A docking ship detection method based on edge line analysis and aggregation channel characteristics

Abstract

The invention provides a docking ship detection method based on edge line analysis and aggregation channel characteristics. The method comprises the following steps: firstly, realizing sea-land segmentation based on multi-scale multi-structure element morphological filtering, defining an edge point gradient tangent angle and port convexity characteristics by combining rectangular shape characteristics of a port in a remote sensing image to position the port, and obtaining a port region-of-interest set; and then, extracting aggregation channel characteristics of the ship target, constructing aship sample training library based on the aggregation channel characteristics, finishing training of a classifier by utilizing an AdaBoost algorithm, and finishing final judgment and confirmation of the ship target by utilizing the trained classifier. According to the invention, the port can be quickly positioned from the large-scale remote sensing image; port positioning does not need to acquiregeographic prior information and perform a large amount of feature matching calculation, ship features are fully reflected by utilizing aggregation channel features, the problem of serious interference of the backgrounds of ports on ship detection is solved, various types of ships can be detected, and the application range is wide.

Description

technical field [0001] The invention belongs to the field of remote sensing image target detection, and more specifically, relates to a method for detecting a docked ship based on edge line analysis and aggregation channel features. Background technique [0002] As an important carrier of maritime shipping, ships can be effectively monitored to understand the shipping conditions in sea areas. In recent years, the continuous improvement of the level of remote sensing technology has made optical remote sensing images have higher and higher resolutions. Optical remote sensing images contain a large amount of visual information, which can not only be used in the field of ship detection to detect non-metallic ships and use surface coatings and The special structural design of the ship that hides the radar can complete the ship detection task that the synthetic aperture radar could not complete in the past; it can also provide a large amount of image detail information similar to ...

AI Technical Summary

Problems solved by technology

[0011] In view of the fact that the existing technology needs to rely on the prior port template information base and cannot locate the port that is not recorded in the template knowledge base in the port positioning, the geometric feature positioning has a large amount of calculation and the feature is sensitive to noise; in the ship detection, it relies more on the highly accurate The sea and land binarization segmentation effect and the ship types detected by the corner point method are relatively single and have many interferences. The present invention proposes a method for detecting ships docked based on edge line analysis and aggregation channel features to solve these problems.

Images