Analyzing Crowds with Deep Learning: A Review of Methods and Challenges

Mohan M. Khambalkar, Pranjal Chaubey, Kalpan Shah, Rana Harshil Jayesh Kumar

Abstract


With the growing population, the need for an effective crowd management tool emerged. It is important to monitor and analyze unusual crowd movements and behavior for many applications such as peaceful events, protests, gatherings, or traffic management. Current systems, such as video surveillance, are a useful technique for crowd monitoring, but they require human visual capabilities to monitor the crowd. This work is a paper on Crowd Analysis using convolution neural networks (CNN). We present three models in this paper. First, Face Mask detection, second Object detection, and third Crowd Analysis. This work contributes towards constructing a model that works on images, video feeds, and live CCTV feeds

References


Vishakha L. Bansod, Asha Ambhaikar, Crowd Analysis System for Images of CCTV Camera, International Journal of Recent Technology and Engineering (IJRTE)3878, Volume-8 Issue-5, January 2020A Study on Crowd Detection and Density Analysis for Safety Control: Mayur D. Chaudhari, Archana S. Ghotkar.

Ali M. Al-Shaery, Norah S. Farooqi, Mohamed O. Khozium “In-Depth Survey to Detect, Monitor and Manage Crowd”, IEEE Xplore, ISSN: 2169-3536, Volume: 8, November 2020, Page(s): 209008 – 209019.

Jingwei Tang, Xingtian Yao, Xin Kang, Shun Nishide, Fuji Ren. "Position-Free Hand Gesture Recognition Using Single Shot MultiBox Detector Based Neural Network" IEEE International Conference on Mechatronics and Automation (ICMA), August 2019, Pages 2251–2256.

Joseph Redmon, Santosh Divvala, Ross Girshick, Ali Farhadi "You Only Look Once: Unified, Real-Time Object Detection" Computer Vision and Pattern Recognition, May 2016 [Online] Available at https://arxiv.org/abs/1506.02640https://www.analyticsvidhya.com/blog/2019/02/building-crowd-counting-model-python/

Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy et al. European Conference on Computer Vision, Computer Vision – ECCV 2016, pp 21–37 SSD: Single Shot MultiBox Detector SpringerLink,

He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8691, pp. 346–361. Springer, Heidelberg (2014). doi:10.1007/978-3-319-10578-9_23

Alexander Toshev, Christian Szegedy, “Deep Pose: Human Pose Estimation via Deep Neural Networks”, Computer Vision and Pattern Recognition, IEEE Conference on Computer Vision, and Pattern Recognition, 2014, Cornell University, IEEE Xplore.

https://static.googleusercontent.com/media/research.google.com/en//pubs/archive/42237.pdfObject detection and tracking in PyTorch

Gaurav Tripathi, Kuldeep Singh, Dinesh Kumar Vishwakarma, “Convolutional neural networks for crowd behavior analysis: a survey”, The Visual Computer: International Journal of Computer Graphics, Volume 35, Issue 5 May 2019, pp 753–776, Springer Link. https://machinelearningmastery.com/object-recognition-with-deep-learning/

LARXEL, “Face Mask Detection”, Kaggle (2020) https://www.kaggle.com/datasets/andrewmvd/face-mask-detection.

Moses Olafenwa, “Video and Live-Feed Detection and Analysis” [Online] Available from https://imageai.readthedocs.io/en/latest/video/index.htmlhttps://ai.stanford.edu/~jkrause/cars/car_dataset.html

Tsung-Yi Lin, What is COCO? Common objects in context (2023) https://cocodataset.org/#home

Sergey Zagoruyko, Nikos Komodakis "Wide Residual Networks" SERGEY ZAGORUYKO AND NIKOS KOMODAKIS: WIDE RESIDUAL NETWORKS, [Online] https://arxiv.org/pdf/1605.07146.pdf

Zhou B., Zhang, F., and Peng L (2012) 'Higher-order SVD analysis for crowd density estimation', Computer Visual Image Understanding, 116(9), pp. 1014-1021.

Donahue J., Hendricks L. A. et al (2017) 'Long-term recurrent convolutional networks for visual recognition and description', IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 39(4), pp. 677-691

Rohith Gandhi "R-CNN, Fast R-CNN, Faster R-CNN, YOLO — Object Detection Algorithms" (2018) Understanding object detection algorithms. towards data science.

https://towardsdatascience.com/r-cnn-fast-r-cnn-faster-r-cnn-yolo-object-detection-algorithms-36d53571365e

Chris Fotache, "Object detection and tracking in PyTorch" Towards Data Science (2018) Detecting multiple objects in images and tracking them in videos.

https://towardsdatascience.com/object-detection-and-tracking-in-pytorch-b3cf1a696a98


Refbacks

  • There are currently no refbacks.