Method for automatically detecting cloud interfering naval vessel target by optical remote sensing image

Abstract

The invention provides a method for automatically detecting clouds interfere naval vessel target by an optical remote sensing image. The method can significantly improve the accuracy of detecting the naval vessel target shielded by clouds, and reduce omission factor and false alarm rate. The method is realized by the following technical proposal that: an adaptive threshold value of image region segmentation is evaluated according to image background and gamma characteristic distribution different of the naval vessel target; background region of ocean and clouds and a target region connected with the naval vessel and clouds thereof in the image are separated; a contour directional chain of a region of interest ROI can be obtained by a contour tracing method so as to strengthen pattern feature description of the target; the region contour directional chain is subjected to match searching by a template of the target contour directional chain so as to distinguish a naval vessel region and a cloud region; and multi-feature parameters of the naval vessel are extracted by a morphological and texture analysis method, and target determination is determined by an iterative decision-making method of multi-feature priority, thereby realizing naval vessel automatic detection of the remote sensing image under clouds interference.

Description

technical field [0001] The invention relates to the intelligent target detection technology in the field of image analysis and pattern recognition, especially relates to the automatic detection method of the ship target under the cloud interference or half-occlusion of the cloud layer of the remote sensing image. Background technique [0002] In the prior art, image processing and target characteristic analysis of optical remote sensing images can be used to understand the image content and interpret the scene. Target detection using optical remote sensing images can effectively support the reconnaissance and surveillance of ships in the military field, and the rescue and management of ships in the civilian field. However, in optical remote sensing images, there are usually multi-form clouds and the interference phenomenon of half-occlusion of ships by clouds. In addition, ship targets are characterized by high sparsity and random distribution. These factors make the ship ta...

AI Technical Summary

Problems solved by technology

For the multi-form clouds and the half-occlusion of the ship by the cloud in the remote sensing image, the above feature matching target detection method is not easy to distinguish the cloud interference area and the ship hull area, which leads to low accuracy of ship detection by feature matching judgment.

The transforming target detection method is not suitable for slow-moving ship detection without obvious wake characteristics. In addition, the polymorphic graphics of the cloud layer will seriously interfere with the wake detection effect, which leads to the detection of ship targets in remote sensing images by the transforming target detection method. Low detection rate, high missed detection rate and high false alarm rate

Neither of these two types of methods can effectively segment the target area of ​​the ship and the area of ​​cloud interference, so it is not suitable for ships with high accuracy in the case of multi-form cloud interference in optical remote sensing images, especially in the case of half-occlusion of the ship by clouds. Target Detection

Images