[1]贾翻连,张丽红.基于改进的卷积神经网络的人群密度估计[J].计算机技术与发展,2019,29(02):77-80.[doi:10．3969/j．issn．1673－629X．2019．02．016]
　JIA Fanlian,ZHANG Lihong.Crowd Density Estimation Based on an Improved Convolution Neural Network[J].,2019,29(02):77-80.[doi:10．3969/j．issn．1673－629X．2019．02．016]
点击复制

基于改进的卷积神经网络的人群密度估计()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年02期
页码:
77-80
栏目:
智能、算法、系统工程
出版日期:
2019-02-10

文章信息/Info

Title:
Crowd Density Estimation Based on an Improved Convolution Neural Network
文章编号:
1673－629X(2019)02－0077－04
作者:
贾翻连; 张丽红
山西大学 物理电子工程学院，山西 太原 030006
Author(s):
JIA Fan－lian; ZHANG Li－hong
School of Physics and Electronic Engineering，Shanxi University，Taiyuan 030006，China
关键词:
人群密度; 深度学习; 小波变换; 神经网络; 权重自适应; 特征提取
Keywords:
population density; deep learning; wavelet transform; neural network; adaptive weight; feature extraction
分类号:
TP183
DOI:
10．3969/j．issn．1673－629X．2019．02．016
摘要:
人群密度估计是视频监控的一个研究热点，为了得到更为准确的估计率，将卷积神经网络应用到人群密度估计中。卷积神经网络在特征提取时能够高效自适应学习深层次的特征，体现了其在深度学习领域的优越性，但在预处理时会出现振荡现象，且卷积层与子采样层间特征图的大小匹配会影响计算速度和时间。对此，提出离散小波变换替换卷积神经网络中的子采样层，并对网络中的权重矩阵进行重新计算，通过权重自适应改善预处理时的振荡现象，提高卷积网络中特征图大小的匹配度，并将之应用到人群密度估计，以有效地提高数据间的相关性，增强网络的学习能力，提高人群密度等级分类的准确率。实验结果表明，改进后的网络具有较好的学习及分类效果和鲁棒性，对人群密度能够进行较为准确和快速的估计。
Abstract:
Crowd density estimation is a research hotspot in video surveillance． In order to get more accurate estimation rate，the convolutional neural network is applied in crowd density estimation． Convolutional neural network can efficiently and adaptively learn deep char-acteristics in feature extraction，which demonstrates its superiority in the field of depth learning． However，oscillation will occur in the preprocessing，and the size matching of feature map between convolutional layer and sub－sampling layer will affect the calculation speed andtime． For this，we adopt discrete wavelet transform to replace the sub－sampling layer in convolutional neural network and recalculate theweight matrix in the network． The phenomenon of oscillation is improved in the preprocessing by adaptive weight，and the matching de-gree of feature map size in convolutional network is enhanced，which is applied in the crowd density estimation，effectively improving thedata correlation and enhancing the learning ability of the network，and also increasing the accuracy of classification of crowd density level． The experiment shows that the improved network has better learning and classification effect and robustness，which can be used to estimate the population density more accurately and quickly．

相似文献/References:

[1]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(02):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[2]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(02):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[3]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(02):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(02):19.
[5]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(02):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[6]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(02):1.
[7]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(02):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[8]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(02):1.
[9]李全兵,文 钊*,田艳梅*,等.基于 WGAN 的音频关键词识别研究[J].计算机技术与发展,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
　LI Quan-bing,WEN Zhao *,TIAN Yan-mei *,et al.Research on Audio Keywords Recognition Based on WassersteinGenerative Adversarial Network[J].,2021,31(02):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
[10]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(02):7.

更新日期/Last Update: 2019-02-10