What is it about?
In aerial multi-view photogrammetry, whether there is a special positional distribution pattern among candidate homologous pixels of a matching pixel in the multi-view images? If so, can this positional pattern be used to precisely confirm the real homologous pixels? These problems have not been studied at present. Therefore, the study of the positional distribution pattern among candidate homologous pixels based on the adjustment theory in surveying is investigated in this paper.
Featured Image
Why is it important?
Furthermore, existing research paid little attention to following questions: whether there is a certain positional distribution pattern among candidate homologous pixels of the matching pixel in multi-view images? How to quantitatively describe this positional distribution pattern? Can this pattern be used to further refine the searching scope of candidate homologous pixels, or even to exclusively confirm the homologous pixels during multi-view image matching? Thorough investigation of these questions will prospectively enhance the accuracy, efficiency and robustness of multi-view image matching from the aspect of matching mechanism, and it has the utmost significance in resolving shortcomings of existing image matching methods.
Perspectives
To our knowledge, this is the first report of positional distribution pattern among candidate homologous pixels in multi-view images in the field of photogrammetry, and the proposed research method on this pattern is expected to provide a new thought for resolving the problems that existing image-side multi-view image matching methods face, i.e., low reliability of matching results in difficult matching regions (such as large geometric distortion, obvious radiometric difference, weak texture or repetitive texture, etc.) at a mechanism level.
Dr Ka Zhang
Nanjing Normal University
Read the Original
This page is a summary of: A discovery about the positional distribution pattern among candidate homologous pixels and its potential application in aerial multi-view image matching, Scientific Reports, May 2021, Springer Science + Business Media,
DOI: 10.1038/s41598-021-89501-z.
You can read the full text:
Resources
Contributors
The following have contributed to this page
