Edge Prior Multilayer Segmentation Network Based on Bayesian Framework

Chu He,Zishan Shi,Bokun He,Dehui Xiong,Mingsheng Liao,Peizhang Fang

doi:10.1155/2020/6854260

Abstract

In recent years, methods based on neural network have achieved excellent performance for image segmentation. However, segmentation around the edge area is still unsatisfactory when dealing with complex boundaries. This paper proposes an edge prior semantic segmentation architecture based on Bayesian framework. The entire framework is composed of three network structures, a likelihood network and an edge prior network at the front, followed by a constraint network. The likelihood network produces a rough segmentation result, which is later optimized by edge prior information, including the edge map and the edge distance. For the constraint network, the modified domain transform method is proposed, in which the diffusion direction is revised through the newly defined distance map and some added constraint conditions. Experiments about the proposed approach and several contrastive methods show that our proposed method had good performance and outperformed FCN in terms of average accuracy for 0.0209 on ESAR data set.

Highlights

The contributions of the proposed approach are as follows: (i) On the basis of Bayesian framework, this study presents a parallel network architecture, which is composed of two parallel networks called the likelihood network (FCN8) and the edge prior network (HED), respectively, and a constraint network behind (ii) To achieve accurate edge detection, edge map obtained from holistically nested edge detection (HED) is utilized, serving as edge prior information to sharpen blurred edge-pixel categories (iii) Considering that the edge distribution in traditional DT is not completely trusted and some edges may be lost, Directed Domain Transform (DDT) is proposed for image classification with complex edges
For data set 1, the proposed approach achieves the highest performance with 81:39% accuracy, outperforming DeepLab DT by 0:49%, which is attributed to internal edge fusion, edge prior information, and directed DT
An edge prior Bayesian semantic segmentation network for Synthetic Aperture Radar (SAR) image is proposed in this study

Summary

Introduction

Semantic segmentation of images is a very important task in computer vision, which aims to classify each pixel in the image and can be applied to autopilot, 3D reconstruction, and other fields. Synthetic Aperture Radar (SAR) image semantic segmentation is widely utilized in military and civilian information applications because SAR can obtain images at any time of the day and night independently of the weather conditions. Traditional segmentation methods can be mainly divided into three steps: segmentation of super-pixel blocks, feature extraction, and classifier selection. Methods like Meanshift [1] and Watershed [2] are typical for extracting super-pixel blocks. Afterwards, Markov Random Field (MRF) [6] and Conditional Random Field (CRF) are introduced to consider the information of surrounding pixels

Methods

Findings

Discussion

Conclusion