计算机科学 ›› 2018, Vol. 45 ›› Issue (8): 236-241.doi: 10.11896/j.issn.1002-137X.2018.08.042

• 图形图像与模式识别 • 上一篇    下一篇

基于卷积特征的非平衡人群密度估计方法

曲佳, 时增林, 叶阳东   

  1. 郑州大学信息工程学院 郑州450001
  • 收稿日期:2017-06-28 出版日期:2018-08-29 发布日期:2018-08-29
  • 作者简介:曲 佳(1993-),女,硕士生,主要研究方向为深度学习、计算机视觉; 时增林(1992-),男,硕士生,主要研究方向为机器学习、深度学习; 叶阳东(1962-),男,博士,教授,博士生导师,CCF高级会员,主要研究方向为机器学习、智能系统,E-mail:ieydye@zzu.edu.cn(通信作者)。
  • 基金资助:
    本文受国家自然科学基金(61170223,61502434),河南省科技攻关项目(172102210011)资助

Unbalanced Crowd Density Estimation Based on Convolutional Features

QU Jia, SHI Zeng-lin, YE Yang-dong   

  1. School of Information Engineering,Zhengzhou University,Zhengzhou 450001,China
  • Received:2017-06-28 Online:2018-08-29 Published:2018-08-29

摘要: 人群密度估计在智能监控领域具有重要的应用价值。大量理论和经验研究表明,基于数据驱动的深度神经网络往往优于传统的基于手工特征的方法。但是人群样本的数据规模很小,深层次的网络很难得到较优解。鉴于此,提出了3种解决方法:训练较浅的神经网络,使用预训练深度模型的全连接层特征和使用预训练深度模型的卷积-FV(Fisher Vector)特征。针对样本的不平衡性问题,提出了使用多个分类评估标准的解决方案。在标准数据集PETs2009上的实验结果表明,相比于现有的手工特征,卷积特征具有更好的效果。其次,相比于训练一个全新的卷积模型,基于迁移学习的深度卷积特征是更好的选择。另外,通过层数较少的深度模型获得的较低层特征的迁移性更好。

关键词: 迁移学习, 人群密度估计, 深度卷积神经网络, 纹理特征, 支持向量机

Abstract: Crowd density estimation plays a central role in intelligent monitoring.Deep neural network usually outperforms conventional approaches based on manual features owing to its data-driven superiority.However,deep neural networks are still far from optimal solution because of the scarceness of large-scale datasets.To address this problem,this paper investigated the feasibility of several solutions which are training shallow neural network from scratch,using fullyconnected layer features of pretrained deep neural network and aggregating convolutional features by way of fisher vector(FV).Aiming at the problem of unbalanced distribution,this paper further proposed several classification evaluation criteria.Comprehensive experiments were carried out on benchmark PETs2009 dataset.Results show that convolutional features outperform existing hand-crafted ones.Moreover,utilizing deep convolutional features based on transfer learning usually leads to better performance than the models trained from scratch.Finally,simpler pretrained models such as AlexNet can generalize better mobility of the lower layer features than more complicated ones such as VGGNet.

Key words: Crowd density estimation, Deep convolutional neural network, SVM, Texture feature, Transfer learning

中图分类号: 

  • TP391.4
[1]YANG H,SU H,ZHENG S,et al.The large-scale crowd density estimation based on sparse spatiotemporal local binary pattern[C]∥Proceedings of IEEE International Conference on Multimedia and Expo.IEEE,2011:1-6.
[2]FRADI H,ZHAO X,DUGELAY J L.Crowd density analysisusing subspace learning on local binary pattern[C]∥IEEE International Conference on Multimedia and Expo Workshops.IEEE,2013:1-6.
[3]DAVIES A C,YIN J H,VELASTIN S A.Crowd monitoring using image processing[J].Electronics & Communication Engineering Journal,1995,7(1):37-47.
[4]XU L Q,ANJULAN A.Crowd behaviours analysis in dynamic visual scenes of complex environment[C]∥IEEE International Conference on Image Processing.IEEE,2008:9-12.
[5]WU X,LIANG G,LEE K K,et al.Crowd density estimationusing texture analysis and learning[C]∥IEEE International Conference on Robotics and Biomimetics.IEEE,2006:214-219.
[6]MA W,HUANG L,LIU C.Crowd density analysis using co-occurrence texture features[C]∥International Conference on Computer Sciences and Convergence Information Technology.IEEE,2010:170-175.
[7]MA W,HUANG L,LIU C.Advanced local binary pattern descriptors for crowd estimation[C]∥IEEE International Confe-rence on Computational Intelligence and Industrial Application Pacific-Asia Workshop.IEEE,2008:958-962.
[8]WANG Z,LIU H,QIAN Y,et al.Crowd density estimationbased on local binary pattern co-occurrence matrix[C]∥IEEE International Conference on Multimedia and Expo Workshops.IEEE,2012:372-377.
[9]MARANA A N,VERONA V V.Wavelet packet analysis for crowd density estimation[OL].http://www.oalib.com/refe-rences/15205544.
[10]MARANA A N,VELASTIN S A,COSTA L F,et al.Estimation of crowd density using image processing[C]∥Proceedings of IEEE Colloquium on Image Processing for Security Applications.1997:11/1-11/8.
[11]HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.
[12]BENGIO Y,COURVILLE A,VINCENT P.Representationlearning:A review and new perspectives[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2013,35(8):1798-1828.
[13]KRIZHEVSKY A,SUTSKEVER I,HINTON G E.ImageNet classification with deep convolutional neural networks[C]∥Proceedings of Advances in Neural Information Processing Systems Nevada.USA:NIPS,2012:1097-1105.
[14]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[J].arXiv preprint arXiv:1409.1556,2014.
[15]SZEGEDY C,LIU W,JIA Y,et al.Going deeper with convolutions[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2015:1-9.
[16]ZHOU Y,CHEUNG N M.Vehicle Classification using Transferable Deep Neural Network Features[J].arXiv preprint ar-Xiv:1601.01145,2016.
[17]SARKAR S,PATEL V M,CHELLAPPA R.Deep feature-based face detection on mobile devices[C]∥IEEE International Conference on Identity,Security and Behavior Analysis.IEEE,2016:1-8.
[18]CIMPOI M,MAJI S,VEDALDI A.Deep filter banks for texture recognition and segmentation[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2015:3828-3836.
[19]KANDASWAMY K K,CHOU K C,MARTINETZ T,et al.AFP-Pred:A random forest approach for predicting antifreeze proteins from sequence-derived properties[J].Journal of Theoretical Biology,2011,270(1):56-62.
[20]LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-basedlearning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[21]POLUS A,SCHOFER J L,USHPIZ A.Pedestrian flow and le-vel of service[J].Journal of Transportation Engineering,1983,109(1):46-56.
[22]ZEILER M D,FERGUS R.Visualizing and understanding con-volutional networks[C]∥European Conference on Computer Vision.Zurich,Switzerland:Springer,2014:818-833.
[23]YOSINSKI J,CLUNE J,BENGIO Y,et al.How transferable are features in deep neural networks?[C]∥Proceedings of Advances in Neural Information Processing Systems.2014:3320-3328.
[24]VEDALDI A,LENC K.MatConvNet:Convolutional NeuralNetworks for MATLAB[C]∥Proceedings of ACM Internatio-nal Conference on Multimedia.ACM,2015:689-692.
[1] 方义秋, 张震坤, 葛君伟.
基于自注意力机制和迁移学习的跨领域推荐算法
Cross-domain Recommendation Algorithm Based on Self-attention Mechanism and Transfer Learning
计算机科学, 2022, 49(8): 70-77. https://doi.org/10.11896/jsjkx.210600011
[2] 沈超, 何希平.
基于纹理特征增强和轻量级网络的人脸防伪算法
Face Anti-spoofing Algorithm Based on Texture Feature Enhancement and Light Neural Network
计算机科学, 2022, 49(6A): 390-396. https://doi.org/10.11896/jsjkx.210600217
[3] 孙洁琪, 李亚峰, 张文博, 刘鹏辉.
基于离散小波变换的双域特征融合深度卷积神经网络
Dual-field Feature Fusion Deep Convolutional Neural Network Based on Discrete Wavelet Transformation
计算机科学, 2022, 49(6A): 434-440. https://doi.org/10.11896/jsjkx.210900199
[4] 单晓英, 任迎春.
基于改进麻雀搜索优化支持向量机的渔船捕捞方式识别
Fishing Type Identification of Marine Fishing Vessels Based on Support Vector Machine Optimized by Improved Sparrow Search Algorithm
计算机科学, 2022, 49(6A): 211-216. https://doi.org/10.11896/jsjkx.220300216
[5] 陈景年.
一种适于多分类问题的支持向量机加速方法
Acceleration of SVM for Multi-class Classification
计算机科学, 2022, 49(6A): 297-300. https://doi.org/10.11896/jsjkx.210400149
[6] 王君锋, 刘凡, 杨赛, 吕坦悦, 陈峙宇, 许峰.
基于多源迁移学习的大坝裂缝检测
Dam Crack Detection Based on Multi-source Transfer Learning
计算机科学, 2022, 49(6A): 319-324. https://doi.org/10.11896/jsjkx.210500124
[7] 侯夏晔, 陈海燕, 张兵, 袁立罡, 贾亦真.
一种基于支持向量机的主动度量学习算法
Active Metric Learning Based on Support Vector Machines
计算机科学, 2022, 49(6A): 113-118. https://doi.org/10.11896/jsjkx.210500034
[8] 彭云聪, 秦小林, 张力戈, 顾勇翔.
面向图像分类的小样本学习算法综述
Survey on Few-shot Learning Algorithms for Image Classification
计算机科学, 2022, 49(5): 1-9. https://doi.org/10.11896/jsjkx.210500128
[9] 胡伏原, 万新军, 沈鸣飞, 徐江浪, 姚睿, 陶重犇.
深度卷积神经网络图像实例分割方法研究进展
Survey Progress on Image Instance Segmentation Methods of Deep Convolutional Neural Network
计算机科学, 2022, 49(5): 10-24. https://doi.org/10.11896/jsjkx.210200038
[10] 邢云冰, 龙广玉, 胡春雨, 忽丽莎.
基于SVM的类别增量人体活动识别方法
Human Activity Recognition Method Based on Class Increment SVM
计算机科学, 2022, 49(5): 78-83. https://doi.org/10.11896/jsjkx.210400024
[11] 谭珍琼, 姜文君, 任演纳, 张吉, 任德盛, 李晓鸿.
基于二分图的个性化学习任务分配
Personalized Learning Task Assignment Based on Bipartite Graph
计算机科学, 2022, 49(4): 269-281. https://doi.org/10.11896/jsjkx.210500125
[12] 武玉坤, 李伟, 倪敏雅, 许志骋.
单类支持向量机融合深度自编码器的异常检测模型
Anomaly Detection Model Based on One-class Support Vector Machine Fused Deep Auto-encoder
计算机科学, 2022, 49(3): 144-151. https://doi.org/10.11896/jsjkx.210100142
[13] 左杰格, 柳晓鸣, 蔡兵.
基于图像分块与特征融合的户外图像天气识别
Outdoor Image Weather Recognition Based on Image Blocks and Feature Fusion
计算机科学, 2022, 49(3): 197-203. https://doi.org/10.11896/jsjkx.201200263
[14] 张舒萌, 余增, 李天瑞.
跨领域文本的可迁移情绪分析方法
Transferable Emotion Analysis Method for Cross-domain Text
计算机科学, 2022, 49(3): 218-224. https://doi.org/10.11896/jsjkx.210400034
[15] 李星燃, 张立言, 姚树婧.
结合特征融合和注意力机制的微表情识别方法
Micro-expression Recognition Method Combining Feature Fusion and Attention Mechanism
计算机科学, 2022, 49(2): 4-11. https://doi.org/10.11896/jsjkx.210900028
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!