计算机科学 ›› 2020, Vol. 47 ›› Issue (4): 184-188.doi: 10.11896/jsjkx.190700212

• 人工智能 • 上一篇    下一篇

基于深度神经网络的“弱监督”密集场景人群计数算法

刘砚, 雷印杰, 宁芊   

  1. 四川大学电子信息学院 成都610065
  • 收稿日期:2019-07-31 出版日期:2020-04-15 发布日期:2020-04-15
  • 通讯作者: 宁芊(ningq@scu.edu.cn)
  • 基金资助:
    四川省重点研发项目(2019YFG0409)

Study of Crowd Counting Algorithm of “Weak Supervision” Dense Scene Based on DeepNeural Network

LIU Yan, LEI Yin-jie, NING Qian   

  1. College of Electronics and Information Engineering,Sichuan University,Chengdu 610065,China
  • Received:2019-07-31 Online:2020-04-15 Published:2020-04-15
  • Contact: NING Qian,born in 1969,associate professor.Her main research interests include computer application and intelligent control.
  • About author:LIU Yan,born in 1995,postgraduate.His main research interests include deep learning and crowd counting.
  • Supported by:
    This work was supported by the Key Research and Development Program of Sichuan Province (2019YFG0409)

摘要: 目前,在密集场景人群计数任务中,标注真实密度图的方法是对行人头部的中心位置进行标注,并利用高斯卷积生成真实的密度分布图作为监督信息。但是,对于密集场景而言,这样的标注方式是费时、费力的,并且密集场景图片中有诸多“非受控”因素,如低分辨率、背景噪声、目标遮挡和尺度变化等。针对这一问题,提出了一种新的标注方法,即只需要知道图片中包含多少个物体,以图片中行人的数量作为监督信息。与传统的真实密度图相比,所提出的标记方法中以真实目标的数值为“弱监督”信息。实验结果表明,对于人群回归任务,利用弱监督信息对神经网络进行训练得到的模型能够较为准确地回归出图片中所包含目标的数量,从而证明了该方法的有效性。

关键词: 人群计数, 弱监督, 深度学习, 神经网络

Abstract: At present,in the crowd counting task of dense scenes,the method of annotating true density is to annotate the central position of pedestrian’s head.Gaussian convolution is used to generate the ground-truth density map as the supervision information.However,for dense scenes,such labeling method is time-consuming and laborious,and there are many “uncontrolled” factors in the images of dense scenes,such as low resolution,background noise,heavy occlusion and scale change.To solve this problem,we proposed a new annotation method,that is,we only need to know how many persons are included in the picture,and the total count of pedestrians in the picture is used as the supervision information.Compared with the traditional real density map,in proposed labeling method,the real target value is used as the “weak supervision” information.The experimental results show that the model obtained by training neural network with weak supervisory information can accurately regress the number of targets in the image for crowd regression task,indicating the effectiveness of this method.

Key words: Crowd counting, Deep learning, Neural network, Weak supervision

中图分类号: 

  • TP391.413
[1]DALAL N,TRIGGS B.Histograms of Oriented Gradients for Human Detection[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.San Diego:IEEE Press,2005:886-893.
[2]VIOLA P,JONES M J.Robust Real-Time Face Detection[J] International Journal of Computer Vision,2004,57(2):137-154.
[3]FIASCHI L,KÖTHE U,NAIR R,et al.Learning to Count with Regression Forest and Sturctured Labels[C]// Proceedings of International Conference on Pattern Recognition.Tsukuba:IEEE Press,2012:2685-2688.
[4]CHAN A B,VASCONCELOS N.Bayesian Poisson Regressionfor Crowd Countin[C]//Proceedings of IEEE International Conference on Computer Vision.Tokyo:IEEE Press,2009.
[5]ZHANG Y,ZHOU D,et al.Single-image Crowd Counting via Multi-column Convolutional Neural Network[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.LAS VEGAS:IEEE Press,2016:589-597.
[6]SAM D B,SURYA S,BABU R V,et al.Switching Convolutional Neural Network for Crowd Counting[C]//Proceedigs of IEEE Conference on Computer Vision and Pattern Recognitio.Honolulu:IEEE Press,2017:5744-5752.
[7]SINDAGI V A,PATEL V M.Generating High-Quality Crowd Density Maps Using Contextual Pyramid Cnns[C]//Procee-dings of IEEE InternationalConferenceon Computer Vision.Ve-nice:IEEE Press,2017:1861-1870.
[8]LI Y,ZHANG X,CHEN D.Csrnet:Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes[C]// Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake:IEEE Press,2018:1091-1100.
[9]SIMONYAN K,ZISSERMAN A.Very deep convolutional networks for large-scale image recognition[C]// Proceedings of International Conference on Learning Representations.San Diego:IEEE Press,2015.
[10]LIU X,VAN DE WEIJER J,et al.Leveraging Unlabeled Data for Crowd Counting by Learning to rank[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Salt Lake:IEEE Press,2018:7661-7669.
[11]WANG Q,GAO J,et al.Learning from Synthetic Data forCrowd Counting in The Wild[C]//Proceedings of IEEE Confe-rence on Computer Vision and Pattern Recognition Long.Beach:IEEE Press,2019.
[12]GOODFELLOW I,POUGET-ABADIE J,et al.Generative Adversarial Nets[C]//Proceedings of International Conference on Neural Information Processing Systems Lake.Tahoe:MIT Press,2014.
[13]SAM D B,SAJJAN N N,et al.Almost Unsupervised Learning for Dense Crowd Counting[C]//Proceedings of American Conference on Artificial Intelligence.Honolulu:AAAI Press,2019.
[14]KRIZHEVSKY A,SUTSKEVER I,et al.Imagenet Classification With Deep Convolutional Neural Networks[C]// Procee-dings of International Conference on Neural Information Proces-sing Systems.Montrea:MIT Press,2012:1097-1105.
[1] 周芳泉, 成卫青.
基于全局增强图神经网络的序列推荐
Sequence Recommendation Based on Global Enhanced Graph Neural Network
计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085
[2] 周乐员, 张剑华, 袁甜甜, 陈胜勇.
多层注意力机制融合的序列到序列中国连续手语识别和翻译
Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion
计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[3] 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺.
时序知识图谱表示学习
Temporal Knowledge Graph Representation Learning
计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[4] 饶志双, 贾真, 张凡, 李天瑞.
基于Key-Value关联记忆网络的知识图谱问答方法
Key-Value Relational Memory Networks for Question Answering over Knowledge Graph
计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277
[5] 宁晗阳, 马苗, 杨波, 刘士昌.
密码学智能化研究进展与分析
Research Progress and Analysis on Intelligent Cryptology
计算机科学, 2022, 49(9): 288-296. https://doi.org/10.11896/jsjkx.220300053
[6] 汤凌韬, 王迪, 张鲁飞, 刘盛云.
基于安全多方计算和差分隐私的联邦学习方案
Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy
计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108
[7] 李宗民, 张玉鹏, 刘玉杰, 李华.
基于可变形图卷积的点云表征学习
Deformable Graph Convolutional Networks Based Point Cloud Representation Learning
计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[8] 王剑, 彭雨琦, 赵宇斐, 杨健.
基于深度学习的社交网络舆情信息抽取方法综述
Survey of Social Network Public Opinion Information Extraction Based on Deep Learning
计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099
[9] 郝志荣, 陈龙, 黄嘉成.
面向文本分类的类别区分式通用对抗攻击方法
Class Discriminative Universal Adversarial Attack for Text Classification
计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077
[10] 姜梦函, 李邵梅, 郑洪浩, 张建朋.
基于改进位置编码的谣言检测模型
Rumor Detection Model Based on Improved Position Embedding
计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046
[11] 王润安, 邹兆年.
基于物理操作级模型的查询执行时间预测方法
Query Performance Prediction Based on Physical Operation-level Models
计算机科学, 2022, 49(8): 49-55. https://doi.org/10.11896/jsjkx.210700074
[12] 陈泳全, 姜瑛.
基于卷积神经网络的APP用户行为分析方法
Analysis Method of APP User Behavior Based on Convolutional Neural Network
计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[13] 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥.
基于注意力机制的医学影像深度哈希检索算法
Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism
计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[14] 孙奇, 吉根林, 张杰.
基于非局部注意力生成对抗网络的视频异常事件检测方法
Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection
计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061
[15] 檀莹莹, 王俊丽, 张超波.
基于图卷积神经网络的文本分类方法研究综述
Review of Text Classification Methods Based on Graph Convolutional Network
计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!