7 minute read

1 综述

  1. A Survey of Human-Sensing: Methods for Detecting Presence, Count, Location, Track, and Identity
    CSUR 2010 2010 paper

  2. Fast crowd density estimation with convolutional neural networks
    AI 2015 2015 paper

  3. Crowded Scene Analysis:A Survey
    IEEE Transactions on Circuits and Systems for Video Technology 2015 2015-02-06 paper

  4. An Evaluation of Crowd Counting Methods, Features and Regression Models
    CVIU 2015 2015 paper

  5. Advances and Trends in Visual Crowd Analysis: A Systematic Survey and Evaluation of Crowd Modelling Techniques
    Neurocomputing 2016 2016 paper

  6. A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation
    PR Letters 2018 2017-07-05 paper

  7. Beyond Counting:Comparisons of Density Maps for Crowd Analysis Tasks
    T-CSVT2018 2017-05-29 paper

2 理论

3 通用

  1. Crowd Counting Via Scale-adaptive Convolutional Neural Network
    WACV 2018 2017-11-13 paper | caffe
    SaCNN

  2. Revisiting Perspective Information for Efficient Crowd Counting
    CVPR 2019 2018-07-05 paper
    PACNN

  3. Context-Aware Crowd Counting
    CVPR 2019 2018-11-26 paper | pytorch
    CAN

  4. ADCrowdNet: An Attention-injective Deformable Convolutional Network for Crowd Understanding
    CVPR 2019 2018-11-29 paper
    ADCrowdNet

  5. Adaptive Scenario Discovery for Crowd Counting
    ICASSP 2019 2018-12-06 paper
    ASD

  6. Almost Unsupervised Learning for Dense Crowd Counting
    AAAI 2019 2019 云从 paper | blog
    GWTA-CCNN

  7. Scale Pyramid Network for Crowd Counting
    WACV 2019 2019-01-17 paper
    SPN

  8. Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank
    T-PAMI 2019 2019-02-17 paper
    SL2R

  9. Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks
    CVPR 2019 2019-03-03 paper
    TEDnet

  10. Crowd Counting Using Scale-Aware Attention Networks
    WACV 2019 2019-03-05 paper
    SAAN

  11. Crowd Counting via Multi-View Scale Aggregation Networks
    ICME 2019 2019

  12. Dynamic Region Division for Adaptive Learning Pedestrian Counting
    ICME 2019 2019

  13. Locality-Constrained Spatial Transformer Network for Video Crowd Counting
    ICME 2019 2019

  14. Learning from Synthetic Data for Crowd Counting in the Wild
    CVPR 2019 2019-03-08 paper | project | pytorch | dataset| 标注工具
    CCWld
    开源了一个数据集 GCC;

  15. CODA: Counting Objects via Scale-aware Adversarial Density Adaption
    ICME 2019 2019-03-25 paper | code-offical-coming
    CODA

  16. Counting with Focus for Free
    2019-03-28 paper

  17. Cross-Line Pedestrian Counting Based on Spatially-Consistent Two-Stage Local Crowd Density Estimation and Accumulation
    IEEE T-CSVT 2019 2019 paper

  18. Point in, Box out: Beyond Counting Persons in Crowds
    CVPR 2019 2019-04-02 paper
    PSDDN

  19. PCC Net: Perspective Crowd Counting via Spatial Convolutional Network
    IEEE T-CSVT 2019 2019-05-24 paper | pytorch-offical
    PCC-Net
    $\bullet \bullet$

  20. Leveraging Heterogeneous Auxiliary Tasks to Assist Crowd Counting
    CVPR 2019 2019 paper
    AT-CFCN

  21. Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs
    CVPR 2019 2019 paper
    MVMS

  22. Residual Regression with Semantic Prior for Crowd Counting
    CVPR 2019 2019 paper
    RRSP

  23. Density Map Regression Guided Detection Network for RGB-D Crowd Counting and Localization
    CVPR 2019 2019 paper
    RDNet

  24. Recurrent Attentive Zooming for Joint Crowd Counting and Precise Localization
    CVPR 2019 2019 paper
    RAZ-Net

  25. Content-aware Density Map for Crowd Counting and Density Estimation
    2019-06-17 paper

  26. Locate, Size and Count: Accurately Resolving People in Dense Crowds via Detection
    2019-06-18 paper | pytorch-offical

  27. Dense Scale Network for Crowd Counting
    2019-06-24 paper

  28. Inverse Attention Guided Deep Crowd Counting Network
    AVSS 2019 2019-07-02 paper
    IA-DNN

  29. C^3 Framework: An Open-source PyTorch Code for Crowd Counting
    2019-07-05 paper | pytorch-offical | blog-offical

4 基于视频

  1. Video Crowd Counting via Dynamic Temporal Modeling
    2019-07-04 paper

TOP

附录

A 参考资料

  1. gjy3035. Awesome Crowd Counting. https://github.com/gjy3035/Awesome-Crowd-Counting. /2019-07-16.
  2. paper with code. Crowd Counting. https://paperswithcode.com/task/crowd-counting/codeless. -/2019-07-16.
  3. 人群计数(Crowd Counting)研究综述

B 性能比对

ShanghaiTech Part A

Year-Conference/Journal Methods MAE MSE PSNR SSIM Params Pre-trained Model
2016–CVPR MCNN 110.2 173.2 21.4CSR 0.52CSR 0.13MSANet None
2017–AVSS CMTL 101.3 152.4 - - - None
2017–CVPR Switching CNN 90.4 135.0 - - 15.11MSANet VGG-16
2017–ICIP MSCNN 83.8 127.4 - - - -
2017–ICCV CP-CNN 73.6 106.4 21.72CP-CNN 0.72CP-CNN 68.4MSANet -
2018–AAAI TDF-CNN 97.5 145.1 - - - -
2018–WACV SaCNN 86.8 139.2 - - - -
2018–CVPR ACSCP 75.7 102.7 - - 5.1M None
2018–CVPR D-ConvNet-v1 73.5 112.3 - - - -
2018–CVPR IG-CNN 72.5 118.2 - - - -
2018–CVPR L2R (Multi-task, Query-by-example) 72.0 106.6 - - - VGG-16
2018–CVPR L2R (Multi-task, Keyword) 73.6 112.0 - - - VGG-16
2018–IJCAI DRSAN 69.3 96.4 - - - -
2018–ECCV ic-CNN (one stage) 69.8 117.3 - - - -
2018–ECCV ic-CNN (two stages) 68.5 116.2 - - - -
2018–CVPR CSRNet 68.2 115.0 23.79 0.76 16.26MSANet VGG-16
2018–ECCV SANet 67.0 104.5 - - 0.91M None
2019–AAAI GWTA-CCNN 154.7 229.4 - - - -
2019–ICASSP ASD 65.6 98.0 - - - -
2019–CVPR SFCN 64.8 107.5 - - - -
2019–CVPR TEDnet 64.2 109.1 25.88 0.83 1.63M -
2019–CVPR ADCrowdNet(AMG-bAttn-DME) 63.2 98.9 24.48 0.88 - -
2019–CVPR PACNN 66.3 106.4 - - - -
2019–CVPR PACNN+CSRNet 62.4 102.0 - - - -
2019–CVPR CAN 62.3 100.0 - - - -
2019–WACV SPN 61.7 99.5 - - - -

ShanghaiTech Part B

Year-Conference/Journal Methods MAE MSE
2016–CVPR MCNN 26.4 41.3
2017–ICIP MSCNN 17.7 30.2
2017–AVSS CMTL 20.0 31.1
2017–CVPR Switching CNN 21.6 33.4
2017–ICCV CP-CNN 20.1 30.1
2018–TIP BSAD 20.2 35.6
2018–WACV SaCNN 16.2 25.8
2018–CVPR ACSCP 17.2 27.4
2018–CVPR CSRNet 10.6 16.0
2018–CVPR IG-CNN 13.6 21.1
2018–CVPR D-ConvNet-v1 18.7 26.0
2018–CVPR DecideNet 21.53 31.98
2018–CVPR DecideNet + R3 20.75 29.42
2018–CVPR L2R (Multi-task, Query-by-example) 14.4 23.8
2018–CVPR L2R (Multi-task, Keyword) 13.7 21.4
2018–IJCAI DRSAN 11.1 18.2
2018–AAAI TDF-CNN 20.7 32.8
2018–ECCV ic-CNN (one stage) 10.4 16.7
2018–ECCV ic-CNN (two stages) 10.7 16.0
2018–ECCV SANet 8.4 13.6
2019–WACV SPN 9.4 14.4
2019–ICASSP ASD 8.5 13.7
2019–CVPR TEDnet 8.2 12.8
2019–CVPR CAN 7.8 12.2
2019–CVPR ADCrowdNet(AMG-attn-DME) 7.7 12.9
2019–CVPR ADCrowdNet(AMG-DME) 7.6 13.9
2019–CVPR SFCN 7.6 13.0
2019–CVPR PACNN 8.9 13.5
2019–CVPR PACNN+CSRNet 7.6 11.8

UCF-QNRF

Year-Conference/Journal Method C-MAE C-NAE C-MSE DM-MAE DM-MSE DM-HI L- Av. Precision L-Av. Recall L-AUC
2013–CVPR Idrees 2013CL 315 0.63 508 - - - - - -
2016–CVPR MCNNCL 277 0.55   0.006670 0.0223 0.5354 59.93% 63.50% 0.591
2017–AVSS CMTLCL 252 0.54 514 0.005932 0.0244 0.5024 - - -
2017–CVPR Switching CNNCL 228 0.44 445 0.005673 0.0263 0.5301 - - -
2018–ECCV CL 132 0.26 191 0.00044 0.0017 0.9131 75.8% 59.75% 0.714
2019–CVPR TEDnet 113 - 188 - - - - - -
2019–CVPR CAN 107 - 183 - - - - - -
2019–CVPR SFCN 102.0 - 171.4 - - - - - -

UCF_CC_50

Year-Conference/Journal Methods MAE MSE
2013–CVPR Idrees 2013 468.0 590.3
2015–CVPR Zhang 2015 467.0 498.5
2016–ACM MM CrowdNet 452.5 -
2016–CVPR MCNN 377.6 509.1
2016–ECCV CNN-Boosting 364.4 -
2016–ECCV Hydra-CNN 333.73 425.26
2016–ICIP Shang 2016 270.3 -
2017–ICIP MSCNN 363.7 468.4
2017–AVSS CMTL 322.8 397.9
2017–CVPR Switching CNN 318.1 439.2
2017–ICCV CP-CNN 298.8 320.9
2017–ICCV ConvLSTM-nt 284.5 297.1
2018–TIP BSAD 409.5 563.7
2018–AAAI TDF-CNN 354.7 491.4
2018–WACV SaCNN 314.9 424.8
2018–CVPR IG-CNN 291.4 349.4
2018–CVPR ACSCP 291.0 404.6
2018–CVPR L2R (Multi-task, Query-by-example) 291.5 397.6
2018–CVPR L2R (Multi-task, Keyword) 279.6 388.9
2018–CVPR D-ConvNet-v1 288.4 404.7
2018–CVPR CSRNet 266.1 397.5
2018–ECCV ic-CNN (two stages) 260.9 365.5
2018–ECCV SANet 258.4 334.9
2018–IJCAI DRSAN 219.2 250.2
2019–AAAI GWTA-CCNN 433.7 583.3
2019–WACV SPN 259.2 335.9
2019–CVPR ADCrowdNet(DME) 257.1 363.5
2019–CVPR TEDnet 249.4 354.5
2019–CVPR PACNN 267.9 357.8
2019–CVPR PACNN+CSRNet 241.7 320.7
2019–CVPR SFCN 214.2 318.2
2019–CVPR CAN 212.2 243.7
2019–ICASSP ASD 196.2 270.9

WorldExpo’10

Year-Conference/Journal Method S1 S2 S3 S4 S5 Avg.
2015–CVPR Zhang 2015 9.8 14.1 14.3 22.2 3.7 12.9
2016–CVPR MCNN 3.4 20.6 12.9 13.0 8.1 11.6
2017–ICIP MSCNN 7.8 15.4 14.9 11.8 5.8 11.7
2017–ICCV ConvLSTM-nt 8.6 16.9 14.6 15.4 4.0 11.9
2017–ICCV ConvLSTM 7.1 15.2 15.2 13.9 3.5 10.9
2017–ICCV Bidirectional ConvLSTM 6.8 14.5 14.9 13.5 3.1 10.6
2017–CVPR Switching CNN 4.4 15.7 10.0 11.0 5.9 9.4
2017–ICCV CP-CNN 2.9 14.7 10.5 10.4 5.8 8.86
2018–AAAI TDF-CNN 2.7 23.4 10.7 17.6 3.3 11.5
2018–CVPR IG-CNN 2.6 16.1 10.15 20.2 7.6 11.3
2018–TIP BSAD 4.1 21.7 11.9 11.0 3.5 10.5
2018–ECCV ic-CNN 17.0 12.3 9.2 8.1 4.7 10.3
2018–CVPR DecideNet 2.0 13.14 8.9 17.4 4.75 9.23
2018–CVPR D-ConvNet-v1 1.9 12.1 20.7 8.3 2.6 9.1
2018–CVPR CSRNet 2.9 11.5 8.6 16.6 3.4 8.6
2018–WACV SaCNN 2.6 13.5 10.6 12.5 3.3 8.5
2018–ECCV SANet 2.6 13.2 9.0 13.3 3.0 8.2
2018–IJCAI DRSAN 2.6 11.8 10.3 10.4 3.7 7.76
2018–CVPR ACSCP 2.8 14.05 9.6 8.1 2.9 7.5
2019–CVPR TEDnet 2.3 10.1 11.3 13.8 2.6 8.0
2019–CVPR PACNN 2.3 12.5 9.1 11.2 3.8 7.8
2019–CVPR ADCrowdNet(AMG-bAttn-DME) 1.7 14.4 11.5 7.9 3.0 7.7
2019–CVPR ADCrowdNet(AMG-attn-DME) 1.6 13.2 8.7 10.6 2.6 7.3
2019–CVPR CAN 2.9 12.0 10.0 7.9 4.3 7.4
2019–CVPR CAN(ECAN) 2.4 9.4 8.8 11.2 4.0 7.2

UCSD

Year-Conference/Journal Method MAE MSE
2015–CVPR Zhang 2015 1.60 3.31
2016–ECCV Hydra-CNN 1.65 -
2016–ECCV CNN-Boosting 1.10 -
2016–CVPR MCNN 1.07 1.35
2017–ICCV ConvLSTM-nt 1.73 3.52
2017–CVPR Switching CNN 1.62 2.10
2017–ICCV ConvLSTM 1.30 1.79
2017–ICCV Bidirectional ConvLSTM 1.13 1.43
2018–CVPR CSRNet 1.16 1.47
2018–CVPR ACSCP 1.04 1.35
2018–ECCV SANet 1.02 1.29
2018–TIP BSAD 1.00 1.40
2019–WACV SPN 1.03 1.32
2019–CVPR ADCrowdNet(DME) 0.98 1.25
2019–CVPR PACNN 0.89 1.18

Mall

Year-Conference/Journal Method MAE MSE
2012–BMVC Chen 2012 3.15 15.7
2016–ECCV CNN-Boosting 2.01 -
2017–ICCV Bidirectional ConvLSTM 2.10 7.6
2018–CVPR DecideNet 1.52 1.90

Comments