基于部件检测与检索的行人精细化分割

doi:10.3969/j.issn.0372-2112.2019.02.035

电子学报 ›› 2019, Vol. 47 ›› Issue (2): 502-508.DOI: 10.3969/j.issn.0372-2112.2019.02.035

基于部件检测与检索的行人精细化分割

王枫, 厉智, 刘青山, 孙玉宝

南京信息工程大学信息与控制学院, 江苏省大数据分析技术实验室, 江苏南京 210044

收稿日期:2017-04-12 修回日期:2017-12-12 出版日期:2019-02-25
- 作者简介:
- 王枫女,1993年生于江苏扬州.南京信息工程大学硕士研究生,研究方向为深度学习、计算机视觉、行人属性分析;刘青山 男,1975年生于安徽庐江.南京信息工程大学教授,博士生导师,主要研究方向为人脸图像分析、图像理解、视频分析、模式识别、机器学习等.E-mail:qsliu@nuist.edu.cn
- 基金资助:
- 国家自然科学基金 (No.61532009）

Fine Pedestrian Segmentation with Parts Detection and Retrieval

WANG Feng, LI Zhi, LIU Qing-shan, SUN Yu-bao

B-DAT Lab, Collaborative Innovation Center, School of Information & Control, Nanjing University of Information Science and Technology, Nanjing, Jiangsu 210044, China

Received:2017-04-12 Revised:2017-12-12 Online:2019-02-25 Published:2019-02-25

摘要/Abstract

摘要： 针对行人图像外观的多样性以及结构、姿态、场景的复杂性，提出一种有效的精细化行人部件分割方法.该方法实现把一幅行人图像分割成不同的语义区域，主要包含三个阶段，前两个阶段单独训练两个Fast R-CNN（Fast Region-based Convolutional Neural Network，快速区域卷积神经网络）模型，分别用来检测整个人体以及各个部件以获得各类别部件的大体位置；第三个阶段使用基于检索过分割图像的方法来对检测到的各个部件进行分割，最后把各部件分割结果还原到原图坐标上以得到最终的分割结果.实验表明所提方法在三个公开的数据库上，与其他算法相比，分割准确率更高，边缘效果更好.

关键词: 行人分割, 快速区域卷积神经网络, 过分割, 部件检索

Abstract: Focused on the diversity of appearance and the complexity of configuration,laying,and occasion in human images,a coarse-to-fine method was proposed for effective human parsing.It can decompose a human image into semantic regions which consists of three phases.In the first two phases,two effective models were trained with Fast Region-based Convolutional Network(Fast R-CNN)to respectively detect human body and clothing items.In the third phase,parsing clothing items based on retrieving similar over-segmented images and morphing them into absolute image coordinates.Experiments are conducted on three public databases,and the experimental results show that proposed method has higher accuracy and promising performance.

Key words: pedestrian segmentation, Fast R-CNN, over-segmentation, parts retrieval

中图分类号:

TP391

王枫, 厉智, 刘青山, 孙玉宝. 基于部件检测与检索的行人精细化分割[J]. 电子学报, 2019, 47(2): 502-508.

WANG Feng, LI Zhi, LIU Qing-shan, SUN Yu-bao. Fine Pedestrian Segmentation with Parts Detection and Retrieval[J]. Acta Electronica Sinica, 2019, 47(2): 502-508.

参考文献

[1] Bourdev L,Maji S,Malik J.Describing people:A poselet-based approach to attribute classification[A].IEEE International Conference on Computer Vision[C].Barcelona:IEEE Press,2011.1543-1550.
[2] Liu S,Feng J,Song Z,et al.Hi,magic closet,tell me what to wear![A].Proceedings of the 20th ACM international conference on Multimedia[C].Nara:ACM,2012.619-628.
[3] Song Z,Wang M,Hua X,et al.Predicting occupation via human clothing and contexts[A].IEEE International Conference on Computer Vision[C].Barcelona:IEEE Press,2011.1084-1091.
[4] Chen H,Xu Z J,Liu Z Q,et al.Composite templates for cloth modeling and sketching[A].IEEE Conference on Computer Vision and Pattern Recognition[C].New York:IEEE Press,2006.943-950.
[5] Lin L,Wang X,Yang W,et al.Discriminatively trained and-or graph models for object shape detection[J].IEEE Transactions on pattern analysis and machine intelligence,2015,37(5):959-972.
[6] Wang N,Ai H.Who blocks who:Simultaneous clothing segmentation for grouping images[A].IEEE International Conference on Computer Vision[C].Barcelona:IEEE Press,2011.1535-1542.
[7] Hasan B,Hogg D C.Segmentation using Deformable Spatial Priors with Application to Clothing[A].British Mahine Vision Conference[C].Aberystwyth:British Machine Vision Association,2010.1-11.
[8] Bo Y,Fowlkes C C.Shape-based pedestrian parsing[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Colorado Springs:IEEE Press,2011.2265-2272.
[9] Yamaguchi K,Kiapour M H,Ortiz L E,et al.Parsing clothing in fashion photographs[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Providence:IEEE Press,2012.3570-3577.
[10] Ladicky L,Torr P H S,Zisserman A.Human pose estimation using a joint pixel-wise and part-wise formulation[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Portland:IEEE Press,2013.3578-3585.
[11] Kohli P,Rihan J,Bray M,et al.Simultaneous segmentation and pose estimation of humans using dynamic graph cuts[J].International Journal of Computer Vision,2008,79(3):285-298.
[12] Dong J,Chen Q,Xia W,et al.A deformable mixture parsing model with parselets[A].IEEE International Conference on Computer Vision[C].Sydney:IEEE Press,2013.3408-3415.
[13] Yang W,Luo P,Lin L.Clothing co-parsing by joint image segmentation and labeling[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Columbus:IEEE Press,2014.3182-3189.
[14] Carreira J,Sminchisescu C.Cpmc:Automatic object segmentation using constrained parametric min-cuts[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(7):1312-1328.
[15] Yamaguchi K,Hadi Kiapour M,Berg T L.Paper doll parsing:Retrieving similar styles to parse clothing items[A].IEEE International Conference on Computer Vision[C].Sydney:IEEE Press,2013.3519-3526.
[16] Yamaguchi K,Kiapour M H,Ortiz L E,et al.Retrieving similar styles to parse clothing[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(5):1028-1040.
[17] LiuS,Liang X,Liu L,et al.Matching-cnn meets knn:Quasi-parametric human parsing[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Boston:IEEE Press,2015.1419-1427.
[18] LiuS,Feng J,Domokos C,et al.Fashion parsing with weak color-category labels[J].IEEE Transactions on Multimedia,2014,16(1):253-265.
[19] Dantone M,Gall J,Leistner C,et al.Human pose estimation using body parts dependent joint regressors[A].IEEE Conference on Computer Vision and Pattern Recognition[C].Portland:IEEE Press,2013.3041-3048.
[20] Liang X,Liu S,Shen X,et al.Deep human parsing with active template regression[J].IEEE transactions on pattern analysis and machine intelligence,2015,37(12):2402-2414.
[21] Liang X,Xu C,Shen X,et al.Human parsing with contextualized convolutional neural network[A].IEEE International Conference on Computer Vision[C].Santiago:IEEE Press,2015.1386-1394.
[22] Girshick R.Fast r-cnn[A].IEEE International Conference on Computer Vision[C].Santiago:IEEE Press,2015.1440-1448.
[23] Zitnick C L,Dollár P.Edge boxes:Locating object proposals from edges[A].European Conference on Computer Vision[C].Zurich:Springer International Publishing,2014.391-405.
[24] Dollár P,Zitnick C L.Structured forests for fast edge detection[A].IEEE International Conference on Computer Vision[C].Sydney:IEEE Press,2013.1841-1848.

基于部件检测与检索的行人精细化分割

Fine Pedestrian Segmentation with Parts Detection and Retrieval

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

[1]	蔡强, 刘亚奇, 曹健, 李海生, 杜军平. 一种基于自适应标记与区域间近邻传播聚类的分水岭图像分割算法[J]. 电子学报, 2017, 45(8): 1911-1918.
[2]	周伟, 孙玉宝, 刘青山, 吴敏. 运动目标检测的l₀群稀疏RPCA模型及其算法[J]. 电子学报, 2016, 44(3): 627-632.