高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于区域与深度残差网络的图像语义分割

罗会兰 卢飞 孔繁胜

罗会兰, 卢飞, 孔繁胜. 基于区域与深度残差网络的图像语义分割[J]. 电子与信息学报, 2019, 41(11): 2777-2786. doi: 10.11999/JEIT190056
引用本文: 罗会兰, 卢飞, 孔繁胜. 基于区域与深度残差网络的图像语义分割[J]. 电子与信息学报, 2019, 41(11): 2777-2786. doi: 10.11999/JEIT190056
Huilan LUO, Fei LU, Fansheng KONG. Image Semantic Segmentation Based on Region and Deep Residual Network[J]. Journal of Electronics & Information Technology, 2019, 41(11): 2777-2786. doi: 10.11999/JEIT190056
Citation: Huilan LUO, Fei LU, Fansheng KONG. Image Semantic Segmentation Based on Region and Deep Residual Network[J]. Journal of Electronics & Information Technology, 2019, 41(11): 2777-2786. doi: 10.11999/JEIT190056

基于区域与深度残差网络的图像语义分割

doi: 10.11999/JEIT190056
基金项目: 国家自然科学基金(61862031, 61462035),江西省自然科学基金(20171BAB202014)
详细信息
    作者简介:

    罗会兰:女,1974年生,博士,教授,研究方向为机器学习和模式识别等

    卢飞:男,1994年生,硕士,研究方向为图像语义分割

    孔繁胜:男,1946年生,博士生导师,教授,研究方向人工智能与知识发现等

    通讯作者:

    罗会兰 luohuilan@sina.com

  • 中图分类号: TP391.41

Image Semantic Segmentation Based on Region and Deep Residual Network

Funds: The National Natural Science Foundation of China (61862031, 61462035), The Natural Science Foundation of Jiangxi Province (20171BAB202014)
  • 摘要: 该文提出了一种结合区域和深度残差网络的语义分割模型。基于区域的语义分割方法使用多尺度提取相互重叠的区域,可识别多种尺度的目标并得到精细的物体分割边界。基于全卷积网络的方法使用卷积神经网络(CNN)自主学习特征,可以针对逐像素分类任务进行端到端训练,但是这种方法通常会产生粗糙的分割边界。该文将两种方法的优点结合起来:首先使用区域生成网络在图像中生成候选区域,然后将图像通过带扩张卷积的深度残差网络进行特征提取得到特征图,结合候选区域以及特征图得到区域的特征,并将其映射到区域中每个像素上;最后使用全局平均池化层进行逐像素分类。该文还使用了多模型融合的方法,在相同的网络模型中设置不同的输入进行训练得到多个模型,然后在分类层进行特征融合,得到最终的分割结果。在SIFT FLOW和PASCAL Context数据集上的实验结果表明该文方法具有较高的平均准确率。
  • 图  1  本文所提模型框架

    图  2  带扩张卷积的卷积神经网络结构

    图  3  全局平均池化层结构示意图

    图  4  模型融合框架示意图

    图  5  SIFT FLOW数据集上图像分割效果

    图  6  PASCAL Context数据集上图像分割效果

    表  1  本文算法与其他先进方法在SIFT FLOW数据集上的实验对比(%)

    方法平均准确率(MA)像素准确率(PA)
    Yang[21]48.7079.80
    Long[7]51.7085.20
    Eigen[22]55.7086.80
    Caesar[15]64.0084.30
    本文算法66.2085.70
    下载: 导出CSV

    表  2  本文算法与其他先进方法在PASCAL Context数据集上的实验对比(%)

    方法平均准确率(MA)像素准确率(PA)平均交并比(MIoU)
    O2P[3]18.10
    Dai[23]34.40
    Long[7]46.5065.9035.10
    Caesar[15]49.9062.4032.50
    本文52.2066.3034.70
    下载: 导出CSV

    表  3  3种不同扩张卷积核使用方案的性能比较

    实验操作 最后卷积层输出大小SIFT FLOW MA(%)
    1无操作19×1964.50
    2仅移除stride操作仅Res4 (stride=1)38×3826.61
    3仅Res5 (stride=1)38×3837.47
    4Res4 (stride=1)+Res5 (stride=1)75×7539.76
    5+设置dilated仅Res4(dilated=2)38×3864.20
    6仅Res5(dilated=4)38×3863.60
    7Res4(dilated=2)+Res5(dilated=4)75×7565.50
    下载: 导出CSV

    表  4  4个单模型以及融合模型在SIFT FLOW上的效果比较

    模型序号候选区域尺寸SIFT FLOW MA(%)
    17×764.20
    29×964.80
    313×1365.30
    415×1565.20
    融合模型3 465.70
    融合模型3 466.00
    融合模型1 2 3 466.20
    下载: 导出CSV
  • 魏云超, 赵耀. 基于DCNN的图像语义分割综述[J]. 北京交通大学学报, 2016, 40(4): 82–91. doi: 10.11860/j.issn.1673-0291

    WEI Yunchao and ZHAO Yao. A review on image semantic segmentation based on DCNN[J]. Journal of Beijing Jiaotong University, 2016, 40(4): 82–91. doi: 10.11860/j.issn.1673-0291
    CARREIRA J, LI Fuxin, and SMINCHISESCU C. Object recognition by sequential figure-ground ranking[J]. International Journal of Computer Vision, 2012, 98(3): 243–262. doi: 10.1007/s11263-011-0507-2
    CARREIRA J, CASEIRO R, BATISTA J, et al. Semantic segmentation with second-order pooling[C]. Proceedings of the 12th European Conference on Computer Vision 2012, Berlin, Germany, 2012: 430–443.
    ARBELÁEZ P, HARIHARAN B, GU Chunhui, et al. Semantic segmentation using regions and parts[C]. Proceedings of 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 3378–3385.
    GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]. Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Portland, USA, 2014: 580–587.
    GIRSHICK R. Fast R-CNN[C]. Proceedings of 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1440–1448.
    SHELHAMER E, LONG J, and DARRELL T. Fully convolutional networks for semantic segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 39(4): 640–651. doi: 10.1109/TPAMI.2016.2572683
    CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[J]. Computer Science, 2015(4): 357–361. doi: 10.1080/17476938708814211
    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, 2016, 40(4): 834–848. doi: 10.1109/TPAMI.2017.2699184
    UIJLINGS J R R, VAN DE SANDE K E A, GEVERS T, et al. Selective search for object recognition[J]. International Journal of Computer Vision, 2013, 104(2): 154–171. doi: 10.1007/s11263-013-0620-5
    HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(9): 1904–1916. doi: 10.1109/TPAMI.2015.2389824
    YU Tianshu, YAN Junchi, ZHAO Jieyi, et al. Joint cuts and matching of partitions in one graph[C]. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 705–713.
    HARIHARAN B, ARBELÁEZ P, GIRSHICK R, et al. Simultaneous detection and segmentation[C]. Proceedings of the 13th Conference on Computer Vision, Zurich, Switzerland, 2014: 297–312.
    DAI Jifeng, HE Kaiming, and SUN Jian. Convolutional feature masking for joint object and stuff segmentation[C]. Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, USA, 2015: 3992–4000.
    CAESAR H, UIJLINGS J, and FERRARI V. Region-based semantic segmentation with end-to-end training[C]. Proceedings of the 14th European Conference on Computer Vision 2016, Amsterdam, The Netherlands, 2016: 381–397.
    HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition[C]. Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, 2016: 770–778.
    YU F and KOLTUN V. Multi-scale context aggregation by dilated convolutions[EB/OL]. https://arxiv.org/abs/1511.07122, 2015.
    LIN Min, CHEN Qiang, and YAN Shuicheng. Network in network[EB/OL]. https://arxiv.org/abs/1312.4400, 2014.
    LIU Ce, YUEN J, and TORRALBA A. Nonparametric scene parsing via label transfer[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(12): 2368–2382. doi: 10.1109/TPAMI.2011.131
    MOTTAGHI R, CHEN Xianjie, LIU Xiaobai, et al. The role of context for object detection and semantic segmentation in the wild[C]. Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 891–898.
    YANG Jimei, PRICE B, COHEN S, et al. Context driven scene parsing with attention to rare classes[C]. Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 3294–3301.
    EIGEN D and FERGUS R. Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture[C]. Proceedings of 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 2650–2658.
    DAI Jifeng, HE Kaiming, and SUN Jian. Boxsup: exploiting bounding boxes to supervise convolutional networks for semantic segmentation[C]. Proceedings of 2015 IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 1635–1643.
  • 加载中
图(6) / 表(4)
计量
  • 文章访问数:  3610
  • HTML全文浏览量:  1719
  • PDF下载量:  129
  • 被引次数: 0
出版历程
  • 收稿日期:  2019-01-18
  • 修回日期:  2019-04-05
  • 网络出版日期:  2019-04-22
  • 刊出日期:  2019-11-01

目录

    /

    返回文章
    返回