结合特征图谱学习的人数统计方法

doi:10.11772/j.issn.1001-9081.2018051162

计算机应用 ›› 2018, Vol. 38 ›› Issue (12): 3591-3595.DOI: 10.11772/j.issn.1001-9081.2018051162

• 虚拟现实与多媒体计算 • 上一篇下一篇

结合特征图谱学习的人数统计方法

易国宪¹, 熊淑华¹, 何小海¹, 吴晓红¹, 郑新波²

1. 四川大学电子信息学院, 成都 610065;
2. 东莞前沿技术研究院, 广东东莞 523000

收稿日期:2018-06-08 修回日期:2018-07-04 出版日期:2018-12-10 发布日期:2018-12-15
通讯作者: 熊淑华
作者简介:易国宪(1994-),男,湖北孝感人,硕士研究生,主要研究方向:数字图像处理、智能监控;熊淑华(1969-),女,四川成都人,副教授,博士,主要研究方向:多媒体通信;何小海(1964-),男,四川成都人,教授,博士,主要研究方向:数字图像处理;吴晓红(1970-),女,四川成都人,副教授,博士,主要研究方向:图像处理、模式识别;郑新波(1984-),男,河南辉县人,高级工程师,博士,主要研究方向:数字图像处理。
基金资助:
国家自然科学基金资助项目（11176018）；成都市产业集群协同创新项目（2016-XT00-00015-GX）；东莞市社会科技发展项目（2017507102428）。

People counting method combined with feature map learning

YI Guoxian¹, XIONG Shuhua¹, HE Xiaohai¹, WU Xiaohong¹, ZHENG Xinbo²

1. College of Electronics and Information Engineering, Sichuan University, Chengdu Sichuan 610065, China;
2. Dongguan Institute of Advanced Technology, Guangdong Dongguan 523000, China

Received:2018-06-08 Revised:2018-07-04 Online:2018-12-10 Published:2018-12-15
Contact: 熊淑华
Supported by:
This work is partially supported by the National Natural Science Foundation of China (11176018), the Chengdu Industrial Cluster Collaborative Innovation Program (2016-XT00-00015-GX), the Dongguan Social Science and Technology Development Program (2017507102428).

摘要/Abstract

摘要： 针对实际公共场景视频的人数统计中存在的背景干扰、光照变化、目标间遮挡等问题，提出一种结合特征图谱学习和一阶动态线性回归的人数统计方法。首先，建立图像的尺度不变特征变换（SIFT）特征与目标真实密度图之间的特征图谱映射模型，利用SIFT特征和前述映射模型得到包含目标和背景特征量的特征图谱；然后，根据通常监控视频中背景变化较小、特征图谱中的背景特征量相对稳定的特点，由特征图谱的积分与真实人数通过一阶动态线性回归建立人数回归模型；最后，通过该回归模型模型得出估计人数。在数据集MALL和PETS2009上进行实验，实验结果表明：与累积属性空间方法相比，所提方法平均绝对误差降低了2.2%；与基于角点检测的一阶动态线性回归方法相比，其平均绝对误差降低了6.5%，平均相对误差降低了2.3%。

关键词: 纹理, 密度图, 特征图谱, 岭回归, 动态线性回归, 人数统计

Abstract: In order to solve the problems such as background interference, illumination variation and occlusion between targets in people counting of actual public scene videos, a new people counting method combined with feature map learning and first-order dynamic linear regression was proposed. Firstly, the mapping model of feature map between the Scale-Invariant Feature Transform (SIFT) feature of image and the target true density map was established, and the feature map containing target and background features was obtained by using aforementioned mapping model and SIFT feature. Then, according to the facts of the less background changes in the monitoring video and the relatively stable background features in the feature map, the regression model of people counting was established by the first-order dynamic linear regression from the integration of feature map and the actual number of people. Finally, the estimated number of people was obtained through the regression model. The experiments were performed on the datasets of MALL and PETS2009. The experimental results show that, compared with the cumulative attribute space method, the mean absolute error of the proposed method is reduced by 2.2%, while compared with the first-order dynamic linear regression method based on corner detection, the mean absolute error and the mean relative error of the proposed method are respectively reduced by 6.5% and 2.3%.

Key words: texture, density map, feature map, ridge regression, dynamic linear regression, people counting

中图分类号:

TP391.41

易国宪, 熊淑华, 何小海, 吴晓红, 郑新波. 结合特征图谱学习的人数统计方法[J]. 计算机应用, 2018, 38(12): 3591-3595.

YI Guoxian, XIONG Shuhua, HE Xiaohai, WU Xiaohong, ZHENG Xinbo. People counting method combined with feature map learning[J]. Journal of Computer Applications, 2018, 38(12): 3591-3595.

参考文献

[1] 新华网.上海外滩踩踏事件[EB/OL].[2018-03-26]. http://www.xinhuanet.com/politics/szjcxzt/shwtctsg/. (Xinhuanet. Shanghai bund stampede[EB/OL].[2018-03-26]. http://www.xinhuanet.com/politics/szjcxzt/shwtctsg/.)
[2] 张君军,石志广,李吉成.人数统计与人群密度估计技术研究现状与趋势[J].计算机工程与科学,2018,40(2):282-291.(ZHANG J J, SHI Z G, LI J C. Current researches and future perspectives of crowd counting and crowd density estimation technology[J]. Computer Engineering and Science, 2018, 40(2):282-291.)
[3] GE W N, COLLINS R T. Marked point processes for crowd counting[C]//Proceedings of the 2009 IEEE Conference on Computer Vision and Pattern Recognition. Washington, DC:IEEE Computer Society, 2009:2913-2920.
[4] BROSTOW G J, CIPOLLA R. Unsupervised Bayesian detection of independent motion in crowds[C]//Proceedings of the 2006 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2006:594-601.
[5] RABAUD V, BELONGIE S. Counting crowded moving objects[C]//Proceedings of the 2006 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2006:705-711.
[6] 韩迎辉,伏林.基于鱼眼视频图像的人群人数估计算法的研究[J].电子器件,2014,37(6):1111-1115.(HAN Y H, FU L. Research on estimation algorithm of crowd counting based on fisheye video image[J]. Chinese Journal of Electron Devices, 2014, 37(6):1111-1115.)
[7] ALBIOL A, SILLA M J, ALBIOL A, et al. Video analysis using corner motion statistics[C]//Proceedings of the 2009 IEEE International Workshop on Performance Evaluation of Trackingand Surveillance. Piscataway, NJ:IEEE, 2009:31-38.
[8] 曹志通,李晓华,周激流.改进的基于角点检测的视频人数统计方法[J].计算机应用,2017,37(S1):141-143,164.(CAO Z T, LI X H, ZHOU J L. Improved method for people counting in video sequences based on corner detection[J]. Journal of Computer Applications, 2017, 37(S1):141-143, 164.)
[9] LEMPITSKY V S, ZISSERMAN A. Learning to count objects in images[C]//Proceedings of the 2010 International Conference on Neural Information Processing Systems. North Miami Beach, FL:Curran Associates Inc. 2010:1324-1332.
[10] ARTETA C, LEMPITSKY V, NOBLE J A, et al. Interactive object counting[C]//Proceedings of the 2014 European Conference on Computer Vision. Berlin:Springer, 2014:504-518.
[11] ZHANG Y Y, ZHOU D S, CHEN S Q, et al. Single-image crowd counting via multi-column convolutional neural network[C]//Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2016:589-597.
[12] SAM D B, SURYA S, BABU R V. Switching convolutional neural network for crowd counting[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2017:4031-4039.
[13] LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International Journal of Computer Vision, 2004, 60(2):91-110.
[14] CHEN K, GONG S G, XIANG T, et al. Cumulative attribute space for age and crowd density estimation[C]//Proceedings of the 2013 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2013:2467-2474.
[15] LOY C C, GONG S G, XIANG T. From semi-supervised to transfer counting of crowds[C]//Proceedings of the 2013 IEEE International Conference on Computer Vision. Piscataway, NJ:IEEE, 2013:2256-2263.
[16] LOY C C, CHEN K, GONG S G, et al. Crowd counting and profiling:methodology and evaluation[M]//ALI S, NISHINO K, MANOCHA D, et al. Modeling, Simulation and Visual Analysis of Crowds. Berlin:Springer, 2013:347-382.
[17] CHEN K, LOY C C, GONG S G, et al. Feature mining for localised crowd counting[C]//Proceedings of the 2012 British Machine Vision Conference. Durham, UK:BMVA, 2012:1-11.
[18] University of Reading. PETS 2009 benchmark data[EB/OL].[2018-03-26]. http://www.cvg.reading.ac.uk/PETS2009/data.html.

结合特征图谱学习的人数统计方法

People counting method combined with feature map learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李辉, 吴传生, 刘俊, 刘文. 基于梯度曲面面积与稀疏约束的图像平滑方法[J]. 计算机应用, 2021, 41(7): 2039-2047.
[2]	蒋考林, 白玮, 张磊, 陈军, 潘志松, 郭世泽. 基于多通道图像深度学习的恶意代码检测[J]. 计算机应用, 2021, 41(4): 1142-1147.
[3]	刘望华, 刘光帅, 陈晓文, 李旭瑞. 结合微分特征和Haar小波分解的鲁棒纹理表达[J]. 计算机应用, 2020, 40(9): 2728-2736.
[4]	汪志远, 降爱莲, 奥斯曼·穆罕默德. 基于正则互表示的无监督特征选择方法[J]. 计算机应用, 2020, 40(7): 1896-1900.
[5]	张一飞, 李新福, 田学东. 基于图像分割的立体匹配算法[J]. 计算机应用, 2020, 40(5): 1415-1420.
[6]	喻光继, 罗伟泰, 吴肖云. 基于改进体素锥追踪的大规模场景光照计算[J]. 计算机应用, 2020, 40(5): 1421-1424.
[7]	张亚洲, 卢先领. 基于改进相干增强扩散与纹理能量测度和高斯混合模型的导光板表面缺陷检测方法[J]. 计算机应用, 2020, 40(5): 1545-1552.
[8]	冯浪, 张玲, 张晓龙. 基于扩张卷积的图像修复[J]. 计算机应用, 2020, 40(3): 825-831.
[9]	余英东, 杨怡, 林澜. 结合纹理特征分析的图像风格转换网络[J]. 计算机应用, 2020, 40(3): 638-644.
[10]	陈放, 刘晓瑞, 杨明业. 基于活体检测和身份认证的人脸识别安防系统[J]. 计算机应用, 2020, 40(12): 3666-3672.
[11]	张斌, 罗晓清, 张战成. 基于TV-L¹结构纹理分解的图像融合质量评价算法[J]. 计算机应用, 2019, 39(9): 2701-2706.
[12]	郎大鹏, 丁巍, 姜昊辰, 陈志远. 基于多特征融合的恶意代码分类算法[J]. 计算机应用, 2019, 39(8): 2333-2338.
[13]	李文俊, 陈斌, 李建明, 钱基德. 基于深度神经网络的表面划痕识别方法[J]. 计算机应用, 2019, 39(7): 2103-2108.
[14]	程露, 周波. 基于纹理分水岭的斜坡单元提取算法[J]. 计算机应用, 2019, 39(6): 1810-1815.
[15]	盛恒, 黄铭, 杨晶晶. 基于Faster R-CNN和IoU优化的实验室人数统计与管理系统[J]. 计算机应用, 2019, 39(6): 1669-1674.