融合多尺度特征的改进Deeplab v3+图像语义分割算法

张文博; 瞿珏; 王崴; 胡俊; 王庆力

doi:doi:10.3969/j.issn.1671-637x.2022.11.003

电光与控制, 2022, 29 (11): 12, 网络出版: 2023-02-10

融合多尺度特征的改进Deeplab v3+图像语义分割算法

An Improved Deeplab v3+ Image Semantic Segmentation Algorithm Incorporating Multi-Scale Features

论文大纲

张文博瞿珏王崴胡俊王庆力

作者单位

空军工程大学, 西安 710000

深度学习语义分割多尺度注意力机制迁移学习 deep learning semantic segmentation multi-scale attention mechanism transfer learning

摘要

针对当前Deeplab v3+模型没有充分采用高分辨率的浅层特征出现的错误分割、遗漏分割等现象, 提出一种融合多尺度特征的改进Deeplab v3+特征图像语义分割算法。在主干网络中, 引入多尺度金字塔卷积; 将空洞空间卷积池化金字塔中的标准卷积替换为深度可分离卷积, 减少整体模型的参数量; 最后, 在解码层采用多尺度方法来捕捉获取全局背景, 将背景特征通过注意力机制, 再与浅层特征和空洞空间金字塔池化层结合, 丰富融合后的浅层特征语义信息。实验表明, 在CityScapes验证集中, 所提算法具有更好的边缘分割效果, 平均交并比达到了74.76%, 较原有算法提升了2.20%。通过与先进算法比较, 也证明所提算法应对改善错误分割、遗漏分割的有效性。

Abstract

To address the phenomena of incorrect segmentation and missing segmentation that occur when the current Deeplab v3+ model does not adequately employ high-resolution shallow features,an improved Deeplab v3+ feature image semantic segmentation algorithm that incorporates multi-scale features is proposed.In the backbone network,multi-scale pyramidal convolution is introduced.The standard convolution in the pooled pyramid of atrous space convolution is replaced by the deep separable convolution to reduce the number of parameters of the whole model.Finally,a multi-scale approach is adopted in the decoding layer to capture the global background,and the background features are combined with the shallow features and the atrous space pyramid pooling layer through the attention mechanism to enrich the semantic information of the fused shallow features.Experiments show that in CityScapes dataset,the proposed algorithm has a better edge segmentation effect,with an Mean Intersection over Union(MIoU) of 74.76%, which is 2.20% higher than that of the original algorithm.Compared with advanced algorithms,it is also proved that it is effective in improving incorrect segmentation and missing segmentation.

参考文献

[1] SZE V,CHEN Y H,YANG T J,et al.Efficient processing of deep neural networks:a tutorial and survey［J］.Proceedings of the IEEE,2017,105(12): 2295-2329.

[2] JLA B,FJAB D,JING Y,et al.Lane-DeepLab:lane semantic segmentation in automatic driving scenarios for high-definition maps［J］.Neurocomputing,2021,465:15-25.

[3] 白傑,郝培涵,陈思汉.用轻量化卷积神经网络图像语义分割的交通场景理解［J］.汽车安全与节能学报2018, 9(4):433-440．

[4] DENG W B,HUANG K H,CHEN X Y L,et al.Semantic RGB-D SLAM for rescue robot navigation［J］.IEEE Access,2020,8:221320-221329.

[5] 严攀.基于目标检测的汽车线束外观检测应用研究［D］.成都: 电子科技大学,2020.

[6] LIU S,DING W R,LIU C H,et al.ERN:edge loss reinforced semantic segmentation network for remote sensing images［J］.Remote Sensing,2018,10(9):1339-1362.

[7] 蔡梅艳,吴庆宪,姜长生.改进Otsu法的目标图像分割［J］.电光与控制,2007,14(6):118-119,151.

[8] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.Semantic image segmentation with deep convolutional nets and fully connected CRFs［J］.Computer Science,2014(4):357-361.

[9] CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab:semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2018,40(4):834-848.

[10] CHEN L C,PAPANDREOU G,SCHROFF F,et al.Rethinking atrous convolution for semantic image segmentation［R］.Los Alamos: arXiv Preprint,2017:arXiv:1706.05587.

[11] 喻根,崔炜,徐照翔,等.基于DeepLabV3+的远距离目标语义分割模型［J］.电光与控制,2021,28(1):66-70.

[12] HE K M,ZHANG X Y,REN S Q,et al.Deep residual learning for image recognition［C］//IEEE Conference on Computer Vision and Pattern Recognition(CVPR).Las Vegas:IEEE,2016:770-778.

[13] DUTA I C,LIU L,ZHU F,et al.Pyramidal convolution:rethinking convolutional neural networks for visual recognition［R］.Los Alamos: arXiv Preprint,2020:arXiv:2006.11538.

[14] WOO S,PARK J,LEE J Y,et al.CBAM:convolutional block attention module［C］//European Conference on Computer Vision.Cham:Springer,2018:3-19.

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

[16] ZHAO H S,SHI J P,QI X J,et al.Pyramid scene parsing network［C］//IEEE Conference on Computer Vision and Pattern Recognition.Honolulu:IEEE,2017:6230-6239.

[17] SINHA A,DOLZ J.Multi-scale self-guided attention for medical image segmentation［J］.IEEE Journal of Biomedical and Health Informatics,2021,25(1):121-130.

[18] SUN K,XIAO B,LIU D,et al.Deep high-resolution representation learning for human pose estimation［R］.Los Alamos: arXiv Preprint,2019:arXiv:1902.09212.

[19] HUANG Z L,WANG X G,HUANG L C,et al.CCNet:criss-cross attention for semantic segmentation［C］//IEEE/CVF International Conference on Computer Vision(ICCV).Seoul:IEEE,2019:603-612.

张文博, 瞿珏, 王崴, 胡俊, 王庆力. 融合多尺度特征的改进Deeplab v3+图像语义分割算法[J]. 电光与控制, 2022, 29(11): 12. ZHANG Wenbo, QU Jue, WANG Wei, HU Jun, WANG Qingli. An Improved Deeplab v3+ Image Semantic Segmentation Algorithm Incorporating Multi-Scale Features[J]. Electronics Optics & Control, 2022, 29(11): 12.

融合多尺度特征的改进Deeplab v3+图像语义分割算法

关于本站 Cookie 的使用提示

全站搜索

融合多尺度特征的改进Deeplab v3+图像语义分割算法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索