Method for identifying oil spilling and suspected object in SAR dark shadow image

Abstract

The invention discloses a method for identifying oil spilling and suspected objects in an SAR (synthetic aperture radar) dark shadow image. The method comprises inputting an SAR image, establishing an oil-spilling image library and a suspected object image library; choosing M pictures at random to form a training sample image library, calculating a fractal characteristic vector of each image in the training sample image library by using a difference box counting method and a wavelet transformation modulus maxima method, forming a training sample set; using the training sample set and labels of the training samples to train an SVM grader; determining a to-be-identified dark shadow area in the SAR image by using a self-adaptive threshold value method, scanning spots pixel by pixel in the dark shadow area, calculating fractal characteristic vector thereof to form a test sample set; and using the trained SVM grader to classify test samples, and outputting a classification result. The method has relatively high operation efficiency, and can be used in identification and classification of oil spilling and suspected objects in the SAR dark shadow image.

Description

technical field [0001] The invention relates to a method for identifying oil spills and suspected objects in SAR shadow images, and belongs to the technical field of microwave ocean remote sensing. Background technique [0002] The ocean is closely related to human economic activities. However, marine oil spill pollution has the characteristics of affecting a wide range of sea areas, lasting for a long time, and causing great damage to marine organisms and the ecological environment. [0003] In the prior art, direct detection and remote sensing detection are two main methods of oil spill monitoring. Synthetic aperture radar (SAR, synthetic aperture radar) belongs to remote sensing detection, which has the advantages of all-time, all-weather, high resolution and large observation range. Due to the low intensity of scattered echoes in the area covered by oil film, it often appears as dark shadow features on SAR images. However, many ocean phenomena such as low-wind speed s...

AI Technical Summary

Problems solved by technology

The problem of high false alarm rate in the process of identifying oil spills and suspected objects has always been a difficulty in the SAR marine oil spill monitoring system, and this problem has not been completely resolved

Literature (M.Bertacca, F.Berizzi, E.D.Mese. AFARIMA-based technique for oil slick and low-wind areas discrimination in sea SAR imagery.IEEE Trans.Geosci.Remote Sensing,2005,43(11):2484-2493) Utilizing the fractal model also has fractional-order characteristics in the spectrum domain, a fractional-order ARMA model is proposed to calculate the radial power spectral density, and the radial power spectral density is selected as the feature for identifying oil spills and low wind speed sea surfaces. The disadvantage is that the recognition accuracy depends on the order of the ARMA model, and the selected recognition features are too simple, and other fractal features are not considered

Images