A Survey on Supervised, Unsupervised, and Semi-Supervised Approaches in Crowd Counting
Source abstract
Abstract
Quantifying the number of individuals in images or videos to estimate crowd density is a challenging yet crucial task with significant implications for fields such as urban planning and public safety. Crowd counting has attra... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Evacuation and Crowd Dynamics · Human Mobility and Location-Based Analysis · Video Surveillance and Tracking Methods
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (100+)
Show source-provided references
1. D. Kang and A. Chan, “Crowd counting by adaptively fusing predictions from an image pyramid,” 2018, arXiv:1805.06115.
2. Switching convolutional neural network for crowd counting
3. Generating high-quality crowd density maps using contextual pyramid cnns
4. Zhai · Multimed. Syst. · 2023 · 29 · 302710.1007/s00530-021-00877-4 ↗
5. An attentive hierarchy ConvNet for crowd counting in smart city10.1007/s10586-022-03749-2 ↗
6. Fast visual object counting via example-based density estimation
7. Learning to count with CNN boosting
8. Learning to count objects in images
9. Cell counting via attentive recognition network
10. Counting in the wild
11. Towards perspective-free object counting with deep learning
12. Scale region recognition network for object counting in intelligent transportation system10.1109/TITS.2023.3296571 ↗
13. Object counting via group and graph attention network10.1109/TNNLS.2023.3336894 ↗
14. FPANet: Feature pyramid attention network for crowd counting10.1007/s10489-023-04499-3 ↗
15. Object counting in remote sensing via selective spatial-frequency pyramid network
16. Leaf counting with deep convolutional and deconvolutional networks
17. Learning to count leaves in rosette plants
18. Convolutional neural networks for counting fish in fisheries surveillance video
19. Crowd analysis: A survey10.1007/s00138-008-0132-4 ↗
20. Deeply learned attributes for crowded scene understanding
21. Understanding collective crowd behaviors: Learning a mixture model of dynamic pedestrian-agents
22. Privacy preserving crowd monitoring: Counting people without people models or tracking
23. Revisiting crowd counting: State-of-the-art, trends, and future perspectives10.1016/j.imavis.2022.104597 ↗
24. Visual crowd analysis: Open research problems
25. A. Bochkovskiy, “YOLOv4: Optimal speed and accuracy of object detection,” 2020, arXiv:2004.10934.
26. Pedestrian detection method based on faster R-CNN
27. Pedestrian detection: An evaluation of the state of the art10.1109/TPAMI.2011.155 ↗
28. HydraPlus-Net: Attentive deep features for pedestrian analysis
29. Single-image crowd counting via multi-column convolutional neural network
30. CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes
31. A deeply-recursive convolutional network for crowd counting
32. Composition loss for counting, density map estimation and localization in dense crowds
33. Bayesian loss for crowd count estimation with point supervision
34. Frame-recurrent video crowd counting10.1109/TCSVT.2023.3250946 ↗
35. Counting people by clustering person detector outputs
36. Estimating the number of people in crowded scenes by mid based foreground segmentation and head-shoulder detection
37. Pedestrian detection in crowded scenes
38. Monocular pedestrian detection: Survey and experiments10.1109/TPAMI.2008.260 ↗
39. Fast R-CNN
40. Faster R-CNN: Towards real-time object detection with region proposal networks
41. Mask R-CNN
42. You only look once: Unified, real-time object detection
43. SSD: Single shot multibox detector
44. Multi-source multi-scale counting in extremely dense crowd images
45. Bayesian poisson regression for crowd counting
46. Chen · Proc. Brit. Mach. Vis. Conf. · 2012
47. Crowd counting using multiple local features
48. Object recognition from local scale-invariant features
49. Gray scale and rotation invariant texture classification with local binary patterns
50. Histograms of oriented gradients for human detection
51. A MRF-based approach for real-time subway monitoring
52. Latent gaussian mixture regression for human pose estimation
53. Count forest: Co-voting uncertain number of targets using random forest for crowd density estimation
54. CNN-based multi-object tracking networks with position correction and imm in intelligent transportation system
55. Deep people counting in extremely dense crowds
56. Fast crowd density estimation with convolutional neural networks10.1016/j.engappai.2015.04.006 ↗
57. Cross-scene crowd counting via deep convolutional neural networks
58. Crowd density estimation using texture analysis and learning
59. Face recognition using kernel ridge regression
60. Cumulative attribute space for age and crowd density estimation
61. CNN-based cascaded multi-task learning of high-level prior and density estimation for crowd counting
62. Locate, size, and count: Accurately resolving people in dense crowds via detection
63. Attention scaling for crowd counting
64. Rethinking counting and localization in crowds: A purely point-based framework
65. Multiscale aggregate networks with dense connections for crowd counting10.1155/2021/9996232 ↗
66. CrowdCLIP: Unsupervised crowd counting via vision-language model
67. Single domain generalization for crowd counting
68. Estimation of number of people in crowded scenes using perspective transformation10.1109/3468.983420 ↗
69. Robust real-time face detection10.1023/B:VISI.0000013087.49260.fb ↗
70. Detecting pedestrians using patterns of motion and appearance
71. Detection of multiple, partially occluded humans in a single image by bayesian combination of edgelet part detectors
72. V. A. Sindagi, R. Yasarla, and V. M. Patel, “JHU-CROWD++: Large-scale crowd counting dataset and a benchmark method,” 2020. Accessed: Aug. 10, 2024. [Online]. Available: http://www.crowd-counting.com/10.1109/TPAMI.2020.3035969 ↗
73. NWPU-Crowd: A large-scale benchmark for crowd counting and localization10.1109/TPAMI.2020.3013269 ↗
74. Spatial uncertainty-aware semi-supervised crowd counting
75. A self-training approach for point-supervised object detection and counting in crowds10.1109/TIP.2021.3055632 ↗
76. Learning to count in the crowd from limited labeled data
77. DeepCorn: A semi-supervised deep learning method for high-throughput image-based corn kernel counting and yield estimation10.1016/j.knosys.2021.106874 ↗
78. Semi-supervised crowd counting via self-training on surrogate tasks
79. Learning error-driven curriculum for crowd counting
80. Modeling noisy annotations for crowd counting
81. HA-CCN: Hierarchical attention-based crowd counting network10.1109/TIP.2019.2928634 ↗
82. Dense crowd counting convolutional neural networks with minimal data using semi-supervised dual-goal generative adversarial networks
83. Generalizing semi-supervised generative adversarial networks to regression using feature contrasting10.1016/j.cviu.2019.06.004 ↗
84. Towards using count-level weak supervision for crowd counting10.1016/j.patcog.2020.107616 ↗
85. Learning from synthetic data for crowd counting in the wild
86. Transcrowd: Weakly-supervised crowd counting with transformers10.1007/s11432-021-3445-y ↗
87. Exploiting unlabeled data in CNNs by self-supervised learning to rank10.1109/TPAMI.2019.2899857 ↗
88. Semi-supervised crowd counting via multiple representation learning10.1109/TIP.2023.3313490 ↗
89. Semi-supervised crowd counting with contextual modeling: Facilitating holistic understanding of crowd scenes10.1109/TCSVT.2024.3392500 ↗
90. Region feature smoothness assumption for weakly semi-supervised crowd counting10.1002/cav.2173 ↗
91. Crowd counting with limited labeling through submodular frame selection10.1109/TITS.2018.2829987 ↗
92. Large-scale crowd analysis through the use of passive radio sensing networks10.3390/s20092624 ↗
93. DroneNet: Crowd density estimation using self-onns for drones
94. LCDnet: A lightweight crowd density estimation model for real-time video surveillance10.1007/s11554-023-01286-8 ↗
95. CLIP: Train faster with less data
96. Online em for functional data10.1016/j.csda.2017.01.006 ↗
97. Patel · Hands-On Unsupervised Learning Using Python: How to Build Applied Machine Learning Solutions from Unlabeled Data · 2019
98. Safe deep semi-supervised learning for unseen-class unlabeled data
99. SD-DiT: Unleashing the power of self-supervised discrimination in diffusion transformer
100. Completely self-supervised crowd counting via distribution matching