基于尺度自适应卷积神经网络的人群计数算法

doi:10.19678/j.issn.1000-3428.0053842

计算机工程 ›› 2020, Vol. 46 ›› Issue (2): 250-254,261. doi: 10.19678/j.issn.1000-3428.0053842

基于尺度自适应卷积神经网络的人群计数算法

翟强, 王陆洋, 殷保群, 彭思凡, 邢思思

中国科学技术大学自动化系, 合肥 230027

收稿日期:2019-01-28 修回日期:2019-03-05 发布日期:2019-03-14
作者简介:翟强(1992-),男,硕士研究生,主研方向为图像处理;王陆洋,博士研究生;殷保群,教授;彭思凡、邢思思,硕士研究生。
基金资助:
装备预研领域基金（61403120201）。

Crowd Counting Algorithm Based on Scale Adaptive Convolutional Neural Network

ZHAI Qiang, WANG Luyang, YIN Baoqun, PENG Sifan, XING Sisi

Department of Automation, University of Science and Technology of China, Hefei 230027, China

Received:2019-01-28 Revised:2019-03-05 Published:2019-03-14

摘要/Abstract

摘要： 为解决单幅图像中的人群遮挡和尺度变化问题，提出一种基于多列卷积神经网络的人群计数算法。利用具有不同尺寸感受野的卷积神经网络（CNN）和特征注意力模块自适应提取多尺度人群特征，引入可变形卷积增强CNN网络空间几何形变学习能力并优化特征图，从而生成高质量的密度图。Shanghai Tech和UCF_CC_50数据集上的实验结果表明，该算法能学习输入图和人群密度图之间的映射关系，且计数准确性高、鲁棒性强。

关键词: 人群计数, 卷积神经网络, 可变形卷积, 特征图, 密度图

Abstract: In order to solve the problem of crowd occlusion and scale change in a single image,this paper proposes a crowd counting algorithm based on multi-column convolution neural network.The algorithm uses Convolutional Neural Network(CNN) with receptive fields of different sizes and the feature attention module to adaptively extract multi-scale crowd features.The deformable convolution is introduced to enhance the learning ability of spatial geometric deformation of the network and optimize the feature map,so as to generate a high quality density map.Experimental results on the Shanghai Tech and UCF_CC_50 datasets show that the algorithm can learn the mapping relationship between input images and crowd density maps,and has high counting accuracy and robustness.

Key words: crowd counting, Convolutional Neural Network(CNN), deformable convolution, feature map, density map

中图分类号:

TP18

翟强, 王陆洋, 殷保群, 彭思凡, 邢思思. 基于尺度自适应卷积神经网络的人群计数算法[J]. 计算机工程, 2020, 46(2): 250-254,261.

ZHAI Qiang, WANG Luyang, YIN Baoqun, PENG Sifan, XING Sisi. Crowd Counting Algorithm Based on Scale Adaptive Convolutional Neural Network[J]. Computer Engineering, 2020, 46(2): 250-254,261.

http://www.ecice06.com/CN/Y2020/V46/I2/250

图/表 6

20200218143750

20200218143754

20200218143757

20200218143800

20200218143803

20200218143805

参考文献

[1] CAO Lu,CHEN Ming,QIN Yufang.Pedestrian detection algorithm based on multi-channel and sparse convolution neural network[J].Transducer and Microsystem Technologies,2018,37(10):130-132,136.(in Chinese) 曹璐,陈明,秦玉芳.基于多通道稀疏卷积神经网络的行人检测算法[J].传感器与微系统,2018,37(10):130-132,136.
[2] Pucuo Cairen,HONG Jianchao.Research on remote sensing image detection based on deep convolution neural network and significant image[J].Automation and Instrumentation,2018(12):50-53,57.(in Chinese) 普措才仁,洪建超.基于深度卷积神经检测网络与显著性图像的遥感图像检测研究[J].自动化与仪器仪表,2018(12):50-53,57.
[3] TANG Siqi,TAO Wei,ZHANG Liangliang,et al.Research and implementation of crowd counting based on convolutional neural network[J].Journal of Zhengzhou University (Natural of Science Edition),2018,50(2):1-6.(in Chinese) 唐斯琪,陶蔚,张梁梁,等.一种多列特征图融合的深度人群计数算法[J].郑州大学学报(理学版),2018,50(2):1-6.
[4] ZHANG Cong,LI Hongsheng,WANG Xiaogang,et al.Cross-scene crowd counting via deep convolutional neural networks[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2015:833-841.
[5] SHANG Chong,AI Haizhou,BAI Bo.End-to-end crowd counting via joint learning local and global count[C]//Proceedings of IEEE Conference on Image Processing.Washington D.C.,USA:IEEE Press,2016:1215-1219.
[6] SAM D B,SURYA S,BABU R V.Switching convolutional neural network for crowd counting[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recogni-tion.Washington D.C.,USA:IEEE Press,2017:1-5.
[7] ZHANG Y,ZHOU D,CHEN S,et al.Single-image crowd counting via multi-column convolutional neural network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2016:589-597.
[8] SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[EB/OL].[2019-01-15]. https://www.cnblogs.com/yinheyi/p/62339 50.html
[9] DAI Jifeng,QI Haozhi,XIONG Yuwen,et al.Deformable convolutional networks[C]//Proceedings of 2017 IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:3.
[10] CAO Xinkun,WANG Zhipeng,ZHAO Yanyun,et al.Scale aggrega-tion network for accurate and efficient crowd counting[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2018:757-773.
[11] SINDAGI V A,PATEL V M.Generating high-quality crowd density maps using contextual pyramid CNNs[C]//Proceed-ings of IEEE International Conference on Computer Vision.Washington D.C.,USA:IEEE Press,2017:1861-1870.
[12] SHEN Z,XU Y,NI B,et al.Crowd counting via adversarial cross-scale consistency pursuit[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:5245-5254.
[13] LI Yuhong,ZHANG Xiaofan,CHEN Deming.CSRNet:dilated convolutional neural networks for understanding the highly congested scenes[C]//Proceedings of Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:1-6.
[14] BABU S D,SAJJAN N N,VENKATESH B R,et al.Divide and grow:capturing huge diversity in crowd images with incrementally growing CNN[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2018:3618-3626.
[15] IDREES H,SALEEMI I,SEIBERT C,et al.Multi-source multi-scale counting in extremely dense crowd images[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2013:2547-2554.
[16] SAM D B,BABU R V.Top-down feedback for crowd counting convolutional neural network[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence.Palo Alto,USA:AAAI Press,2018:1-8.
[17] RANJAN V,LE H,HOAI M.Iterative crowd counting[C]//Proceedings of European Conference on Computer Vision.Berlin,Germany:Springer,2018:278-293.

选择文件类型/文献管理软件名称

选择包含的内容

基于尺度自适应卷积神经网络的人群计数算法

Crowd Counting Algorithm Based on Scale Adaptive Convolutional Neural Network

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	曹坪, 杨怀志, 薄一军, 尤嘉, 张淳杰, 李丹勇. 面向低质量裂缝图像的多知识蒸馏分类[J]. 计算机工程, 2023, 49(7): 204-213.
[2]	白明昌. 基于折叠路径聚合的属性网络节点嵌入方法[J]. 计算机工程, 2023, 49(7): 76-84.
[3]	代祖华, 刘园园, 狄世龙. 语义增强的图神经网络方面级文本情感分析[J]. 计算机工程, 2023, 49(6): 71-80.
[4]	沈学利, 田桂源, 姜彦吉, 马琳琳. 基于双阶段Conv-Transformer的时频域语音增强算法[J]. 计算机工程, 2023, 49(6): 123-130.
[5]	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.
[6]	陈治旭, 靳雁霞, 芦烨, 杨晶, 刘亚变, 史志儒. 基于子图卷积神经网络的多精度服装建模方法[J]. 计算机工程, 2023, 49(4): 174-181.
[7]	徐康, 李霏, 姬东鸿. 结合依存图卷积与文本片段搜索的方面情感三元组抽取[J]. 计算机工程, 2023, 49(4): 61-67.
[8]	衡红军, 苗菁. 语义与句法信息加强的二元标记实体关系联合抽取[J]. 计算机工程, 2023, 49(4): 77-84.
[9]	钟宝荣, 吴夏灵. 基于高分辨率网络的轻量型人体姿态估计研究[J]. 计算机工程, 2023, 49(4): 226-232,239.
[10]	杨晶晶, 谢海燕, 薛妮妮, 张傲明. 基于双通道残差网络的水下图像去噪研究[J]. 计算机工程, 2023, 49(4): 188-198.
[11]	刘晶晶, 黄浩. 引入非局部模块卷积神经网络的基频提取模型[J]. 计算机工程, 2023, 49(3): 128-133,160.
[12]	邹长龙, 安敬民, 李冠宇. 基于邻域聚合与CNN的知识图谱实体类型补全[J]. 计算机工程, 2023, 49(3): 134-141.
[13]	翟社平, 张宇航, 柏晓夏. 融合实体邻域信息的知识图谱嵌入负采样方法[J]. 计算机工程, 2023, 49(3): 95-104.
[14]	程小辉, 李钰, 康燕萍. 基于中间图特征提取的卷积网络双标准剪枝[J]. 计算机工程, 2023, 49(3): 105-112.
[15]	陈柏霖, 王天极, 任丽娜, 黄瑞章. 融合ELECTRA和文本局部信息的中文语法错误检测方法[J]. 计算机工程, 2023, 49(3): 304-311.

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

基于尺度自适应卷积神经网络的人群计数算法

Crowd Counting Algorithm Based on Scale Adaptive Convolutional Neural Network

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献

相关文章 15

编辑推荐

Metrics

本文评价