[1]罗南超,郑伯川.视频监控领域深度特征编码的行人检测算法[J].西安科技大学学报,2019,(04):151-157.[doi:10.13800/j.cnki.xakjdxxb.2019.0419]
 LUO Nan-chao,ZHENG Bo-chuan.Deep feature coding for pedestrian detection in video surveillance[J].Journal of Xi’an University of Science and Technology,2019,(04):151-157.[doi:10.13800/j.cnki.xakjdxxb.2019.0419]
点击复制

视频监控领域深度特征编码的行人检测算法(/HTML)
分享到:

西安科技大学学报[ISSN:1672-9315/CN:61-1434/N]

卷:
期数:
2019年04期
页码:
151-157
栏目:
出版日期:
2019-07-30

文章信息/Info

Title:
Deep feature coding for pedestrian detection in video surveillance
文章编号:
1672-9315(2019)04-0701-07
作者:
罗南超1郑伯川2
(1.阿坝师范学院 数学与计算机科学学院,四川 汶川 623002; 2.西华师范大学 数学与信息学院,四川 南充 637002)
Author(s):
LUO Nan-chao1ZHENG Bo-chuan2
(1.School of Mathematics and Computer Science,Aba Teachers University,Wenchuan 623002,China; 2.School of Mathematics and Information,China West Normal University,Nanchong 637002,China)
关键词:
模式识别 深度编码 行人检测 SVM算法 自编码网络 聚合通道特征
Keywords:
pattern recognition deep coding pedestrian detection SVM Model auto-encoder network aggregation channel feature
分类号:
TP 391.9
DOI:
10.13800/j.cnki.xakjdxxb.2019.0419
文献标志码:
A
摘要:
由于高清视频监控领域现有行人检测算法在复杂背景下检测准确率不高且检测实时性不强,提出了一种新颖的深度特征行人检测算法,该算法利用聚合通道特征模型对监控高清图像进行预处理,筛选出具有显著特性的疑似目标,大大降低目标检测的数量; 然后对获取的疑似目标区域进行尺度校正与特征提取,并输入到深度模型中进行深度特征编码,提高特征的表征能力; 最后输入到LSSVM分类模型,得到最终的行人检测结果。仿真实验结果显示所提行人检测算法在保证检测准确率的同时,具有较高的检测效率。
Abstract:
To solve the problem of poor real-time detection and low precision in video surveillance,a novel deep feature-based pedestrian detection algorithm is proposed.The algorithm firstly uses the aggregation channel feature model to process the surveillance images,and selects the suspected target region with salient characteristics.Then,the scaled correction and feature extraction are performed on the obtained suspected target region.The corresponding low-level features are obtained and input into the deep auto-encoder network for deep feature coding so as to enhance the representation ability.Finally,the coding feature is input into the least squares SVM classification model to obtain the final detection results.A large number of qualitative and quantitative experimental results show that the proposed detection algorithm guarantees the accuracy of pedestrian detection with higher efficiency.

参考文献/References:

[1] 覃 剑,王美华.采用在线高斯模型的行人检测候选框快速生成方法[J].光学学报,2016,36(11):169-179.QIN Jian,WANG Mei-hua.Fast pedestrian proposal generation algorithm using online Gaussian model[J].Acta Optica Sinica,2016,36(11):169-179.[2]吴冬梅,王 静,李白萍,等.基于改进SURF算法的大规模群体人数统计[J].西安科技大学学报,2015,35(5):650-655.WU Dong-mei,WANG Jing,LI Bai-ping,et al.Large-scale population statistics based on improved SURF algorithm[J].Journal of Xi’an University of Science and Technology,2015,35(5):650-655.[3]Benenson R,Omran M,Hosang J,et al.Ten years of pedestrian detection,what have we learned?[C]//European Conference on Computer Vision,2014:613-627.[4]Tian Y,Luo P,Wang X,et al.Deep learning strong parts for pedestrian detection[C]//International Conference on Computer Vision,2015:1904-1912.[5]Liu W,Anguelov D,Erhan D,et al.SSD:Single shot MultiBox detector[C]//European Conference on Computer Vision,2016:21-37.[6]Ren S,He K,Girshick R,et al.Faster rcnn:towards real-time object detection with region proposal networks[C]//Advances in Neural Information Processing Systems,2015:91-99.[7]Byeon Y H,Kwak K C.A performance comparison of pedestrian detection using faster RCNN and ACF[C]//International Conference on Advanced Applied Informatics,2017:858-863.[8]Zh Z,Xie C,Wang J,et al.Deepvotin:a robust and explainable deep network for semantic part detection under partial occlusion[C]//IEEE Conference on Computer Vision and Pattern Recognition,2018:1372-1380.[9]Munder S,Gavrila D M.An experimental study on pedestrian classification[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(11):1863-1868.[10]Zhao X,He Z,Zhang S,et al.Robust pedestrian detection in thermal infrared imagery using a shape distribution histogram feature and modified sparse representation classification[J].Pattern Recognition,2015,48(6):1947-1960.[11]Tang Z,Wang S,Huo J,et al.Bayesian framework with non-local and low-rank constraint for image reconstruction[C]//Journal of Physics Conference Series,2017:010-038.[12]Zhang S,Benenson R,Schiele B,et al.Filtered channel features for pedestrian detection[C]//Computer Vision and Pattern Recognition,2015:1751-1760.[13]Guo L,Ge P S,Zhang M H,et al.Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine[J].Expert Systems with Applications,2012,39(4):4274-4286.[14]Zhang J,Shan S,Kan M,et al.Coarse-to-Fine Auto-Encoder Networks(CFAN)for real-time face alignment[C]//European Conference on Computer Vision,2014:1-16.[15]Mathur,Mridul Kumar.Image compression using robust error back propagation neural network with GDAL[J].International Journal of Research and Engineering,2017,14(4):133-136.[16]Li L,Yu S,Xiao W,et al.Sequence-based identification of recombination spots using pseudo nucleic acid representation and recursive feature extraction by linear kernel SVM[J].BMC Bioinformatics,2014,15(1):340.[17]Hosang J H,Benenson R,Dollar P,et al.What makes for effective detection proposals[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(4):814-830.[18]Girshick R B,Donahue J,Darrell T,et al.Region-based convolutional networks for accurate object detection and segmentation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(1):142-158.[19]Dalal N,Triggs B.Histograms of oriented gradients for human detection[C]//Computer Vision and Pattern Recognition,2005:886-893.[20]Dollar P,Wojek C,Schiele B,et al.Pedestrian detection:an evaluation of the state of the art[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2012,34(4):743-761.[21]Dollar P,Appel R,Kienzl W.Crosstalk cascades for frame-rate pedestrian detection[C]//European Conference on Computer Vision,2012:645-659.[22]Sabzmeydani P, Mori G. Detecting Pedestrians by Learning Shapelet Features[C]//Computer Vision and Pattern Recognition, 2007: 1-8.[23]Wang X,Han T X,Yan S,et al.An HOG-LBP human detector with partial occlusion handling[C]//International Conference on Computer Vision,2009:32-39.[24]Girshick R B.Fast R-CNN[C]//International Conference on Computer Vision,2015:1440-1448.[25]Felzenszwalb P F,Girshick R B,Mcallester D A,et al.Object detection with discriminatively trained part-based models[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2010,32(9):1627-1645.

备注/Memo

备注/Memo:
收稿日期:2019-01-28 责任编辑:高 佳基金项目:四川省科技计划资助项目(2019YFG0299); 四川省教育厅自然科学重点项目(15ZA0339); 四川省教育厅自然科学一般项目(18ZB0007); 阿坝师范学院校级项目( ASB17-04)第一作者:罗南超(1975-),男,四川富顺人,副教授,E-mail:luonc75@aliyun.com通信作者:郑伯川(1974-),男,四川自贡人,博士,教授,E-mail:zhengbochuan@126.com罗南超,郑伯川.视频监控领域深度特征编码的行人检测算法[J].西安科技大学学报,2019,39(4):701-707.LUO Nan-chao,ZHENG Bo-chuan.Deep feature coding for pedestrian detection in video surveillance[J].Journal of Xi’an University of Science and Technology,2019,39(4):701-707.
更新日期/Last Update: 1900-01-01