多尺度空间金字塔池化PCANet的行人检测

doi:10.19678/j.issn.1000-3428.0049831

计算机工程 ›› 2019, Vol. 45 ›› Issue (2): 270-277. doi: 10.19678/j.issn.1000-3428.0049831

多尺度空间金字塔池化PCANet的行人检测

夏胡云,叶学义,罗宵晗,王鹏

杭州电子科技大学模式识别与信息安全实验室,杭州 310018

收稿日期:2017-12-25 出版日期:2019-02-15 发布日期:2019-02-15
作者简介:夏胡云(1994—),男,硕士研究生,主研方向为深度学习、计算机视觉;叶学义,副教授、博士;罗宵晗、王鹏,硕士研究生。
基金资助:
国家自然科学基金(60802047,60702018)。

Pedestrian Detection Using Multi-scale Principal Component Analysis Network of Spatial Pyramid Pooling

XIA Huyun,YE Xueyi,LUO Xiaohan,WANG Peng

Lab of Pattern Recognition and Information Security,Hangzhou Dianzi Universtiy,Hangzhou 310018,China

Received:2017-12-25 Online:2019-02-15 Published:2019-02-15

摘要/Abstract

摘要：

针对非理想条件下行人检测的性能和效率问题,提出多尺度空间金字塔PCANet。将空间金字塔作为网络的特征池化层,通过分层池化特征的方式获得图像的显著性特征,并将底层特征和高层特征级联以获得样本的多尺度特征的向量表示,输入SVM分类器。在INRIA和NICTA数据库中,与HOG、CNN等算法进行行人检测对比实验,结果表明,该算法有更高的正确检测率、更低的漏检率和误检率。

关键词: 行人检测, 深度学习架构, 主成分分析网络, 多尺度特征, 空间金字塔池化, 显著性特征

Abstract:

Pedestrian detection is easily affected by non-ideal factors such as complex background,shooting angle and diversity of human body posture in natural environment.To solve this problem,this paper proposes a Multi-scale Principal Component Analysis Network of Spatial Pyramid Pooling (MS-PCANet-SPP).The feature pooling layer using spatial pyramid pooling method extract the saliency features of the image.The multi-scale features of the input samples can be obtained by cascading the high-level and low-level features,which is input to the SVM classifer.The comparative experiments are performed in the INRIA and NICTA databases.Experimental results show that,compared with HOG,CNN and other algorithms,MS-PCANet-SPP has a higher detection rate,a lower miss rate,and a lower false positive rate.

Key words: pedestrian detection, deep learning framework, Principal Component Analysis Network(PCANet), multi-scale feature, spatial pyramid pooling, saliency feature

中图分类号:

TP391.4

夏胡云,叶学义,罗宵晗,王鹏. 多尺度空间金字塔池化PCANet的行人检测[J]. 计算机工程, 2019, 45(2): 270-277.

XIA Huyun,YE Xueyi,LUO Xiaohan,WANG Peng. Pedestrian Detection Using Multi-scale Principal Component Analysis Network of Spatial Pyramid Pooling[J]. Computer Engineering, 2019, 45(2): 270-277.

http://www.ecice06.com/CN/Y2019/V45/I2/270

参考文献

［1］苏志松,李绍滋,陈淑媛,等.行人检测技术综述［J］.电子学报,2012,40(4):814-820.
［2］DALAL N,TRIGGS B.Histograms of oriented gradients for human detection［C］//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2005:886-893.
［3］MU Y,YAN S,LIU Y,et al.Discriminative local binary binary pattems for pedestrian detection i personal album［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2008:1-8.
［4］TUZEL O,PORIKLI F,MEER P.Pedestrian detection via classification on Riemannian manifolds［J］.IEEE Transactions on Pattem Analysis and Machine Intelligence,2008,30(10):1713-1727.
［5］VIOLA P,JONES M.Robust real-time face detection［J］.International Journal of Computer Vision,2004,57(2):137-154.
［6］HINTON G,SALAKHUTDINOV R.Reducing the dimensionality of data with neural networks［J］.Science,2006,313(5786):304-304.
［7］余凯,贾磊,陈雨强,等.深度学习的昨天、今天和明天［J］.计算机研究与发展,2013,50(9):1799-1804.
［8］CHAN T H,JIA K,GAO S,et al.PCANet:a simple deep learning baseline for image classification?［J］.IEEE Transactions on Image Processing,2015,24(12):5017-5032.
［9］GAO F,DONG J,LI B,et al.Automatic change detection in synthetic aperture radar images based on PCANet［J］.IEEE Geoscience and Remote Sensing Letters,2016,13(12):1792-1796.
［10］WANG Z,BI Z,WANG C,et al.Traffic lights recognition based on PCANet［C］//Proceedings of Chinese Automation Congress.Washington D.C.,USA:IEEE Press,2016:559-564.
［11］WANG S,CHEN L,ZHOU Z,et al.Human fall detection in surveillance video based on PCANet［J］.Multimedia Tools and Applications,2016,75(19):11603-11613.
［12］YANG J,YU K,GONG Y,et al.Linear spatial pyramid matching using sparse coding for image classification［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2009:1794-1801.
［13］SERMANET P,LECUN Y.Traffic sign recognition with multi-scale convolutional networks［C］//Proceedings of International Joint Conference on Neural Networks.Washington D.C.,USA:IEEE Press,2011:2809-2813.
［14］HOAI M.Regularized max pooling for image categoriza-tion［J］.Journal of the British Institution of Radio Engineers,2014,14(3):94-100.
［15］顾凌云,吕志文,杨勇,等.基于PCANet和SVM的谎言测试研究［J］.电子学报,2016,44(8):1969-1973.
［16］CHANG C C,LIN C J.LIBSVM:A library for support vector machines［J］.ACM Transactions on Intelligent Systems and Technology,2011,2(3):1-27.
［17］OVERETT G,PETERSSON L.Boosting with multiple classifier families［C］//Proceedings of IEEE Intelligent Vehicles Symposium.Washington D.C.,USA:IEEE Press,2007:1039-1044.
［18］SHAILAJA K,ANURADHA B.Effective face recognition using deep learning based linear discriminant classifica-tion［C］//Proceedings of IEEE International Conference on Computational Intelligence and Computing Research.Washington D.C.,USA:IEEE Press,2016:1-6.
［19］KRIZHEVSKY A,SUTSKEVER I,HINTON G.ImageNet classification with deep convolutional neural networks［C］//Proceedings of NIPS’12.Nevada,USA:Curran Associates InC.,2012:1097-1105.
［20］WOJEK C,WALK S,SCHIELE B.Multi-cue onboard pedestrian detection［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2009:794-801.

[1]	宋志娜, 李莎, 杨建明, 徐川. 基于特征与区域定位增强的遥感舰船目标检测[J]. 计算机工程, 2023, 49(8): 257-264.
[2]	丁子轩, 俞雷, 张娟, 李想, 王新宇. 基于深度残差自适应注意力网络的图像超分辨率重建[J]. 计算机工程, 2023, 49(5): 231-238.
[3]	任家豪, 张光华, 乔钢柱, 武秀萍. 多尺度特征融合的头影标志点检测[J]. 计算机工程, 2023, 49(3): 271-279.
[4]	苏鸣方, 胡立坤, 黄润辉. 基于上下文注意力的室外点云语义分割方法[J]. 计算机工程, 2023, 49(3): 248-256.
[5]	马素刚, 陈期梅, 侯志强, 杨小宝, 张子贤. 基于密集连接与特征增强的语义分割算法[J]. 计算机工程, 2023, 49(3): 263-270.
[6]	赵国川, 王姮, 张华, 庞杰, 周建. 基于完全自注意力的水电枢纽缺陷识别方法[J]. 计算机工程, 2022, 48(9): 277-285.
[7]	赫晓慧, 宋定君, 李盼乐, 田智慧, 周广胜. 融合多尺度特征的遥感影像道路提取方法[J]. 计算机工程, 2022, 48(8): 196-205.
[8]	徐超越, 余映, 何鹏浩, 李淼, 马玉辉. 基于U-Net的多尺度低照度图像增强网络[J]. 计算机工程, 2022, 48(8): 215-223.
[9]	于敏, 屈丹, 司念文. 改进的RetinaNet目标检测算法[J]. 计算机工程, 2022, 48(8): 249-257.
[10]	程志康, 孙锐, 孙琦景, 张旭东. 基于条件对抗自动编码器的跨年龄人脸合成[J]. 计算机工程, 2022, 48(6): 304-313.
[11]	刘晓蓉, 李小霞, 秦昌辉. 融合多尺度对比池化特征的行人重识别方法[J]. 计算机工程, 2022, 48(4): 292-298.
[12]	谢斌红, 秦耀龙, 张英俊. 基于学习主动中心轮廓模型的场景文本检测[J]. 计算机工程, 2022, 48(3): 244-252,262.
[13]	黄帅, 张毅. 基于梯形跨尺度特征耦合网络的SAR图像舰船检测[J]. 计算机工程, 2022, 48(12): 270-280.
[14]	陈乔松, 蒲柳, 张羽, 孙开伟, 邓欣, 王进. 结合整体注意力与分形稠密特征的图像超分辨率重建[J]. 计算机工程, 2022, 48(11): 207-214,223.
[15]	施政, 毛力, 孙俊. 基于YOLO的多模态加权融合行人检测算法[J]. 计算机工程, 2021, 47(8): 234-242.

选择文件类型/文献管理软件名称

选择包含的内容

多尺度空间金字塔池化PCANet的行人检测

Pedestrian Detection Using Multi-scale Principal Component Analysis Network of Spatial Pyramid Pooling

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

多尺度空间金字塔池化PCANet的行人检测

Pedestrian Detection Using Multi-scale Principal Component Analysis Network of Spatial Pyramid Pooling

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价