Fusion attention Mechanic Crowd counting Network Based on Transformer
Pages 37 - 43
Abstract
For crowded scenes in dense occlusion conditions, it was difficult to count the crowd accurately. A Transformer-based fusion attention mechanism crowd counting network was proposed. First, in order to adapt more efficiently to small-scale changes, the network was based on the VGG19 network architecture, incorporate the attention mechanism ECANet, so as to better integrate channel interaction features. Then, the output feature mapping was transferred to the Transformer. Considering that the Transformer fails to feel localized information well and stable fusion, and added local attention module and streaming attention module. Finally, a regression attention mechanism header was designed to obtain finer density maps and predicted numbers of people. The effectiveness of the proposed method has been confirmed by extensive experiments on three challenging crowd counting datasets, namely UCF-QNRF, JHU++Crowd, and NWPU.
References
[1]
Li M,Zhang Z,Huang K,et al.Estimating the number opeople in crowded scenes by mid based foreground segmentation and head-shoulder detection[C]//2008 19th international conference on pattern recognition.IEEE,2008:1-4.
[2]
Zhou W, Liu C, Lei J,et al. RLLNet: a lightweight remaking learning network for saliency redetection on RGB-D images[J]. Sciences, 2022, 65(6):1-2.
[3]
Lin Z,Davis L S.Davis.Shape-based human detection and segmentation via hierarchical part-template matching[J].IEEE transactions on pattern analysis and machine intelligence,2010,32(4):604-618.
[4]
Chen K,Loy C C,Gong S,et al.Feature Mining for Localized Crowd Counting[C]//British Machine Vision Conferenc,2012:1-11.
[5]
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,2013:2547-2554.
[6]
Ren S,He K,Girshick R,et al.Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,39(6):1137-1149.
[7]
Chen L C,Zhu Y,Papandreou G,et al.Encoder-Decoderwith Atrous Separable Convolution for Semantic ImageSegmentation[C]//European Conference on Computer Vision,2018:833-851.
[8]
Zhang T,Xu C,Yang M H.Learning Multi-Task Correlation Particle Filters for Visual Tracking[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019,41(2):365-378.
[9]
Zhang Y,Zhou D,Chen S,et al.Single-image crowd counting via multi-column convolutional neural network[C]//Proceedings of the IEEE conference on computer vision and pattern recognition,2016:589-597.
[10]
Babu Sam D,Surya S,Venkatesh Babu R.Switching co nvolutional neural network for crowd counting[C]//Pro ceedings of the IEEE conference on computer vision and pattern recognition,2017:5744-5752.
[11]
Zhang A,Yue L,Shen J,et al.Attentional neural fields for crowd counting[C]//Proceedings of the IEEE inter national conference on computer vision,. 2019:5714-572 3.
[12]
Zhang A,Shen J,Xiao Z,et al.Relational attention netw ork for crowd counting[C]//Proceedings of the IEEE i nternational conference on computer vision,2019:6788- 6797.
[13]
Liang D,Chen X,Xu W,et al.TransCrowd:weakly-super vised crowd counting with transformers[J].Science Chi na Information Sciences,2022,65(6):1-14 .
[14]
Sun G,Liu Y,Probst T,et al.Boosting crowd counting with transformers[J].arXiv:2105.10926,2021.
[15]
Tian Y,Chu X,Wang H.Cctrans:Simplifying and impr oving crowd counting with transformer[J].arXiv:2109.1 4483,2021.
[16]
Wei X,Kang Y,Yang J,et al.Scene-adaptive attention network for crowd counting[J].arXiv:2112.15509,2021.
[17]
Wang F,Liu K,Long F,et al. Joint CNN and Transform er Network via weakly supervised Learning for effici ent crowd counting[J]. arXiv:2203.06388,2022.
[18]
Chen Y,Yang J,Chen B,et al.Counting Varying Densit y Crowds Through Density Guided Adaptive Selection CNN and Transformer Estimation[J].IEEE Transactions on Circuits and Systems for Video Technology,2022,3 3(3):1055-1068.
[19]
Wang Q,Wu B,Zhu P,et al.ECA-Net:Efficient Channel Attention for Deep Convolutional Neural Networks[C] //Proceedingsof the IEEE conference on computer vision and pattern recognition,2020:11531-11539.
[20]
Vaswani A,Shazeer N,Parmar N,et al.Attention Is All You Need[J].Proceedings of the International Conferen ce on Neural Information Processing Systems,2017,04 (10):6000-6010.
[21]
Lin H,Ma Z, Ji R,et al.Boosting Crowd Counting via Multifaceted Attention[C]//Proceedingsof the IEEE con ference on computer vision and pattern recognition,20 22:19596-19605.
[22]
Wu H,Wu J,Xu J,et al. Flowformer:Linearizing Transfo rmers with Conservation Flows[C]//International Confe r ence on Machine Learning,2022.
[23]
Liu W,Salzmann M,Fua P.Context-Aware Crowd Coun ting[C]// Proceedings of the IEEE conference on com puter vision and pattern recognition, 2019:5099- 5108.
[24]
Ma Z,Wei X,Hong X,et al.Bayesian Loss for Crowd Count Estimation WithPoint Supervision[C]//Proceedin gs of International Conference on Computer Vision,20 20:6141-6150.
[25]
Liu X,Yang J,Ding W.Adaptive Mixture Regression N etwork with Local Counting Map for Crowd Countin g[C]// European Conference on Computer Vision, 2020. 2 41-257.
[26]
Wang B,Liu H,Samaras D,et al.Distribution Matching for Crowd Counting[J].Advances in Neural Informati on Processing Systems,2020,33(1):1595-1607 .
[27]
Song Q, Wang C, Jiang Z,et al. Rethinking Counti ng and Localization in Crowds:A Purely Point-Based Framework[C]//Proceedings of International Conferen ce on Computer Vision,2021:3345-3354.
[28]
Wan J,Liu Z,Chan A B.A Generalized Loss Function for Crowd Counting and Localization[C]//Proceedings of the IEEE conference on computer vision and pattern recognition,2021:1974-1983.
[29]
Ma Z,Wei X,Hong X,et al.Learning to count via unb alanced optimal transport[C]//Proceedings of the AAA I Conference on Artificial Intelligence.2021. 2319-2327.
[30]
Wang Q,Gao J,Lin W,et al.Learning from Synthetic Data for Crowd Counting in the Wild[C]//Proceedings of the IEEE conference on computer vision and patte rn recognition,2019:8198-8207.
[31]
Wan J,Wang Q,Chan A B.Kernel-based density map generation for dense object counting[J].IEEE Trans ac ti ons on Pattern Analysis and Machine Intelligence, 2022,44(3):1357-1370.
[32]
Idrees H, Tayyab M, Athrey K,et al. Composition Loss for Counting, Density Map Estimation and Loca lization in Dense Crowds[C]//European Conference on Computer Vision,2018:544-559.
[33]
Sindagi V A, Yasarla R, Patel V M.JHU-CROWD++:Large-Scale Crowd Counting Dataset and A BenchmarkMethod[J].IEEE Transactions on Pattern Analysisand Machine Intelligence,2020. 44(5): 2594-2609.
[34]
Wang Q, Gao J, Lin W, NWPU-crowd: a large-scale benchmarkfor crowd counting and localization[J].IEEE transactions on pattern analysis and machine intelligence, 2020, 43(6): 2141-2149.
[35]
Dosovitskiy A, Beyer L, Kolesnikov A,et al. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale[J]. arXiv:2010.11929,2020.
Index Terms
- Fusion attention Mechanic Crowd counting Network Based on Transformer
Index terms have been assigned to the content through auto-classification.
Recommendations
Crowd counting with crowd attention convolutional neural network
AbstractCrowd counting is a challenging problem due to the scene complexity and scale variation. Although deep learning has achieved great improvement in crowd counting, scene complexity affects the judgement of these methods and they usually ...
Crowd counting via Localization Guided Transformer
AbstractThe rapidly growing demands on real-world crowd security and commercial applications have drawn widespread attentions to crowd counting, a computer vision task that aims to count all persons that appear in a given image. Recent state-...
Graphical abstractDisplay Omitted
Highlights- We propose a Localization Guided Transformer (LGT) framework.
- We devise a ...
Context Attention Fusion Network for crowd counting
AbstractContext information, which plays a crucial role in many computer vision tasks, can benefit deep networks to construct better cognitive competence from more comprehensive surrounding. However, most existing crowd counting methods often ...
Highlights- Propose a context attention fusion network for crowd counting.
- Explore local ...
Comments
Information & Contributors
Information
Published In
January 2024
297 pages
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 08 March 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
- Chongqing Natural Science Foundation Project
- Chongqing Education Commission Science and Technology Research Project
Conference
CCEAI 2024
CCEAI 2024: 2024 8th International Conference on Control Engineering and Artificial Intelligence
January 26 - 28, 2024
Shanghai, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 10Total Downloads
- Downloads (Last 12 months)10
- Downloads (Last 6 weeks)0
Reflects downloads up to 06 Aug 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format