A Line Objects Recognition Algorithm based on Non-subsampled Contourlet Transform

Aiming at the recognition of line features represented by bridges and airport runways in remote sensing data, this paper presents a line objects extraction algorithm based on Non-subsampled Contourlet Transform(NSCT). Firstly, NSCT is used to decompose the source image into multiple layers and direc...

Full description

Saved in:
Bibliographic Details
Published in:Chinese Control Conference pp. 3050 - 3055
Main Authors: Jiang, Qinghua, Yang, Yi, Zhang, Meng, Zhang, Sixian
Format: Conference Proceeding
Language:English
Published: Technical Committee on Control Theory, Chinese Association of Automation 01.07.2020
Subjects:
Feature extraction
fusion
Image edge detection
Image fusion
Image segmentation
Line feature
LSD
NSCT
Object recognition
Transforms
Visualization
ISSN:1934-1768
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aiming at the recognition of line features represented by bridges and airport runways in remote sensing data, this paper presents a line objects extraction algorithm based on Non-subsampled Contourlet Transform(NSCT). Firstly, NSCT is used to decompose the source image into multiple layers and directions to obtain the corresponding frequency sub-bands. Then the Line Segment Detection(LSD) algorithm with visual saliency is used to detect the line segments. Finally, line objects recognition is completed by multi-scale and multi-direction line features combination according to the established fusion rules. Comparison with some traditional algorithms verifies that the proposed algorithm can improve the recognition accuracy.
ISSN:1934-1768
DOI:10.23919/CCC50068.2020.9188900