Ship target detection and identification method and system for satellite-borne remote sensing optical image

Abstract

The invention discloses a ship target detection and identification method for a satellite-borne remote sensing optical image. The method comprises the following steps of preprocessing, ineffective information removal, connected region marking, feature extraction and classifier design. A coarse-to-fine strategy is adopted, firstly, a satellite image is subjected to downsampling and Gaussian filtering processing, then, land and isolated noisy points are removed from the processed image, a candidate region is quickly extracted and is marked, feature information is extracted after the image is rotated, then, the feature information is put into a pre-trained classifier to be furthered confirmed and analyzed, false alarms are removed, and a real ship target is found. Meanwhile, the invention also realizes a ship target detection and identification system for the satellite-bone remote sensing optical image. By use of the technical scheme, satellite-borne storage and calculation of limited resources can be effectively utilized to improve the stability and the real time of a ship detection algorithm, meanwhile, a false alarm rate is effectively lowered, and accurate data can be provided for maritime search and rescue and ship image positioning in time.

Description

technical field [0001] The invention belongs to the technical field of image detection and recognition, and more particularly relates to a ship target detection and recognition method and system for space-borne remote sensing optical images. Background technique [0002] Ship targets include merchant ships, cargo ships, passenger ships, and even warships. As a key target for maritime monitoring, timely ocean search and rescue, and real-time wartime strikes, it is an important content of automatic target detection and recognition of spaceborne remote sensing images. [0003] Researchers have carried out a lot of research on the automatic detection and recognition of ship targets in SAR images, mainly using the differences in SAR images of different electromagnetic scattering characteristics between ship targets and water bodies. The SAR ship target surveillance systems that have been completed or are currently being developed mainly include: Canada’s Ocean Monitoring Workstat...

AI Technical Summary

Problems solved by technology

However, the current relevant technologies are not accurate enough and are too complicated. Most of the data need to be sent back to the ground for processing, which cannot achieve real-time processing, which wastes precious time in marine search and rescue situations, and is unreliable, inaccurate, and poor in performance. good

Images