基于ACF与PCANet改进通道特征的级联行人检测

doi:10.3969/j.issn.1000-3428.2017.11.036

摘要/Abstract

摘要：

针对聚合通道特征(ACF)算法误检窗口多的问题,提出一种由粗到精的级联行人检测算法。采用ACF算法快速粗检,改进通道特征来滤除误检窗口,以每个图像通道学习主成分分析(PCA)滤波器组,代替PCANet从训练图像和卷积图中学习滤波器组,用图像通道进行单层卷积,代替PCANet的双层卷积以降低特征维数,提升对行人的表达能力,并对卷积图池化降维,得到改进的通道特征。仿真结果表明,该算法相对于原ACF算法误检窗口减少,检测率在INRIA、Caltech数据库上分别提高3.8%和17.5%。

关键词: 行人检测, 聚合通道特征算法, 积分通道特征, 卷积网络, 主成分分析, 自动学习

Abstract:

As the Aggregate Channel Features(ACF) algorithm has many false detection windows,a coarse-to-fine cascaded pedestrian detection algorithm is proposed.ACF is employed as the coarse detector,and then the channel features are improved to filter out false detection windows.The Principal Component Analysis(PCA) filter bank are learned from each channel,instead of learning filter bank from the training image and convolution maps.The single-layer convolution is executed on the filter bank and channels,to reduce feature dimension and improve feature discrimination capability,Finally,a pooling operation is applied on convolution maps to reduce the feature dimensionobtaining improving channel features.Simulation results show that compared with the original ACF algorithm,the proposed method has less false detection windows and the detection rate on INRIA and Caltech databases increases by 3.8% and 17.5% respectively.

Key words: pedestrian detection, Aggregate Channel Features(ACF) algorithm, Integral Channel Features(ICF), convolutional network, Principal Component Analysis(PCA), automatic learning

中图分类号:

TP391.41

黄鹏,于凤芹. 基于ACF与PCANet改进通道特征的级联行人检测[J]. 计算机工程, doi: 10.3969/j.issn.1000-3428.2017.11.036.

HUANG Peng,YU Fengqin. Cascaded Pedestrian Detection Based on ACF and Improved Channel Features by PCANet[J]. Computer Engineering, doi: 10.3969/j.issn.1000-3428.2017.11.036.

参考文献

参考文献［1］苏松志,李绍滋,陈淑媛.行人检测计数综述［J］.电子学报,2012,4:814-820. ［2］DALAL N,TRIGGS B.Histograms of Oriented Gradients for Human Detection［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Reco-gnition.Washington D.C.,USA:IEEE Press,2005:886-893. ［3］姚雪琴,李晓华,周激流.基于边缘对称性和HOG的行人检测方法［J］.计算机工程,2012,38(5):179-182. ［4］DOLLR P,TU Z,PERONA P,et al.Integral Channel Features［C］//Proceedings of British Machine Vision Conference.Washington D.C.,USA:IEEE Press,2009:1-11. ［5］DOLLR P,APPEL R,BELONGIE S,et al.Fast Feature Pyramids for Object Detection［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(8):1532-1545. ［6］NAM W,DOLLR P,HAN J.Local Decorrelation for Improved Pedestrian Detection［C］//Proceedings of the 27th International Conference on Neural Information Processing Systems.Montreal,Canada:MIT Press,2014:424-432. ［7］BENENSON R,MATHIAS M,TUYTELAARS T,et al.Seeking the Strongest Rigid Detector［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3666-3673. ［8］ZHANG S S,BAUCKHAGE C,CREMERS A.Informed Haar-like Features Improve Pedestrian Detec-tion［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:947-954. ［9］ZHANG S S,BENENSON R,SCHIELE B.Filtered Channel Features for Pedestrian Detection［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:1751-1760. ［10］SERMANET P,KAVUKCUOGLU K,CHINTALA S,et al.Pedestrian Detection with Unsupervised Multistage Feature Learning［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3626-3633. ［11］RENX F,RAMANAN D.Histograms of Sparse Codesfor Object Detection［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3246-3253. ［12］LIM J,ZITNICK C,DOLLR P.Sketch Tokens:A Learned Mid-level Representation for Contour and Object Detection［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:3158-3165. ［13］CHEN T H,JIA K,GAO S H,et al.PCANet:A Simple Deep Learning Baseline for Image Classification［J］.IEEE Transactions on Image Processing,2015,12(24):5017-5032. ［14］KANG L,YE P,LI Y,et al.Convolutional Neural Net-works for No-reference Image Quality Assessment［C］//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:1733-1740. ［15］DOLLáR P,WOJEK C,BELONGIE S,et al.Pedestrian Detection:An Evaluation of the State of the Art［J］.IEEE Transactionson Pattern Analysis and Machine Intelligence,2011,34(4):743-761. 编辑刘冰

[1]	曹渝昆, 桂丽嫒. 基于深度可分离卷积的轻量级时间卷积网络设计[J]. 计算机工程, 2020, 46(9): 95-100,109.
[2]	张毅, 赵杰煜, 王翀, 郑烨. 时域注意力Dense-TCNs在多模手势识别中的应用[J]. 计算机工程, 2020, 46(9): 101-109.
[3]	陈泽, 叶学义, 钱丁炜, 魏阳洋. 基于改进Faster R-CNN的小尺度行人检测[J]. 计算机工程, 2020, 46(9): 226-232,241.
[4]	杨瑞朋, 屈丹, 朱少卫, 钱叶魁, 唐永旺. 基于改进时间卷积网络的日志序列异常检测[J]. 计算机工程, 2020, 46(8): 50-57.
[5]	胡涛, 佃松宜, 蒋荣华. 基于长短时记忆神经网络的硬件木马检测[J]. 计算机工程, 2020, 46(7): 110-115.
[6]	林凯瀚, 赵慧民, 吕巨建, 詹瑾, 刘晓勇, 陈荣军. 基于Mask R-CNN的人脸检测与分割方法[J]. 计算机工程, 2020, 46(6): 274-280.
[7]	党小超, 邓琦研, 郝占军. 基于30°角同心圆环形取样的室内人员检测方法[J]. 计算机工程, 2020, 46(4): 198-205.
[8]	张驰, 谭南林, 李国正, 苏树强. 基于多级特征的红外图像行人检测算法[J]. 计算机工程, 2020, 46(4): 260-265.
[9]	蔡凯, 李新福, 田学东. 基于视觉注意力分析的3D内容生成方法[J]. 计算机工程, 2020, 46(4): 266-272.
[10]	张瑞, 陈红卫. 基于特征优化与SVPSO的工控入侵检测[J]. 计算机工程, 2020, 46(4): 19-25.
[11]	张传伟, 曾虹钧, 杨萌月, 李波, 陈尚瑞. 基于多分辨率滤波通道的多尺度行人检测[J]. 计算机工程, 2020, 46(2): 235-241.
[12]	李浩, 霍雯, 裴春营, 袁瑶瑶, 康雁. 融合VGG与FCN的智能出租车订单预测模型[J]. 计算机工程, 2020, 46(12): 276-282.
[13]	杨姗姗, 姜丽芬, 孙华志, 马春梅. 基于时间卷积网络的多项选择机器阅读理解[J]. 计算机工程, 2020, 46(11): 97-103.
[14]	王旭仁,马慧珍,冯安然,许祎娜. 基于信息增益与主成分分析的网络入侵检测方法[J]. 计算机工程, 2019, 45(6): 175-180.
[15]	闫玉娟,李化,赵菊敏,李灯熬,刘佳. 基于CRFID和模式识别的跌倒检测系统[J]. 计算机工程, 2019, 45(6): 297-302,309.