SAR remote sensing image water area detection false alarm elimination method based on feature cascading
A false alarm elimination and remote sensing image technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of high false alarm rate, complex calculation, slow detection speed, etc., and achieve the effect of improving accuracy
Inactive Publication Date: 2019-08-09
北京理工雷科电子信息技术有限公司
View PDF6 Cites 7 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] In view of this, the present invention provides a method for eliminating false alarms in SAR remote sensing image water area detection based on feature cascading, which can solve the problems of high false alarm rate, complex calculation and slow detection speed in existing water area detection methods
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0034] One method to solve the problems raised by the background technology is to eliminate false alarms based on feature cascading. Due to the presence of speckle noise in SAR images, the signal-to-noise ratio is high. Therefore, the original SAR image is firstly subjected to mean filtering to remove the speckle noise of the SAR image; then, the SAT integral map is calculated, and the water area candidate area is obtained by adaptive threshold segmentation; On the basis of domain marking, by counting the area of the connected domain of the water area candidate area, small-area water area false alarms are eliminated, and then through the aspect ratio and duty cycle characteristics, as well as the expansion and corrosion ratio characteristics layer by layer, roads, valleys, and dark areas are eliminated. Spots and other false alarms are taken as the results of fine water detection. The present invention provides a method for eliminating false alarms in SAR remote sensing ima...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention provides an SAR remote sensing image water area detection false alarm elimination method based on feature cascading. The method comprises the following steps: marking a connected domain;the area of a connected domain of a water area candidate area is counted; the method has the advantages that the method is simple, the small-area water area false alarm is removed, then the road, valley dark spots and other false alarms are removed layer by layer through the length-width ratio and duty ratio characteristics and the expansion corrosion ratio characteristics to serve as water areafine detection results, and due to the fact that the morphological structure difference between the false alarms is fully considered, various false alarms are removed layer by layer, and the water area detection precision is improved.
Description
technical field [0001] The invention relates to the technical field of image detection, in particular to a method for eliminating false alarms in SAR remote sensing image water area detection based on feature cascading. Background technique [0002] Synthetic Aperture Radar (SAR) is a microwave remote sensing system that acquires side-view, all-weather, all-time active microwave remote sensing images. Water detection in SAR images has been widely used in water mapping and flood monitoring. [0003] SAR image water area detection is mainly divided into three parts: data preprocessing, water area candidate area extraction and false alarm elimination. Affected by the principle of SAR imaging, there are likely to be false alarms such as vegetation and road networks with low gray values and dark spots in valleys in the candidate water area, which are difficult to distinguish from real water targets. How to quickly and accurately distinguish water targets from false alarm area...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/136G06T5/00G06T5/30G06T7/187
CPCG06T7/136G06T7/187G06T5/30G06T2207/10044G06T2207/30181G06T5/70
Inventor 陈天明王玉亭丁萌张俊青
Owner 北京理工雷科电子信息技术有限公司