Segmentation of low-informative areas on panchromatic high spatial resolution images of Earth surface

V. Eremeev; A. Kuznetcov; A. Kochergin; A. Makarenkov; N. Egoshkin

doi:10.1117/12.2325095

Translator Disclaimer

9 October 2018 Segmentation of low-informative areas on panchromatic high spatial resolution images of Earth surface

V. Eremeev, A. Kuznetcov, A. Kochergin, A. Makarenkov, N. Egoshkin

Author Affiliations +

Proceedings Volume 10789, Image and Signal Processing for Remote Sensing XXIV; 107891F (2018) https://doi.org/10.1117/12.2325095
Event: SPIE Remote Sensing, 2018, Berlin, Germany

Abstract

In the paper is described fast 3-staged algorithm for segmentation of low-information areas on high spatial resolution panchromatic images of Earth surface. At the first stage, an image is divided into the fragments of 128×128 pixels in size and analysis of pixels “Top of the atmosphere” reflectance is performed. At the second stage the analysis of frequency characteristic of fragments is performed. At the third stage the objects of an artificial origin such as strongly pronounced straight lines is assessed using the Hough transformation. The developed algorithm got high expert appraisal. In the case of high percent of low-informative fragments on the image the proposed algorithm provides significant decrease of GCP finding time.

Citation Download Citation

V. Eremeev, A. Kuznetcov, A. Kochergin, A. Makarenkov, and N. Egoshkin "Segmentation of low-informative areas on panchromatic high spatial resolution images of Earth surface", Proc. SPIE 10789, Image and Signal Processing for Remote Sensing XXIV, 107891F (9 October 2018); https://doi.org/10.1117/12.2325095

ACCESS THE FULL ARTICLE