# American Institute of Mathematical Sciences

## Night panoramic image stitching algorithm based on cyclic symmetric structure

 1 Graduate School of Advanced Imaging Science, Multimedia and Film, Chung-Ang University, Seoul 06974, Korea 2 Department of Environmental Art Design, Arts Academy, Qingdao University of Science and Technology, Qingdao 266061, China 3 Medical Beauty, The Affiliated Hospital of Qingdao University, Qingdao 266000, China

* Corresponding author: Joonki Paik

Received  March 2019 Revised  April 2019 Published  December 2019

Aiming at the problem that the current stitching image has poor visual effect and low stitching efficiency when performing the night panoramic image stitching task, a night panoramic image stitching algorithm based on cyclic symmetric structure is proposed. In this algorithm, appropriate image acquisition method is used and the image obtained by the acquisition is smoothed, edge sharpened, geometrically corrected, etc. The position of the key point of the preprocessed image and the corresponding scale are determined by Gaussian function, and the direction value is assigned to the feature point to generate the feature descriptor, so as to realize the image edge feature extraction; on this basis, the edge feature points are hierarchically segmented according to the topological structure of the edge feature point set of target image, and the edge feature point registration of night panoramic image is completed; the cyclic symmetric structure is used to make the discrete Fourier transform of the target image, in order to reduce the amount of calculation; according to the gradient value and correlation coefficient of each pixel neighborhood in the overlapping region, the stitching line is searched to overcome the ghost image of the image after registration and realize seamless stitching of night panoramic image. The experimental results show that the proposed algorithm can effectively preserve the texture information of the original image while eliminating the smooth transition of the stitching seam, and at the same time, it has better stitching effect and stitching efficiency for the images under different conditions.

Citation: Sun Hao, Yuanxin Miao, Joonki Paik. Night panoramic image stitching algorithm based on cyclic symmetric structure. Discrete & Continuous Dynamical Systems - S, doi: 10.3934/dcdss.2020198
##### References:

show all references

##### References:
Reference image
Image to be registered
Stitching effect of the algorithm in reference [6]
Stitching effect of the algorithm in reference [7]
Stitching effect of the proposed algorithm
Comparison of the evaluation indexes of image stitching effect
 Evaluation index Proposed algorithm Algorithm in the reference [6] Algorithm in the reference [7] Information entropy 7.5342 7.3185 7.1799 Standard deviation 53.8867 52.9017 48.3676 Mutual information 8.5249 8.5407 8.5574 Average gradient 0.9982 0.9924 0.9779
 Evaluation index Proposed algorithm Algorithm in the reference [6] Algorithm in the reference [7] Information entropy 7.5342 7.3185 7.1799 Standard deviation 53.8867 52.9017 48.3676 Mutual information 8.5249 8.5407 8.5574 Average gradient 0.9982 0.9924 0.9779
Comparison of parameters of ghost removal effect
 Experimental team Evaluation index Algorithm in the reference [6] Algorithm in the reference [7] Proposed algorithm Group with small gray difference Spatial frequency activity 0.0265 0.0366 0.0264 Structural contrast 1.2292 1.2002 1.1602 Comprehensive evaluation index constructed by the two 1.2353 1.3974 1.1763 Group with large gray difference Spatial frequency activity 0.1047 0.1054 0.1044 Structural contrast 1.3795 1.2764 1.1345 Comprehensive evaluation index constructed by the two 1.4094 1.3622 1.2847 Regular texture group Spatial frequency activity 0.0342 0.0342 0.0342 Structural contrast 1.2280 1.3244 1.2343 Comprehensive evaluation index constructed by the two 1.3667 1.4122 1.3635 Irregular texture group Spatial frequency activity 0.1652 0.0602 0.0545 Structural contrast 1.2215 1.0002 0.9675 Comprehensive evaluation index constructed by the two 1.4122 0.8829 0.8848
 Experimental team Evaluation index Algorithm in the reference [6] Algorithm in the reference [7] Proposed algorithm Group with small gray difference Spatial frequency activity 0.0265 0.0366 0.0264 Structural contrast 1.2292 1.2002 1.1602 Comprehensive evaluation index constructed by the two 1.2353 1.3974 1.1763 Group with large gray difference Spatial frequency activity 0.1047 0.1054 0.1044 Structural contrast 1.3795 1.2764 1.1345 Comprehensive evaluation index constructed by the two 1.4094 1.3622 1.2847 Regular texture group Spatial frequency activity 0.0342 0.0342 0.0342 Structural contrast 1.2280 1.3244 1.2343 Comprehensive evaluation index constructed by the two 1.3667 1.4122 1.3635 Irregular texture group Spatial frequency activity 0.1652 0.0602 0.0545 Structural contrast 1.2215 1.0002 0.9675 Comprehensive evaluation index constructed by the two 1.4122 0.8829 0.8848
Time-consuming of general image stitching
 Time consuming/s Algorithm Algorithm in reference [6] Algorithm in reference [7] Proposed algorithm Time-consuming for feature extraction/s 2.450 1.555 0.136 Descriptor generation time/s 17.056 7.437 8.123 Stitching time/s 10.540 2.445 1.286 Total time 30.046 11.437 9.545
 Time consuming/s Algorithm Algorithm in reference [6] Algorithm in reference [7] Proposed algorithm Time-consuming for feature extraction/s 2.450 1.555 0.136 Descriptor generation time/s 17.056 7.437 8.123 Stitching time/s 10.540 2.445 1.286 Total time 30.046 11.437 9.545
Time-consuming of image stitching wit uneven illumination
 Time consuming/s Algorithm Algorithm in reference [6] Algorithm in reference [7] Proposed algorithm Time-consuming for feature extraction/s 2.274 1.453 0.115 Descriptor generation time/s 12.502 3.274 5.126 Stitching time/s 8.869 2.158 1.130 Total time 23.654 6.885 6.371
 Time consuming/s Algorithm Algorithm in reference [6] Algorithm in reference [7] Proposed algorithm Time-consuming for feature extraction/s 2.274 1.453 0.115 Descriptor generation time/s 12.502 3.274 5.126 Stitching time/s 8.869 2.158 1.130 Total time 23.654 6.885 6.371
Time-consuming of rotation image stitching
 Time consuming/s Algorithm Algorithm in reference [6] Algorithm in reference [7] Proposed algorithm Time-consuming for feature extraction/s 2.161 1.439 0.117 Descriptor generation time/s 10.359 3.322 5.480 Stitching time/s 7.794 2.979 1.198 Total time 20.314 7.740 6.795
 Time consuming/s Algorithm Algorithm in reference [6] Algorithm in reference [7] Proposed algorithm Time-consuming for feature extraction/s 2.161 1.439 0.117 Descriptor generation time/s 10.359 3.322 5.480 Stitching time/s 7.794 2.979 1.198 Total time 20.314 7.740 6.795
Time-consuming of scaling image stitching
 Time consuming/s Algorithm Algorithm in reference [6] Algorithm in reference [7] Proposed algorithm Time-consuming for feature extraction/s 2.472 1.548 0.130 Descriptor generation time/s 17.131 3.484 5.509 Stitching time/s 8.612 2.845 1.224 Total time 28.215 7.877 6.683
 Time consuming/s Algorithm Algorithm in reference [6] Algorithm in reference [7] Proposed algorithm Time-consuming for feature extraction/s 2.472 1.548 0.130 Descriptor generation time/s 17.131 3.484 5.509 Stitching time/s 8.612 2.845 1.224 Total time 28.215 7.877 6.683
 [1] Hadi Khatibzadeh, Vahid Mohebbi, Mohammad Hossein Alizadeh. On the cyclic pseudomonotonicity and the proximal point algorithm. Numerical Algebra, Control & Optimization, 2018, 8 (4) : 441-449. doi: 10.3934/naco.2018027 [2] Duanzhi Zhang. $P$-cyclic symmetric closed characteristics on compact convex $P$-cyclic symmetric hypersurface in R2n. Discrete & Continuous Dynamical Systems - A, 2013, 33 (2) : 947-964. doi: 10.3934/dcds.2013.33.947 [3] Wenzhong Zhu, Huanlong Jiang, Erli Wang, Yani Hou, Lidong Xian, Joyati Debnath. X-ray image global enhancement algorithm in medical image classification. Discrete & Continuous Dynamical Systems - S, 2019, 12 (4&5) : 1297-1309. doi: 10.3934/dcdss.2019089 [4] Eric Bedford, Kyounghee Kim. Degree growth of matrix inversion: Birational maps of symmetric, cyclic matrices. Discrete & Continuous Dynamical Systems - A, 2008, 21 (4) : 977-1013. doi: 10.3934/dcds.2008.21.977 [5] Lacramioara Grecu, Constantin Popa. Constrained SART algorithm for inverse problems in image reconstruction. Inverse Problems & Imaging, 2013, 7 (1) : 199-216. doi: 10.3934/ipi.2013.7.199 [6] Tianran Zhang. Traveling waves for a reaction-diffusion model with a cyclic structure. Discrete & Continuous Dynamical Systems - B, 2020, 25 (5) : 1859-1870. doi: 10.3934/dcdsb.2020006 [7] Jie Huang, Xiaoping Yang, Yunmei Chen. A fast algorithm for global minimization of maximum likelihood based on ultrasound image segmentation. Inverse Problems & Imaging, 2011, 5 (3) : 645-657. doi: 10.3934/ipi.2011.5.645 [8] Shi Yan, Jun Liu, Haiyang Huang, Xue-Cheng Tai. A dual EM algorithm for TV regularized Gaussian mixture model in image segmentation. Inverse Problems & Imaging, 2019, 13 (3) : 653-677. doi: 10.3934/ipi.2019030 [9] Rongliang Chen, Jizu Huang, Xiao-Chuan Cai. A parallel domain decomposition algorithm for large scale image denoising. Inverse Problems & Imaging, 2019, 13 (6) : 1259-1282. doi: 10.3934/ipi.2019055 [10] Xuefeng Zhang, Hui Yan. Image enhancement algorithm using adaptive fractional differential mask technique. Mathematical Foundations of Computing, 2019, 2 (4) : 347-359. doi: 10.3934/mfc.2019022 [11] Yi Zhang, Xiao-Li Ma. Research on image digital watermarking optimization algorithm under virtual reality technology. Discrete & Continuous Dynamical Systems - S, 2019, 12 (4&5) : 1427-1440. doi: 10.3934/dcdss.2019098 [12] Jiangchuan Fan, Xinyu Guo, Jianjun Du, Weiliang Wen, Xianju Lu, Brahmani Louiza. Analysis of the clustering fusion algorithm for multi-band color image. Discrete & Continuous Dynamical Systems - S, 2019, 12 (4&5) : 1233-1249. doi: 10.3934/dcdss.2019085 [13] Xin Li, Ziguan Cui, Linhui Sun, Guanming Lu, Debnath Narayan. Research on iterative repair algorithm of Hyperchaotic image based on support vector machine. Discrete & Continuous Dynamical Systems - S, 2019, 12 (4&5) : 1199-1218. doi: 10.3934/dcdss.2019083 [14] Yukio Kan-On. Structure on the set of radially symmetric positive stationary solutions for a competition-diffusion system. Conference Publications, 2013, 2013 (special) : 427-436. doi: 10.3934/proc.2013.2013.427 [15] Yunmei Chen, Xiaojing Ye, Feng Huang. A novel method and fast algorithm for MR image reconstruction with significantly under-sampled data. Inverse Problems & Imaging, 2010, 4 (2) : 223-240. doi: 10.3934/ipi.2010.4.223 [16] Editorial Office. Retraction: Xiaohong Zhu, Zili Yang and Tabharit Zoubir, Research on the matching algorithm for heterologous image after deformation in the same scene. Discrete & Continuous Dynamical Systems - S, 2019, 12 (4&5) : 1281-1281. doi: 10.3934/dcdss.2019088 [17] Behrouz Kheirfam. A full Nesterov-Todd step infeasible interior-point algorithm for symmetric optimization based on a specific kernel function. Numerical Algebra, Control & Optimization, 2013, 3 (4) : 601-614. doi: 10.3934/naco.2013.3.601 [18] Yanqin Bai, Lipu Zhang. A full-Newton step interior-point algorithm for symmetric cone convex quadratic optimization. Journal of Industrial & Management Optimization, 2011, 7 (4) : 891-906. doi: 10.3934/jimo.2011.7.891 [19] Sai Gong, Jiawu Li, Peng Tang. Spanwise effect of vortex-induced vibration of bridge beam based on symmetric algorithm. Discrete & Continuous Dynamical Systems - S, 2018, 0 (0) : 0-0. doi: 10.3934/dcdss.2020262 [20] Abdel-Rahman Hedar, Ahmed Fouad Ali, Taysir Hassan Abdel-Hamid. Genetic algorithm and Tabu search based methods for molecular 3D-structure prediction. Numerical Algebra, Control & Optimization, 2011, 1 (1) : 191-209. doi: 10.3934/naco.2011.1.191

2018 Impact Factor: 0.545