Image segmentation method having multi-layer segmentation networks based on Bayes framework with edge prior information

Abstract

The invention relates to an image segmentation method having multi-layer segmentation networks based on Bayes framework with edge prior information. The method herein includes the following steps: S1.performing general classification on input data by using a full convolutional neural network, outputting scoring graphs of all types that have the same sizes of the input data, also extracting an implicit edge image from an internal feature layer of the full convolutional neural network; S2. extracting an explicit edge image from the input data by using an edge detection network; S3.performing first restraining on the types that are obtained from S2 by using domain transformation and conditional random field, obtaining an initial segmentation image; S4. transforming the explicit edge image obtained from S2 to an edge distance image; and S5. inputting the edge distance image to defined domain transformation, performing second edge restraining on the initial segmentation image that is obtained from S3, and obtaining a final segmentation result. According to the invention, the method can extract edge prior information through an external edge network and performs edge region segmentationand filtering on the result from the general segmentation by using the edge prior information, so that the method herein can increase the accuracy in segmenting a SAR image.

Description

technical field [0001] The invention belongs to the technical field of remote sensing image processing, in particular to an image segmentation method based on a Bayesian framework edge prior multi-layer segmentation network. Background technique [0002] SAR image segmentation is to merge connected areas with similar attributes into one piece to form multiple blocks on the image, and mark them with different colors to obtain the segmentation map of the area, such as dividing into fields, waters, building areas, roads, etc., which can be Widely used in military or civilian information utilization. [0003] The special imaging mechanism of SAR images makes the simple introduction of optical image segmentation methods difficult. Such as the expression of polarization characteristics, the suppression of coherent speckle phenomenon, the modeling of multiplicative non-Gaussian noise, etc. Various statistical properties have been proposed for SAR images to model images of the sam...

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the problem that there is still a large margin area segmentation error when the neural network-based model processes complex images, and proposes a multi-layer parallel network architecture based on the Bayesian framework, and proposes a limited domain conversion ( Directed Domain Transform,DDT)

Images