Title:
OBJECT-ORIENTED HIGH-RESOLUTION REMOTE SENSING IMAGE MULTI-SCALE SEGMENTATION METHOD AND SYSTEM
Document Type and Number:
WIPO Patent Application WO/2022/141145
Kind Code:
A1
Abstract:
Disclosed is an object-oriented high-resolution remote sensing image multi-scale segmentation method, comprising: acquiring a remote sensing image; extracting spectral features, shape features, texture features and edge features of the remote sensing image; respectively calculating the heterogeneities of the spectral features, the shape features and the texture features, and segmenting the image according to the heterogeneities to obtain a heterogeneous image; calculating the edge intensity of the remote sensing image by using the edge features, and generating an edge intensity map; and combining the heterogeneous image and the edge intensity map to obtain a remote sensing image segmentation feature map. By means of segmenting the image on the scale of the spectral features, the shape features, the texture features and the edge features, a segmented object is determined, so that an object hierarchical network can be constructed during subsequent processing. Therefore, when applied to a visual attention model, the object and hierarchical structure thereof can be determined.
Inventors:
SHEN XIAOLE (CN)
WEI BIYUN (CN)
LU JINHUI (CN)
WEI BIYUN (CN)
LU JINHUI (CN)
Application Number:
PCT/CN2020/141206
Publication Date:
July 07, 2022
Filing Date:
December 30, 2020
Export Citation:
Assignee:
UNIV SHENZHEN TECHNOLOGY (CN)
International Classes:
G06T7/10
Foreign References:
| CN105894513A | 2016-08-24 | |||
| CN107085708A | 2017-08-22 | |||
| CN104751478A | 2015-07-01 | |||
| CN109993753A | 2019-07-09 | |||
| US20060050984A1 | 2006-03-09 |
Other References:
TIAN YINGJIE: "Change Detection of Buildings in Urban Area with High-resolution Remote Sensing Images Based on Multi-scale Object", CHINESE DOCTORAL DISSERTATIONS FULL-TEXT DATABASE, UNIVERSITY OF CHINESE ACADEMY OF SCIENCES, CN, no. 6, 15 June 2020 (2020-06-15), CN , XP055948537, ISSN: 1674-022X
SHEN XIAOLE: "Object-oriented Building Extraction from High-resolution Remote Sensing Images Based on Visual Attention Mechanism", CHINESE DOCTORAL DISSERTATIONS FULL-TEXT DATABASE, UNIVERSITY OF CHINESE ACADEMY OF SCIENCES, CN, no. 1, 15 January 2017 (2017-01-15), CN , XP055948541, ISSN: 1674-022X
SHEN XIAOLE: "Object-oriented Building Extraction from High-resolution Remote Sensing Images Based on Visual Attention Mechanism", CHINESE DOCTORAL DISSERTATIONS FULL-TEXT DATABASE, UNIVERSITY OF CHINESE ACADEMY OF SCIENCES, CN, no. 1, 15 January 2017 (2017-01-15), CN , XP055948541, ISSN: 1674-022X
Attorney, Agent or Firm:
SHINY INTELLECTUAL PROPERTY FIRM (CN)
Download PDF:
Previous Patent: TIME-BASED APPLICATION OF PATH LOSS ESTIMATION
Next Patent: CURED SILICONE ADHESIVE COMPOSITION
Next Patent: CURED SILICONE ADHESIVE COMPOSITION