photogrammetry demands rapid modeling speeds, high automaticity and low costs These attributes rely upon the technology in the digital photogrammetry and computer vision fields, and image dense matching is exactly the key to this problem. The research on and implementation of UAV multi-view stereo-matching are of great practical significance and scientific value
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 callDisclaimer: 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.
