Title:
SEAWATER-POLLUTED AREA IDENTIFICATION METHOD BASED ON HIGH-RESOLUTION REMOTE-SENSING IMAGE, AND DEVICE
Document Type and Number:
WIPO Patent Application WO/2021/077847
Kind Code:
A1
Abstract:
Disclosed are a seawater-polluted area identification method based on a high-resolution remote-sensing image, and a device, belonging to the field of digital image processing. According to the method, first, automatic sea and land classification is performed on a remote-sensing image by means of a supervised learning algorithm, a classification result can achieve a relatively high precision level by means of processed iterative clustering, and additionally, compared with existing sea-land border analysis and classification methods, the method has a relatively small computation amount; and then, a chlorophyll concentration difference and a pollutant shadow brightness difference between a marine polluted area and surrounding seawater are used to combine a normalized vegetation index related to chlorophyll, a normalized water body shadow index related to brightness, segmentation-based image interpretation ideas and a human-vision-based significance mechanism in remote sensing interpretation to extract the marine polluted area by means of threshold segmentation, an area with good water quality and a heavily polluted area are respectively extracted, and a pollution transition area is further acquired. The method of the present invention provides a convenient and accurate reference for marine pollution prevention and control.
Inventors:
ZHANG XUELING (CN)
LI LU (CN)
LI LU (CN)
Application Number:
PCT/CN2020/106921
Publication Date:
April 29, 2021
Filing Date:
August 05, 2020
Export Citation:
Assignee:
UNIV BEIJING CIVIL ENG & ARCHITECTURE (CN)
International Classes:
G06K9/00
Foreign References:
| CN110765941A | 2020-02-07 | |||
| CN108256534A | 2018-07-06 | |||
| CN108986116A | 2018-12-11 |
Other References:
XUELING ZHANG , ZHE LI , DI LI , YUKUN HE: "Marine Environment Distinctions and Change Law Based on eCongnition Remote Sensing Technology", JOURNAL OF COASTAL RESEARCH, vol. 94, no. SI, 9 September 2019 (2019-09-09), pages 107 - 111, XP009527514, ISSN: 0749-0208
Attorney, Agent or Firm:
BEIJING HUIZE INTELLECTUAL PROPERTY LAW LLC (CN)
Download PDF: