Superpixel-Based Stripe Noise Removal for Satellite Imageries
| Autor: | Kamirul, Khairunnisa, Ega Asti Anggari, Dicka Ariptian Rahayu, Agus Herawan, Moedji Soedjarwo, Chusnul Tri Judianto |
|---|---|
| Jazyk: | English<br />Indonesian |
| Rok vydání: | 2023 |
| Předmět: | |
| Zdroj: | Jurnal Nasional Teknik Elektro dan Teknologi Informasi, Vol 12, Iss 2, Pp 124-130 (2023) |
| Druh dokumentu: | article |
| ISSN: | 2301-4156 2460-5719 |
| DOI: | 10.22146/jnteti.v12i2.7443 |
| Popis: | This work introduces a novel noise removal algorithm for satellite imageries based on superpixel segmentation followed by statistics-based filtering. The algorithm worked in three main steps. First, the noisy input image was divided into subregions by employing simple linear iterative clustering (SLIC)-based superpixel segmentation. Then, the statistical property of each subregion was calculated, including their standard deviations and maximum values. Last, an adaptive statistics-based stripe noise removal was performed for each subregion by constructing adaptive filter sizes according to calculated properties. The algorithm was tested using real satellite imageries taken by the LAPAN-A2 and LAPAN-A3 satellites. Its performance was then compared to three existing methods in terms of image quality and computation speed. Extensive experiments on two datasets of 3-channel images captured by the LAPAN-A2 satellite showed that the algorithm was capable of reducing the stripe pattern as measured using the peak-signal-to-noise-ratio (PSNR) metric without introducing additional artifacts, which commonly appeared on over-corrected regions. Moreover, compared to existing methods, the proposed algorithm ran 42 to 103 times faster and provided better image quality by 2.46%, measured using the structural similarity metric (SSIM). The code of this work and the datasets used for the testing are publicly available on www.github.com/dancingpixel/SPSNR. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|