2.845

2023影响因子

(CJCR)

  • 中文核心
  • EI
  • 中国科技核心
  • Scopus
  • CSCD
  • 英国科学文摘

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于序的空间金字塔池化网络的人群计数方法

时增林 叶阳东 吴云鹏 娄铮铮

时增林, 叶阳东, 吴云鹏, 娄铮铮. 基于序的空间金字塔池化网络的人群计数方法. 自动化学报, 2016, 42(6): 866-874. doi: 10.16383/j.aas.2016.c150663
引用本文: 时增林, 叶阳东, 吴云鹏, 娄铮铮. 基于序的空间金字塔池化网络的人群计数方法. 自动化学报, 2016, 42(6): 866-874. doi: 10.16383/j.aas.2016.c150663
SHI Zeng-Lin, YE Yang-Dong, WU Yun-Peng, LOU Zheng-Zheng. Crowd Counting Using Rank-based Spatial Pyramid Pooling Network. ACTA AUTOMATICA SINICA, 2016, 42(6): 866-874. doi: 10.16383/j.aas.2016.c150663
Citation: SHI Zeng-Lin, YE Yang-Dong, WU Yun-Peng, LOU Zheng-Zheng. Crowd Counting Using Rank-based Spatial Pyramid Pooling Network. ACTA AUTOMATICA SINICA, 2016, 42(6): 866-874. doi: 10.16383/j.aas.2016.c150663

基于序的空间金字塔池化网络的人群计数方法

doi: 10.16383/j.aas.2016.c150663
基金项目: 

国家自然科学基金资助 61170223, 61502432, 61502434

详细信息
    作者简介:

    时增林 郑州大学信息工程学院硕士研究生. 主要研究方向为计算机视觉, 机器学习, 深度学习. E-mail: iezlshi@gs.zzu.edu.cn

    吴云鹏 郑州大学信息工程学院博士研究生. 主要研究方向为机器学习, 计算机视觉. E-mail: ieypwu@zzu.edu.cn

    娄铮铮 郑州大学信息工程学院讲师, 博士.主要研究方向为机器学习, 模式识别, 计算机视觉. E-mail: iezzlou@zzu.edu.cn

    通讯作者:

    叶阳东 郑州大学信息工程学院教授. 主要研究方向为智能系统, 机器学习, 数据库.本文通信作者. E-mail: ieydye@zzu.edu.cn

Crowd Counting Using Rank-based Spatial Pyramid Pooling Network

Funds: 

National Natural Science Foundation of China 61170223, 61502432, 61502434

More Information
    Author Bio:

    SHI Zeng-Lin Master student at the School of Information Engineering, Zhengzhou University. His research interest covers computer vision, machine learning, and deep learning

    WU Yun-Peng Ph. D. candidate at the School of Information Engineering, Zhengzhou University. His research interest covers machine learning and computer vision

    LOU Zheng-Zheng Lecturer, Ph. D. at the School of Information Engineering, Zhengzhou University. His research interest covers machine learning, pattern recognition, and computer vision

    Corresponding author: YE Yang-Dong Professor at the School of Information Engineering, Zhengzhou University. His research interest covers intellectual system, machine learning, and database system. Corresponding author of this paper
  • 摘要: 视频中的人群计数在智能监控领域具有重要价值. 由于摄像机透视效果、图像背景、人群密度分布不均匀和行人遮挡等干扰因素的制约, 基于底层特征的传统计数方法准确率较低. 本文提出一种基于序的空间金字塔池化(Rank-based spatial pyramid pooling, RSPP)网络的人群计数方法. 该方法将原图像分成多个具有相同透视范围的子区域并在各个子区域分别取不同尺度的子图像块, 采用基于序的空间金字塔池化网络估计子图像块人数, 然后相加所有子图像块人数得出原图像人数. 提出的图像分块方法有效地消除了摄像机透视效果和人群密度分布不均匀对计数的影响. 提出的基于序的空间金字塔池化不仅能够处理多种尺度的子图像块, 而且解决了传统池化方法易损失大量重要信息和易过拟合的问题. 实验结果表明, 本文方法相比于传统方法具有准确率高和鲁棒性好的优点.
  • 图  1  传统人群计数方法和本文人群计数方法的流程

    Fig.  1  The flow chart of traditional and the proposed crowd counting methods

    图  2  当前典型的卷积-池化结构

    Fig.  2  The typical convolution-pooling structure

    图  3  典型的空间金字塔层结构

    Fig.  3  The typical spatial pyramid pooling structure

    图  4  图像分块方法

    Fig.  4  The methods of dividing image into sub-image blocks

    图  5  计数模型的整体结构

    Fig.  5  The overall structure of the crowd counting model

    图  6  UCSD 数据集示例帧

    Fig.  6  Examples frames of the UCSD dataset

    图  7  子图像块示例

    Fig.  7  Examples of sub-image blocks

    图  8  整个测试集的计数结果

    Fig.  8  The recognition results on the entire testing frames

    图  9  在多种人群密度上的计数结果

    Fig.  9  Various density crowd counting

    表  1  人群CNN 模型的详细结构

    Table  1  Architecture specics for crowd CNN model

    层数1234 5(输出)
    操作conv+relu+rsp+rn conv+relu+rsp+rn conv+relu+rspp full full
    通道数6464645121
    卷积大小5×5 5×5 5×5 - -
    卷积步长1×1 1×1 1×1 - -
    池化大小3×3 3×3 {4×4, 2×2, 1×1} - -
    池化步长2×2 2×2 - - -
    填充大小2×2×2×2 2×2×2×2 2×2×2×2 - -
    下载: 导出CSV

    表  2  实验数据

    Table  2  Experimental data

    图像块尺度训练集测试集
    64×64 104 000 3 600
    44×44 104 000 4 800
    28×28 44 000 3 600
    下载: 导出CSV

    表  3  多种池化方法在尺度为64 的子图像块上的测试结果

    Table  3  Testing results for sub-image blocks with the scale of 64 of various pooling methods

    池化方法训练集测试集
    MAE MSE MAE MSE
    平均池化1.122.291.523.13
    最大池化0.270.130.841.15
    随机池化1.292.271.423.18
    基于序的随机池化0.430.320.640.81
    下载: 导出CSV

    表  4  子图像块上的测试结果

    Table  4  The testing results in sub-image blocks

    图像块尺度联合训练单独训练
    MAE MSE MAE MSE
    64×640.640.810.640.81
    44×440.841.081.985.7
    28×280.721.061.684.16
    下载: 导出CSV

    表  5  整幅图像上的测试结果

    Table  5  The testing results in image

    方法MAE MSE
    文献[4]3.657.41
    文献[9]2.257.82
    文献[3]2.247.97
    单CNN方法2.126.83
    文献[[23]2.087.25
    本文方法1.895.43
    下载: 导出CSV
  • [1] Wu B, Nevatia R. Detection of multiple, partially occluded humans in a single image by Bayesian combination of edgelet part detectors. In: Proceedings of the 10th IEEE International Conference on Computer Vision. Beijing, China: IEEE, 2005. 90-97
    [2] Zhao T, Nevatia R, Wu B. Segmentation and tracking of multiple humans in crowded environments. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(7) : 1198-1211
    [3] Chan A B, Liang Z S J, Vasconcelos N. Privacy preserving crowd monitoring: counting people without people models or tracking. In: Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition. Anchorage, AK: IEEE, 2008. 1-7
    [4] Chan A B, Vasconcelos N. Counting people with low-level features and Bayesian regression. IEEE Transactions on Image Processing, 2012, 21(4) : 2160-2177
    [5] Idrees H, Saleemi I, Seibert C, Shah M. Multi-source multi-scale counting in extremely dense crowd images. In: Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Portland, USA: IEEE, 2013. 2547-2554
    [6] Lempitsky V, Zisserman A. Learning to count objects in images. In: Proceedings of Advances in Neural Information Processing Systems. Vancouver, Canada: NIPS, 2010. 1324-1332
    [7] Ma W, Huang L, Liu C. Crowd density analysis using co-occurrence texture features. In: Proceedings of the 5th IEEE International Conference on Computer Sciences and Convergence Information Technology. Seoul, Korea: IEEE, 2010. 170-175
    [8] Kong D, Gray D, Tao H. A viewpoint invariant approach for crowd counting. In: Proceedings of the 18th IEEE International Conference on Pattern Recognition. Hong Kong, China: IEEE, 2006. 1187-1190
    [9] Chen K, Loy C C, Gong S G, Xiang T. Feature mining for localised crowd counting. In: Proceedings of the 23rd British Machine Vision Conference. Surrey, British: BMVA Press, 2012. 1-3
    [10] Ryan D, Denman S, Sridharan S, Fookes C. An evaluation of crowd counting methods, features and regression models. Computer Vision and Image Understanding, 2015, 130: 1-17
    [11] Rosten E, Porter R, Drummond T. Faster and better: a machine learning approach to corner detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2010, 32(1) : 105-119
    [12] Wu X Y, Liang G Y, Lee K K, Xu Y. Crowd density estimation using texture analysis and learning. In: Proceedings of the 2006 IEEE International Conference on Robotics and Biomimetics. Kunming, China: IEEE, 2006. 214-219
    [13] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks. Science, 2006, 313(5786) : 504-507
    [14] Zeiler M D, Fergus R. Visualizing and understanding convolutional networks. In: Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014. 818-833
    [15] Nair V, Hinton G E. Rectified linear units improve restricted Boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning. Haifa, Israel: JMLR, 2010. 807-814
    [16] Krizhevsky A, Sutskever I, Hinton G E. ImageNet classification with deep convolutional neural networks. In: Proceedings of Advances in Neural Information Processing Systems. Nevada, USA: NIPS, 2012. 1097-1105
    [17] He K M, Zhang X Y, Ren S Q, Sun J. Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Proceedings of the 13th European Conference on Computer Vision. Zurich, Switzerland: Springer, 2014. 346-361
    [18] Zeiler M D, Fergus R. Stochastic pooling for regularization of deep convolutional neural networks. In: Proceedings of the 2013 International Conference on Learning Representation. Arizona, USA: ICLR, 2013. 1-9
    [19] Sainath T N, Kingsbury B, Saon G, Soltau H, Mohamed A R, Dahl G, Ramabhadran B. Deep convolutional neural networks for large-scale speech tasks. Neural Networks, 2015, 64: 39-48
    [20] Michalewicz Z. Genetic Algorithms + Data Structures=Evolution Programs. Berlin Heidelberg: Springer Science & Business Media, 2013. 59-61
    [21] Saunders C, Gammerman A, Vovk V. Ridge regression learning algorithm in dual variables. In: Proceedings of the 15th International Conference on Machine Learning. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc., 1998. 515-521
    [22] Jia Y Q, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T. Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia. Florida, USA: ACM, 2014. 675-678
    [23] Zhang Z X, Wang M, Geng X. Crowd counting in public video surveillance by label distribution learning. Neurocomputing, 2015, 166: 151-163
  • 加载中
图(9) / 表(5)
计量
  • 文章访问数:  3553
  • HTML全文浏览量:  453
  • PDF下载量:  1652
  • 被引次数: 0
出版历程
  • 收稿日期:  2015-10-31
  • 录用日期:  2016-04-01
  • 刊出日期:  2016-06-20

目录

    /

    返回文章
    返回