Search method of SAR images classified based on Gauss hybrid model

Abstract

The invention discloses a search method of SAR images classified based on Gauss hybrid model, which mainly solves the problem that the existing SAR image search method has long search time and low precision. The search method comprises the following steps of: establishing SAR image library (I1, I2, ..., Ik), and selecting legible SAR images with relatively even lamellation (I1, I2, ..., Il); extracting the characteristic vectors of all images (f1, f2, ..., fn); classifying the selected SAR images (I1, I2, ..., Il) into (c1, c2, ..., cm), and using the corresponding characteristic vectors as training samples to train the Gauss hybrid model; using the trained Gauss hybrid model to classify the whole image library (I1, I2, ..., Ik) so as to obtain an image library with classification label; extracting a characteristic vector f ' for the inquired image I' input by a user, and using the trained Gauss hybrid model for classification to obtain a classification number ci; and calculating the similarity distances between the inquired image I' and the region comprehensive characteristics of all images of ci classification in the library, and returning the required amount of images of the user according to an ascending distance order. The invention has the advantages of high search speed and high search precision and can be used for searching a large amount of SAR images.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to image recognition pattern recognition, is a method for SAR image retrieval, and can be applied to large-scale SAR image search. Background technique [0002] As a representative of microwave remote sensing, synthetic aperture radar (SAR) is a high-resolution radar system that can be used in many fields such as military affairs, agriculture, navigation, and geographical surveillance. Compared with optical images, SAR images have the following characteristics: high-resolution synthetic aperture radar has all-weather and all-weather detection and detection and tracking capabilities, and has the ability to detect outside defense zones, and has a longer-distance working ability than ordinary infrared and electro-optical sensors; Its coherent imaging properties can be used for aperture synthesis, enabling SAR to provide detailed ground mapping data and images with high resolution; o...

AI Technical Summary

Problems solved by technology

Nowadays, many mature and well-known retrieval systems have been proposed, such as SIMPLIcity retrieval system, see James Z.Wang, Jia Li, GioWiederhold.SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture Llbraries.IEEE Trans.on Pattern Analysis and Machine Intelligence . Not suitable for retrieval of SAR images

Another example is the remote sensing image retrieval system combined with hidden Markov model classification proposed in 2006, see Ritendra Datta, JiaLi, Ashish Parulekar, James Z. Wang. Scalable Remotely Sensed Image Mining Using Supervised Learning and Content-based Retrieval. Penn State University Technical Report CSE 2006, 06-019, this method is oriented to multi-spectral remote sensing images, and a large number of color and spectral features are used in the retrieval process. These features are the missing feature information in SAR images, so this retrieval method is directly used in SAR images search, the effect is not satisfactory

Images