# Feature Point Matching Method for Aerial Image Based on Recursive Diffusion Algorithm

^{1}

^{2}

^{*}

## Abstract

**:**

## 1. Introduction

## 2. Methodology

#### 2.1. Dividing of Density Nodes

#### 2.2. Marking of High-Density Nodes

#### 2.3. Extracting of High-Density Areas

#### 2.3.1. Data Structure

#### 2.3.2. Logical Design

#### 2.3.3. Model Construction

#### 2.3.4. Coordinate Position Update

#### 2.4. Matching of Feature Points

## 3. Results and Discussion

#### 3.1. Matching Results of the Diffusion Recursive Algorithm

#### 3.2. Comparison with the Mean Shift Algorithm

#### 3.3. Comparison with the Correlation Coefficient Matching Algorithm

#### 3.4. Analysis of Matching Accuracy and Timing Performance

## 4. Conclusions

## Author Contributions

## Funding

## Acknowledgments

## Conflicts of Interest

## References

- Hassaballah, M.; Abdelmgeid, A.A.; Alshazly, H.A. Image Features Detection, Description and Matching. In Image Feature Detectors and Descriptors; Awad, A., Hassaballah, M., Eds.; Springer: Cham, Switzerland, 2016; Volume 630, pp. 11–45. [Google Scholar]
- Chen, L.; Rottensteiner, F.; Heipke, C. Feature detection and description for image matching: From hand-crafted design to deep learning. Geo-Spat. Inf. Sci.
**2020**. [Google Scholar] [CrossRef] - Lowe, D.G. Object Recognition from Local Scale-Invariant Features. In Proceedings of the IEEE International Conference on Computer Vision, Kerkyra, Greece, 20–27 September 1999; pp. 1150–1157. [Google Scholar]
- Lowe, D.G. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis.
**2004**, 60, 91–110. [Google Scholar] [CrossRef] - Brown, M.; Lowe, D.G. Automatic panoramic image stitching using invariant features. Int. J. Comput. Vis.
**2007**, 74, 59–73. [Google Scholar] [CrossRef] [Green Version] - Rublee, E.; Rabaud, V.; Konolige, K.; Bradski, G. ORB: An efficient alternative to SIFT or SURF. In Proceedings of the IEEE International Conference on Computer Vision, Barcelona, Spain, 6–13 November 2011; pp. 2564–2571. [Google Scholar]
- Dellinger, F.; Delon, J.; Gousseau, Y.; Michel, J.; Tupin, F. SAR-SIFT: A SIFT-Like Algorithm for SAR Images. IEEE Trans. Geosci. Remote Sens.
**2015**, 53, 453–466. [Google Scholar] [CrossRef] [Green Version] - Liu, Y.; Liu, S.P.; Wang, Z.F. Multi-focus image fusion with dense SIFT. Inf. Fusion
**2015**, 23, 139–155. [Google Scholar] [CrossRef] - Shi, H.T.; Guo, L.; Tan, S.; Li, G.; Sun, J. Improved Parallax Image Stitching Algorithm Based on Feature Block. Symmetry
**2019**, 11, 348. [Google Scholar] [CrossRef] [Green Version] - Yang, J.R.; Huang, J.W.; Jiang, Z.Y.; Dong, S.B.; Tang, L.Q.; Liu, Y.P.; Liu, Z.J.; Zhou, L.C. 3D SIFT aided path independent digital volume correlation and its GPU acceleration. Opt. Lasers Eng.
**2021**, 136, 106323. [Google Scholar] [CrossRef] - Fukunaga, K.; Hostetler, L.D. The Estimation of the Gradient of a Density Function, with Applications in Pattern Recognition. IEEE Trans. Inf. Theory
**1975**, 21, 32–40. [Google Scholar] [CrossRef] [Green Version] - Comaniciu, D.; Meer, P. Mean shift: A robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Mach. Intell.
**2002**, 24, 603–619. [Google Scholar] [CrossRef] [Green Version] - Subbarao, R.; Meer, P. Nonlinear Mean shift over Riemannian Manifolds. Int. J. Comput. Vis.
**2009**, 84, 1–20. [Google Scholar] [CrossRef] [Green Version] - Anand, S.; Mittal, S.; Tuzel, O.; Meer, P. Semi-Supervised Kernel Mean Shift Clustering. IEEE Trans. Pattern Anal. Mach. Intell.
**2014**, 36, 1201–1215. [Google Scholar] [CrossRef] - Hu, X.Y.; Li, Y.J.; Shan, J.; Zhang, J.Q.; Zhang, Y.J. Road Centerline Extraction in Complex Urban Scenes From LiDAR Data Based on Multiple Features. IEEE Trans. Geosci. Remote Sens.
**2014**, 52, 7448–7456. [Google Scholar] - Feng, Q.; Wang, T.J.; Liu, F.; Lin, H.F. Research on multi-camera information fusion method for intelligent perception. Multimed. Tools Appl.
**2018**, 77, 15003–15026. [Google Scholar] - Yue, L.W.; Li, H.J.; Zheng, X.W. Distorted Building Image Matching with Automatic Viewpoint Rectification and Fusion. Sensors
**2019**, 19, 5205. [Google Scholar] [CrossRef] [Green Version] - Duraisamy, P.; Jackson, S. Orthogonal Detection and Registration for Microstructures Images. In Proceedings of the IEEE International Conference on Communication and Computer Vision, Coimbatore, India, 20–21 December 2013; pp. 1–6. [Google Scholar]
- Won, I.; Jeong, J.; Yang, H.; Kwon, J.; Jeong, D. Adaptive Image Matching Using Discrimination of Deformable Object. Symmetry
**2016**, 8, 68. [Google Scholar] [CrossRef] [Green Version] - Jeong, J.; Won, I.; Yang, H.; Lee, B.; Jeong, D. Deformable Object Matching Algorithm Using Fast Agglomerative Binary Search Tree Clustering. Symmetry
**2017**, 9, 25. [Google Scholar] [CrossRef] [Green Version] - Ma, J.Y.; Zhou, H.B.; Zhao, J.; Gao, Y.; Jiang, J.J.; Tian, J.W. Robust Feature Matching for Remote Sensing Image Registration via Locally Linear Transforming. IEEE Trans. Geosci. Remote Sens.
**2015**, 53, 6469–6481. [Google Scholar] [CrossRef] - Ma, J.Y.; Jiang, J.J.; Zhou, H.B.; Zhao, J.; Guo, X.J. Guided Locality Preserving Feature Matching for Remote Sensing Image Registration. IEEE Trans. Geosci. Remote Sens.
**2018**, 56, 4435–4447. [Google Scholar] [CrossRef] - Ma, J.Y.; Zhao, J.; Jiang, J.J.; Zhou, H.B.; Guo, X.J. Locality Preserving Matching. Int. J. Comput. Vis.
**2019**, 127, 512–531. [Google Scholar] [CrossRef] - Abdel-Basset, M.; Manogaran, G.; Fakhry, A.E.; El-Henawy, I. 2-Levels of clustering strategy to detect and locate copy-move forgery in digital images. Multimed. Tools Appl.
**2020**, 79, 5419–5437. [Google Scholar] [CrossRef] - Simo-Serra, E.; Trulls, E.; Ferraz, L.; Kokkinos, I.; Fua, P.; Moreno-Noguer, F. Discriminative Learning of Deep Convolutional Feature Point Descriptors. In Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 11–18 December 2015; pp. 118–126. [Google Scholar]
- Liu, Z.S.; Li, Z.X.; Zhang, J.Y.; Liu, L.G. Euclidean and Hamming Embedding for Image Patch Description with Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Las Vegas, NV, USA, 26 June–1 July 2016; pp. 1145–1151. [Google Scholar]
- Krizhevsky, A.; Sutskever, I.; Hinton, G.E. ImageNet Classification with Deep Convolutional Neural Networks. Commun. ACM
**2017**, 60, 84–90. [Google Scholar] [CrossRef] - Wang, R.Z.; Yan, J.C.; Yang, X.K. Learning Combinatorial Embedding Networks for Deep Graph Matching. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea, 27 October–2 November 2019; pp. 3056–3065. [Google Scholar]
- Kluger, F.; Brachmann, E.; Ackermann, H.; Rother, C.; Yang, M.Y.; Rosenhahn, B. CONSAC: Robust Multi-Model Fitting by Conditional Sample Consensus. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 4633–4642. [Google Scholar]

**Figure 3.**Division results of different sizes of the feature point density nodes: (

**a**) 10 × 10 pixels; (

**b**) 20 × 20 pixels; (

**c**) 40 × 40 pixels; (

**d**) 80 × 80 pixels.

**Figure 4.**Marking of high-density nodes: (

**a**) Feature points traversal; (

**b**) The number of feature points in each density node; (

**c**) The high-density nodes; (

**d**) The coordinate system.

**Figure 6.**Process of the high-density node diffusion: (

**a**) The high-density connected areas obtained by diffusion in each step; (

**b**) The diffusion process of the central high-density node in four directions.

**Figure 8.**Matching results of the diffusion recursive algorithm: (

**a**) The first set of experiments; (

**b**) The second set of experiments; (

**c**) The third set of experiments.

**Figure 10.**The first set of experiments: (

**a**) Results of the correlation coefficient matching algorithm; (

**b**) Results of the diffusion recursive algorithm.

**Figure 11.**The second set of experiments: (

**a**) Results of the correlation coefficient matching algorithm; (

**b**) Results of the diffusion recursive algorithm.

**Figure 12.**The third set of experiments: (

**a**) Results of the correlation coefficient matching algorithm; (

**b**) Results of the diffusion recursive algorithm.

The Correlation Coefficient Method | The Mean Shift Algorithm | The Diffusion Recursive Algorithm | |
---|---|---|---|

Number of successful matches | 4 | 15 | 17 |

Successful matching rate (%) | 22.2 | 83.3 | 94.4 |

Time-consumption (ms) | 7434 | 12,587 | 16,648 |

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |

© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).

## Share and Cite

**MDPI and ACS Style**

Shen, J.; Guo, X.; Zhou, W.; Zhang, Y.; Li, J.
Feature Point Matching Method for Aerial Image Based on Recursive Diffusion Algorithm. *Symmetry* **2021**, *13*, 407.
https://doi.org/10.3390/sym13030407

**AMA Style**

Shen J, Guo X, Zhou W, Zhang Y, Li J.
Feature Point Matching Method for Aerial Image Based on Recursive Diffusion Algorithm. *Symmetry*. 2021; 13(3):407.
https://doi.org/10.3390/sym13030407

**Chicago/Turabian Style**

Shen, Jiayan, Xiucheng Guo, Wenzong Zhou, Yiming Zhang, and Juchen Li.
2021. "Feature Point Matching Method for Aerial Image Based on Recursive Diffusion Algorithm" *Symmetry* 13, no. 3: 407.
https://doi.org/10.3390/sym13030407