Aerosol spatio-temporal evolution map feature finding comparison method based on image similarity algorithm

In this paper, a method based on different similarity algorithms is proposed to find and compare the salient features in the spatio-temporal evolution map of aerosols. The pixel number difference of similar features calculated using this method in different aerosol spatio-temporal evolution maps is equivalent to the movement time. By analyzing the design principles, advantages and disadvantages of four different algorithms: SSIM, Corr2, Ahash and Dhash, the simulation analysis experiment is designed. From the aspects of theoretical analysis and experimental test, the images with different pixel numbers are layered and solved, and the solution effects of different similarity algorithms are comprehensively compared. The results of simulation and comparison show that among the four similarity algorithms, Ahash and Dhash algorithms perform well and have less fluctuation in accuracy, and the above conclusions can provide reference for the feature finding comparison methods of similarity algorithms in aerosol density mapping.