一种基于改进的MobileNetV2网络语义分割算法  

Semantic Segmentation Algorithm Based on Improved MobileNetV2

作　　者：孟琭[1] 徐磊 郭嘉阳 MENG Lu;XU Lei;GUO Jia-yang(College of Information Science and Engineering,Northeastern University,Shenyang,Liaoning 110000,China;Department of Electrical Engineering and Computer Science,University of Cincinnati,Cincinnati,Ohio 45221,USA)

机构地区：[1]东北大学信息科学与工程学院,辽宁沈阳110000 [2]辛辛那提大学电气工程与计算机系,俄亥俄州辛辛那提45221

出　　处：《电子学报》2020年第9期1769-1776,共8页Acta Electronica Sinica

基　　金：国家自然科学基金(No.61973058);教育部中央高校基本科研基金(No.N2004020)。

摘　　要：基于金字塔卷积神经网络的语义分割算法准确率很高,但是其计算资源消耗巨大、算法执行时间长、无法满足实时性要求.为了解决这个问题,本文做出了以下改进:(1)用MobileNet替换原网络的结构,减少了网络运算时间和内存开销;(2)引入编码器-解码器结构提高输出图像的分辨率,进一步细化分割结果;(3)针对高分辨率图像推断时间过长的问题,本文设计了多级图像输入方法,降低了网络推断高分辨率图像所消耗的时间.本文在VOC 2012数据集和Cityscapes数据集上进行了测试,并与FCN、SegNet、DeepLab、PSPNet以及DFN等语义分割模型对比.实验结果表明,本文设计的语义分割算法在VOC 2012数据集上达到了76.1%的mIoU,在Cityscapes数据集上达到了74.1%的mIoU,略低于传统语义分割算法;处理一张分辨率为1024×512的图片需要18ms,少于传统语义分割算法,满足了实时性要求,达到了准确率与计算资源消耗之间的平衡.The algorithm of semantic segmentation based on pyramid convolution neural network has high accuracy,but it consumes a lot of computing resources,takes a long time to execute,and cannot meet the real-time requirements.To overcome these shortcomings,this paper made the following improvements:(1)replacing the original network structure with MobileNet in order to reduce the computation time and memory consumption;(2)using encoder-decoder structure to improve the resolution of the output image and further refine the segmentation results;(3)using a multi-level image input method,which can reduce the time consumed by network inference of high-resolution image.Our method was tested on the VOC 2012 dataset and the Cityscapes dataset compared with other state-of-the-art semantic segmentation models such as FCN(Fully Convolutional Networks),SegNet,DeepLab,PSPNet and DFN(Discriminative Feature Network).Experimental results showed that our method achieved mIoU of 76.1%on the VOC 2012 dataset,and achieved mIOU of 74.1%on the Cityscapes dataset,which was a little lower than the traditional semantic segmentation algorithms.It took 18ms for our method to predict a 1024×512 picture,which achieved a balance between accuracy and computational resource consumption.

关 键 词：语义分割 卷积神经网络 金字塔网络 快速语义分割 MobileNet 编码器-解码器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]