Abstract
This paper presents a novel two-view Structure-from-Motion (SfM) algorithm with the application of multiple Feature Detector Operators (FDO). The key of this study is the implementation of multiple FDOs into a two-view SfM algorithm. The two-view SfM algorithm workflow can be divided into three general steps: feature detection and matching, pose estimation and point cloud (PCL) generation. The experimental results, the quantitative analyses and a comparison with existing algorithms demonstrate that the implementation of multiple FDOs can effectively improve the performance of a two-view SfM algorithm. Firstly, in the Oxford test dataset, the RMSE reaches on average 0.11 m (UBC), 0.36 m (bikes), 0.52 m (trees) and 0.37 m (Leuven). This proves that illumination changes, blurring and JPEG compression can be handled satisfactorily. Secondly, in the EPFL dataset, the number of features lost in the processes is 21% with a total PCL of 27,673 pt, and this is only minimally higher than ORB (20.91%) with a PCL of 10,266 pt. Finally, the verification process with a real-world unmanned aerial vehicle (UAV) shows that the point cloud is denser around the edges, the corners and the target, and the process speed is much faster than existing algorithms. Overall, the framework proposed in this study has been proven a viable alternative to a classical procedure, in terms of performance, efficiency and simplicity.
Subject
General Earth and Planetary Sciences
Reference75 articles.
1. Unninayar, S., and Olsen, L.M. (2015). Reference Module in Earth Systems and Environmental Sciences, Elsevier.
2. Lin, C.-H., Ma, W.-C., Torralba, A., and Lucey, S. (2021, January 10–17). BARF: Bundle-Adjusting Neural Radiance Fields. Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), Montreal, Canada.
3. Meyers, R.A. (2003). Encyclopedia of Physical Science and Technology, Academic Press. [3rd ed.].
4. Dikovski, B., Lameski, P., Zdravevski, E., and Kulakov, A. (2013, January 18–19). Structure from motion obtained from low quality images in indoor environment. Proceedings of the 10th Conference for Informatics and Information Technology (CIIT 2013), Mumbai, India.
5. Pittaluga, F., Koppal, S., Kang, S.B., and Sinha, S.N. (2019, January 16–20). Revealing Scenes by Inverting Structure from Motion Reconstructions. Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献