结合ASPP与改进HRNet的多尺度图像语义分割方法研究

史健锋; 高治明; 王阿川

doi:10.37188/CJLCD.2021-0093

您当前的位置：

首页 >

文章列表页 >

结合ASPP与改进HRNet的多尺度图像语义分割方法研究

图像增强与分割 | 更新时间：2021-11-08

- 结合ASPP与改进HRNet的多尺度图像语义分割方法研究
- Multi-scale image semantic segmentation based on ASPP and improved HRNet
- 液晶与显示 2021年36卷第11期页码：1497-1505
- 作者机构：
  
  1. 东北林业大学信息与计算机工程学院, 黑龙江哈尔滨 150040
  2. 东北林业大学机电工程学院, 黑龙江哈尔滨 150040
- 作者简介：
  
  [ " 史健锋(1997-)，男，黑龙江齐齐哈尔人，硕士研究生，2019年于黑龙江大学获得学士学位，主要从事计算机视觉研究。E-mail： 2020111879@nefu.edu.cn " ]
  [ " 王阿川(1964-)，男，黑龙江哈尔滨人，博士，教授，2011年于东北林业大学获得博士学位主要从事计算机视觉，高分辨率遥感影像研究。E-mail： wangca1964@126.com " ]
- 基金信息：
  
  黑龙江省自然科学基金(F2018002)
- DOI：10.37188/CJLCD.2021-0093
  中图分类号： TP391.4
- 收稿日期：2021-04-08，
  
  修回日期：2021-05-18，
  
  纸质出版日期：2021-11
- 稿件说明：
移动端阅览
史健锋, 高治明, 王阿川. 结合ASPP与改进HRNet的多尺度图像语义分割方法研究[J]. 液晶与显示, 2021,36(11):1497-1505.

Jian-feng SHI, Zhi-ming GAO, A-chuan WANG. Multi-scale image semantic segmentation based on ASPP and improved HRNet[J]. Chinese journal of liquid crystals and displays, 2021, 36(11): 1497-1505.
史健锋, 高治明, 王阿川. 结合ASPP与改进HRNet的多尺度图像语义分割方法研究[J]. 液晶与显示, 2021,36(11):1497-1505. DOI： 10.37188/CJLCD.2021-0093.

Jian-feng SHI, Zhi-ming GAO, A-chuan WANG. Multi-scale image semantic segmentation based on ASPP and improved HRNet[J]. Chinese journal of liquid crystals and displays, 2021, 36(11): 1497-1505. DOI： 10.37188/CJLCD.2021-0093.

摘要

针对经典语义分割算法中存在的模型庞大、训练困难以及多尺度目标分割等问题，基于空洞空间金字塔池化(ASPP)和高分辨率网络(HRNet)提出了一种高效的多尺度图像语义分割方法。首先利用深度可分离卷积结合1*1卷积的方式改进了HRNet的基础模块，减少了模型参数；其次通过在全部的卷积层之后、修正线性单元(relu)激活函数之前添加批归一化层(BN)改善DeadRelu问题；最后添加了使用混合扩张卷积框架重构的ASPP，使用并行的上采样通道融合二者的优势，获得空间精准的分割结果，提出了Re-ASPP-HRNet。在公开数据集PASCAL VOC2012和CityScapes上的实验表明，改进后的方法相比于原HRNet分别实现了0.8%、0.5%平均交并比的精度提升，且减少了1/2的参数数量以及1/3占用内存。进一步提升了网络的性能，实现了更加高效可靠、有普适性的多尺度语义分割算法。

Abstract

Aiming at the problems of huge model and multi-scale object segmentation in the classical semantic segmentation algorithm

an efficient multi-scale image semantic segmentation method based on ASPP and HRNet is proposed. Firstly

the basic block is improved by using deep separable convolution combined with 1 * 1 convolution to reduce the model parameters. Secondly

a batch normalization layer (BN) is added after all convolution layers and before the relu activation function to improve the dead relu problem. Finally

the improved ASPP module based on the hybrid dilated convolution is added

and the advantages of the two are fused by using the parallel upsampling channels to obtain the spatial accurate segmentation results. The RE-ASPP-HRNet is proposed. Results on Pascal voc2012 and CityScapes show that the proposed method is effective. Compared with the original HRNet

it can improve the accuracy of 0.8% or 0.5% MIoU

and reduce the number of parameters by 1/2 and memory by 1/3. We implement a more efficient and reliable multi-scale semantic segmentation algorithm.

关键词

Keywords

references

王曦 , 于鸣 , 任洪娥 . UNET与FPN相结合的遥感图像语义分割 . 液晶与显示 , 2021 . 36 ( 3 ): 475 - 483 . http://cjlcd.lightpublishing.cn/thesisDetails#10.37188/CJLCD.2020-0116 http://cjlcd.lightpublishing.cn/thesisDetails#10.37188/CJLCD.2020-0116 .

X WANG , M YU , H E REN . Remote sensing image semantic segmentation combining UNET and FPN . Chinese Journal of Liquid Crystals and Displays , 2021 . 36 ( 3 ): 475 - 483 . http://cjlcd.lightpublishing.cn/thesisDetails#10.37188/CJLCD.2020-0116 http://cjlcd.lightpublishing.cn/thesisDetails#10.37188/CJLCD.2020-0116 .

陈晓冬 , 盛婧 , 杨晋 , 等 . 多参数Gabor预处理融合多尺度局部水平集的超声图像分割 . 中国光学 , 2020 . 13 ( 5 ): 1075 - 1084 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA202005019.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA202005019.htm .

X D CHEN , J SHENG , J YANG , 等 . Ultrasound image segmentation based on a multi-parameter Gabor filter and multiscale local level set method . Chinese Optics , 2020 . 13 ( 5 ): 1075 - 1084 . https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA202005019.htm https://www.cnki.com.cn/Article/CJFDTOTAL-ZGGA202005019.htm .

LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]// IEEE Conference on Computer Vision and Pattern Recognition . Boston: IEEE, 2015: 3431-3440.

RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C]//18 th International Conference on Medical Image Computing and Computer-Assisted Intervention . Munich: Springer, 2015: 234-241.

L C CHEN , G PAPANDREOU , I KOKKINOS , 等 . DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2018 . 40 ( 4 ): 834 - 848 . DOI: 10.1109/TPAMI.2017.2699184 http://doi.org/10.1109/TPAMI.2017.2699184 .

ZHENG S, JAYASUMANA S, ROMERA-PAREDES B, et al . Conditional random fields as recurrent neural networks[C]// IEEE International Conference on Computer Vision . Santiago: IEEE, 2015: 1529-1537.

SUN K, XIAO B, LIU D, et al . Deep high-resolution representation learning for human pose estimation[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition ( CVPR ). Long Beach: IEEE, 2019: 5686-5696.

V BADRINARAYANAN , A KENDALL , R CIPOLLA . SegNet: a deep convolutional encoder-decoder architecture for image segmentation . IEEE Transactions on Pattern Analysis and Machine Intelligence , 2017 . 39 ( 12 ): 2481 - 2495 . DOI: 10.1109/TPAMI.2016.2644615 http://doi.org/10.1109/TPAMI.2016.2644615 .

H S WU , C X LIANG , M S LIU , 等 . Optimized HRNet for image semantic segmentation . Expert Systems with Applications , 2021 . 174 114532 DOI: 10.1016/j.eswa.2020.114532 http://doi.org/10.1016/j.eswa.2020.114532 .

SUN K, ZHAO Y, JIANG B R, et al . High-resolution representations for labeling pixels and regions[J]. arXiv : 1904.04514, 2019: 1-4.

CHOLLET F. Xception: deep learning with depthwise separable convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Honolulu: IEEE, 2017: 1800-1807.

SZEGEDY C, VANHOUCKE V, IOFFE S, et al . Rethinking the inception architecture for computer vision[C]// IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas: IEEE, 2016: 2818-2826.

IOFFE S, SZEGEDY C. Batch normalization: accelerating deep network training by reducing internal covariate shift[J]. arXiv : 1502.03167, 2015: 2-4.

CHEN L C, ZHU Y K, PAPANDREOU G, et al . Encoder-decoder with atrous separable convolution for semantic image segmentation[C]//15 th European Conference on Computer Vision . Munich: Springer, 2018: 833-851.

WANG P Q, CHEN P F, YUAN Y, et al . Understanding convolution for semantic segmentation[C]//2018 IEEE Winter Conference on Applications of Computer Vision ( WACV ). Lake Tahoe: IEEE, 2018: 1451-1460.

CORDTS M, OMRAN M, RAMOS S, et al . The cityscapes dataset for semantic urban scene understanding[C]// IEEE Conference on Computer Vision and Pattern Recognition ( CVPR ). Las Vegas: IEEE, 2016: 3213-3223.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于语义分割的高分辨率场景解析网络

FRKDNet：基于知识蒸馏的特征提炼语义分割网络