Image Mosaic Based on Local Guidance and Dark Channel Prior

Chong Zhang; Fang Xu; Dejiang Wang; He Sun

doi:10.5566/ias.3307

Authors

Chong Zhang Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences
Fang Xu
Dejiang Wang
He Sun

DOI:

https://doi.org/10.5566/ias.3307

Keywords:

dark channel, image mosaic, KAZE, local guided

Abstract

Image mosaic is of significance in various areas such as object tracking and drone reconnaissance. Aiming at the problems of poor performance and high rate of false match in foggy images, an improved stitching method based on local guided KAZE and dark channel prior is proposed. First of all, the KAZE algorithm is utilized for rough feature matching. Secondly, a local fixed point asymptotic method is introduced to optimize the global objective and eliminate mismatched point pairs. Then, the warp images are obtained by the estimated transformation matrix. Thirdly, the compensation of color and luminance difference of the overlap is applied to the overall image, which improves the inhomogeneity of stitching image. Eventually, the final result is obtained by enhancing algorithm based on dark channel prior. The proposed algorithm is assessed through intuitive renderings and quantitative values. Furthermore, the proposed method is compared with other common stitching methods. The results reveal that the method proposed in this paper gives the best performance in terms of the magnitude of feature matching pairs, the mean absolute error (MAE), the root mean square error (RMSE) and the processing time.

References

Alcantarilla PF, Bartoli A, Davison AJ (2012). KAZE features. Lect Notes Comput SC 214-27.

Brostow GJ, Fauqueur J, Cipolla R (2009). Semantic object classes in video: A high-definition ground truth database. Pattern Recogn Lett 30(2): 88-97.

Chilukuri PK, Padala P, Padala P, Desanamukula VS, Pvgd PR (2021). L, r-stitch unit: encoder-decoder-cnn based image-mosaicing mechanism for stitching non-homogeneous image sequences. IEEE Access 9, 16761-82.

Fan J, Wu Y, Li M, Liang W, Cao Y (2018). SAR and optical image registration using nonlinear diffusion and phase congruency structural descriptor. IEEE T Geosci Remote 56(9), 5368-79.

Gómez-Reyes JK, Benítez-Rangel JP, Morales-Hernández LA (2022). Image Mosaicing Applied on UAVs Survey. Appl Mech Mater 12(5), 2729.

Han LL, Wang SM, Li WJ (2018). Moving object detection based on BRISK feature in dynamic background. P Soc Photo-Opt Ins.

He K, Sun J, Tang X (2010). Single image haze removal using dark channel prior. IEEE T Pattern Anal 33(12): 2341-53.

Jong, T.K.; Bong, D.B.L (2023). An effective feature detection approach for image stitching of near-uniform scenes. Signal Process 110: 116872.

Khajehzadeh M, Taha MR, Keawsawasvong S (2022). An effective artificial intelligence approach for slope stability evaluation. IEEE Access. 10: 5660-71.

Kokul T, Anparasy S (2020). Single Image Defogging using Depth Estimation and Scene-Specific Dark Channel Prior. Proc CVPR IEEE 190-5.

Lin M, Liu T, Li Y, Miao X, He C (2022). Image stitching by disparity-guided multi-plane alignment. Signal Process 197, 108534.

Liu Y, He M, Wang Y, Sun Y, Gao X (2022). Farmland aerial images fast-stitching method and application based on improved sift algorithm. IEEE Access 10, 95411-24.

Mahto DK, Anand A, Singh AK (2022). Hybrid optimisation-based robust watermarking using denoising convolutional neural network. Soft Comput 1-12.

Nie L, Lin C, Liao K (2022). Learning edge-preserved image stitching from multi-scale deep homography. Neurocomputing 491: 533-43.

Ordóñez, Á.; Acción, Á.; Argüello, F.; Heras, D. B (2021). HSI-MSER: Hyperspectral Image Registration Algorithm Based on MSER and SIFT. IEEE J Sel Top Appl 14, 12061-72.

Peng Z, Ma Y, Zhang Y (2023). Seamless UAV hyperspectral image stitching using optimal seamline detection via graph cuts. IEEE T Geosci Remote.

Pham NT, Park S, Park CS (2021). Fast and efficient method for large-scale aerial image stitching. IEEE Access. 9, 127852-65.

Qi J, Du J, Siniscalchi SM (2020). On mean absolute error for deep neural network based vector-to-vector regression. IEEE Signal Proc Let 27: 1485-9.

Roy M, Thounaojam DM, Pal S (2022). Perceptual hashing scheme using KAZE feature descriptors for combinatorial manipulations. P Soc Photo-Opt Ins 81(20) : 29045-73.

Salehi B, Jarahizadeh S, Sarafraz A (2022). An improved RANSAC outlier rejection method for UAV-derived point cloud. Remote Sens-Basel 14(19): 4917.

Setumin S, Suandi SA (2018). Difference of Gaussian oriented gradient histogram for face sketch to photo matching. IEEE Access 6: 39344-52.

Shen Y, Peng F, Zhang Z (2019). Efficient optical proximity correction based on semi-implicit additive operator splitting. Opt Express 27(2): 1520-28.

Wan Q, Chen J, Luo L, Gong W, Wei L (2021). Drone Image Stitching Using Local Mesh-Based Bundle Adjustment and Shape-Preserving Transform. IEEE T Geosci Remote 59, 8, 7027-37.

Wang Z, Yang Z (2020). Review on image-stitching techniques. P Soc Photo-Opt Ins 26, 413–30.

Wang Z, Zhang S, Fang Z, Wang W, Zhang C, Yang G (2020). Image Stitching Algorithm Based on Improved Harris Corners Extraction. IEEE 714-18.

Xia Y, Ma J (2022). Locality-Guided Global-Preserving Optimization for Robust Feature Matching. IEEE T Image Process 31, 5093-108.

Xie Y, Wang Q, Chang Y, Zhang X (2022). Fast target recognition based on improved ORB feature. Appl Mech Mater 12(2), 786.

Zhang L, Huang H (2022). Image Stitching with Manifold Optimization. IEEE T Multimedia.

Zhang T, Zhao R, Chen Z (2020). Application of migration image registration algorithm based on improved SURF in remote sensing image mosaic. IEEE Access 8, 163637-45.

Zhu F, Li J, Zhu B (2023). Uav remote sensing image stitching via improved vgg16 siamese feature extraction network. Expert Syst Appl 229: 120525