| Autor: |
N. A. Zhilnikova, V. O. Smirnova, I. V. Matelenok, A. S. Smirnova |
| Rok vydání: |
2019 |
| Předmět: |
|
| Zdroj: |
Issues of radio electronics. 1:82-88 |
| ISSN: |
2218-5453 |
| DOI: |
10.21778/2218-5453-2019-7-82-88 |
| Popis: |
The most complete information on the state of different man-made objects, collected with on-site and remote sensing methods, is required to ensure environmental and technospheric safety at the regional scale. The procedures of oil tank detection traditionally utilize high-cost, ultra-high-resolution images. The research is devoted to studying the possibility of using high and mediumresolution data from Landsat‑8 and Sentinel‑2 sensors to handle the task. Operating of the parts of the detection algorithms used in practice was analyzed, and some of them were selected as workable options which lead to satisfactory results being applied to data from mentioned instruments. A new technique of tank identifying which consists of classification, blob detection and filtering steps was developed. Testing of proposed solutions on data on the territory of Chaunsky District of Chukotka Autonomous Okrug showed the possibility of their use for detecting objects of the considered category. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
