基于划分图像内容分级的语义分割算法  

Semantic Segmentation Based on Dividing Different Difficulty Class Levels

作　　者：罗子明 冯开平[1] 罗立宏 LUO Zi-ming;FENG Kai-ping;LUO Li-hong(School of Computers,Guangdong University of Technology,Guangzhou Guangdong 510006)

机构地区：[1]广东工业大学计算机学院,广东广州510006

出　　处：《数字技术与应用》2021年第1期117-120,共4页Digital Technology & Application

基　　金：教育部人文社科项目《基于VR/AR的历史文化展览沉浸式可视化叙事构架研究》(20YJAZH073)。

摘　　要：语义分割的任务是将给定图片的每一个像素进行分类,为了解决当类数目急剧增多或类的特征频繁改变的时候,语义分割的准确性会急剧地下降的问题。本研究提出将像素分类任务按照分类难度划分成不同的子任务。具体工作分为两部分:为每一个子任务训练一个神经网络,训练一个集成神经网络。根据图像像素的多少来划分难度等级的数量。通过为每一个不同的难度等级训练神经网络,可以获得各个子任务的概率图,然后通过这些概率图来训练集成网络。在实验部分,本研究将数据集上的11个类别划分成容易、中等、困难三类进行训练,在CamVid数据集上使用平均IoU衡量该方法语义分割准确率。实验结果表明,本研究方法与单一U-net对比传统方法对比在各类平均IoU上有了2%的提升。尤其是在围栏,人行道,自行车手这三类上有超过5%的提升。The task of semantic segmentation is to classify each pixel of a given picture,in order to solve the problem that the accuracy of semantic segmentation will drop sharply when the number of classes increases sharply or the characteristics of classes change frequently.This research proposes to divide the pixel classification task into different subtasks according to the classification difficulty.The specific work is divided into two parts:training a neural network for each subtask and training an integrated neural network.Divide the number of difficulty levels according to the number of image pixels.By training the neural network for each different difficulty level,the probability map of each subtask can be obtained,and then the integrated network can be trained through these probability maps.In the experimental part,this research divides the 11 categories on the data set into three categories:easy,medium,and difficult for training.The average IoU is used on the CamVid data set to measure the accuracy of semantic segmentation of this method.The experimental results show that this research method has a 2%improvement in the average IoU of various types compared with the single U-net compared with the traditional method.Especially in the three categories of fences,sidewalks,and cyclists,there is an increase of more than 5%.

关 键 词：语义分割 子任务 集成分类器 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]