Deep Trajectory Classification Model for Congestion Detection in Human Crowds
Source abstract
Abstract
In high-density gatherings, crowd disasters frequently occur despite all the safety measures. Timely detection of congestion in human crowds using automated analysis of video footage can prevent crowd disasters. Recent work o... | Find, read and cite all the research you need on Tech Science Press
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Anomaly Detection Techniques and Applications · Video Surveillance and Tracking Methods · Evacuation and Crowd Dynamics
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (70)
Show source-provided references
1. Loveparade 2010: Automatic video analysis of a crowd disaster10.1016/j.cviu.2011.08.006 ↗
2. Still · Introduction to Crowd Science · 201410.1201/b17097 ↗
3. Social force model for pedestrian dynamics10.1103/PhysRevE.51.4282 ↗
4. Simulation of pedestrian dynamics using a two-dimensional cellular automaton10.1016/S0378-4371(01)00141-8 ↗
5. Dynamics of crowd disasters: An empirical study10.1103/PhysRevE.75.046109 ↗
6. Crowded scene analysis: A survey10.1109/TCSVT.2014.2358029 ↗
7. Scene perception guided crowd anomaly detection10.1016/j.neucom.2020.07.019 ↗
8. Real-world anomaly detection in surveillance videos
9. Crowd panic state detection using entropy of the distribution of enthalpy10.1016/j.physa.2019.04.033 ↗
10. Abnormal crowd behavior detection using social force model
11. Context-aware crowd counting
12. Crowd counting with crowd attention convolutional neural network10.1016/j.neucom.2019.11.064 ↗
13. Cross-scale generative adversarial network for crowd density estimation from images10.1016/j.engappai.2020.103777 ↗
14. Crowd density estimation using fusion of multi-layer features
15. Floor fields for tracking in high density crowd scenes
16. Multiple human tracking in high-density crowds10.1016/j.imavis.2012.08.013 ↗
17. Crowd behaviours analysis in dynamic visual scenes of complex environment
18. Congestion detection of pedestrians using the velocity entropy: A case study of love parade 2010 disaster10.1016/j.physa.2015.08.013 ↗
19. Congestion detection in pedestrian crowds using oscillation in motion trajectories10.1016/j.engappai.2019.07.009 ↗
20. Crowd scene understanding from the video: A survey10.1145/3052930 ↗
21. Crowd analysis: A survey10.1007/s00138-008-0132-4 ↗
22. Crowd analysis using computer vision techniques
23. Density aware person detection and tracking in crowds
24. Learning to count objects in images
25. Interactive object counting
26. Learning to count with regression forest and structured labels
27. Beyond counting: Comparisons of density maps for crowd analysis tasks—Counting, detection, and tracking10.1109/TCSVT.2018.2837153 ↗
28. Beyond counting: Comparisons of density maps for crowd analysis tasks—Counting, detection, and tracking10.1109/TCSVT.2018.2837153 ↗
29. Multi-source multi-scale counting in extremely dense crowd images
30. Counting people with low-level features and Bayesian regression10.1109/TIP.2011.2172800 ↗
31. Cross-scene crowd counting via deep convolutional neural networks
32. Generating high-quality crowd density maps using contextual pyramid CNNS
33. Spatiotemporal modeling for crowd counting in videos
34. Faster R-CNN: Towards real-time object detection with region proposal networks10.1109/TPAMI.2016.2577031 ↗
35. M2tracker: A multi-view approach to segmenting and tracking people in a cluttered scene10.1023/A:1021849801764 ↗
36. Tracking people in crowded scenes across multiple cameras
37. Multi view image surveillance and tracking
38. An algorithm for multiple object trajectory tracking
39. A Bayesian multiple-blob tracker
40. Real-time tracking of non-rigid objects using mean shift
41. Max-margin offline pedestrian tracking with multiple cues
42. Performance of optical flow techniques10.1007/BF01420984 ↗
43. Determining optical flow10.1016/0004-3702(81)90024-2 ↗
44. Definition and properties of lagrangian coherent structures from finite-time lyapunov exponents in two-dimensional aperiodic flows10.1016/j.physd.2005.10.007 ↗
45. Visualizing vector field topology in fluid flows10.1109/38.79452 ↗
46. Image based flow visualization10.1145/566654.566646 ↗
47. Anomaly detection in extremely crowded scenes using spatiotemporal motion pattern models
48. Kratz · Machine Learning for Vision-Based Motion Analysis · 2011 · 26310.1007/978-0-85729-057-1_10 ↗
49. Random field topic model for semantic region analysis in crowded scenes from tracklets
50. Understanding collective crowd behaviors: Learning a mixture model of dynamic pedestrian-agents
51. Extracting descriptive motion information from crowd scenes
52. S. D. Khan, M. Tayyab, M. K. Amin, A. Nour, A. Basalamah et al., “Towards a crowd analytic framework for crowd management in Majid-Al-Haram,” arXiv preprint, vol. 1709.05952, pp. 1–11, 2017. [Online]. Available: https://arxiv.org/abs/1709.05952.
53. Trajectory-based anomalous event detection10.1109/TCSVT.2008.2005599 ↗
54. Goal-based trajectory analysis for unusual behaviour detection in intelligent surveillance10.1016/j.imavis.2010.11.003 ↗
55. Anomaly detection in moving crowds through spatiotemporal autoencoding and additional attention
56. Learning temporal regularity in video sequences
57. Abnormal event detection in videos using spatiotemporal autoencoder
58. Good features to track
59. Particle video: Long-range motion estimation using point trajectories10.1007/s11263-008-0136-6 ↗
60. Dense point trajectories by gpu accelerated large displacement optical flow
61. A lagrangian particle dynamics approach for crowd flow segmentation and stability analysis
62. High accuracy optical flow estimation based on a theory for warping
63. Detecting dominant motion flows and people counting in high density crowds
64. Sequential deep trajectory descriptor for action recognition with three-stream cnn10.1109/TMM.2017.2666540 ↗
65. Classifying spatial trajectories using representation learning10.1007/s41060-016-0014-1 ↗
66. S. K. Kumaran, D. P. Dogra, P. P. Roy and A. Mitra, “Video trajectory classification and anomaly detection using hybrid CNN-VAE,” arXiv preprint, vol. 1812.07203, pp. 1–9, 2018. [Online]. Available: https://arxiv.org/abs/1812.07203.
67. Dropout: A simple way to prevent neural networks from overfitting
68. Visualizing data using t-SNE
69. The crowd congestion level—A new measure for risk assessment in video-based crowd monitoring
70. Learning spatiotemporal features with 3d convolutional networks