River Contour Recognition and Extraction Algorithm Based on Kirsch Operator and Multi-level Threshold Segmentation
The intelligent extraction accuracy of river contour from high-resolution remote sensing images under complex backgrounds is low.Thus,a method of combining the Kirsch operator with threshold segmentation is proposed to preprocess and pre-segment the gray images.Then,according to the morphological ch...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Pearl River
2023-01-01
|
| Series: | Renmin Zhujiang |
| Subjects: | |
| Online Access: | http://www.renminzhujiang.cn/thesisDetails#10.3969/j.issn.1001-9235.2023.07.014 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The intelligent extraction accuracy of river contour from high-resolution remote sensing images under complex backgrounds is low.Thus,a method of combining the Kirsch operator with threshold segmentation is proposed to preprocess and pre-segment the gray images.Then,according to the morphological characteristics of the river,the image is morphologically processed to remove most of the background noise.Finally,the second threshold segmentation is conducted on the main area to realize accurate river contour recognition and extraction.The applicability of this method is proven by recognizing river samples in different terrain conditions.By employing objective evaluation indexes,the recognition accuracy of river area is verified to exceed 90%,which is much higher than the simple threshold segmentation method.This meets the needs of high-precision river channel extraction and provides references for intelligent and rapid extraction of river channel information. |
|---|---|
| ISSN: | 1001-9235 |