A High-Density Crowd Counting Method Based on Convolutional Feature Fusion
Source abstract
Abstract
In recent years, the trampling events due to overcrowding have occurred frequently, which leads to the demand for crowd counting under a high-density environment. At present, there are few studies on monitoring crowds in a large-scale crowded environment, while there exists technology drawbacks and a lack of mature systems. Aiming to solve the crowd counting problem with high-density under complex environments, a feature fusion-based deep convolutional neural network method FF-CNN (Feature Fusion of Convolutional Neural Network) was proposed in this paper. The proposed FF-CNN mapped the crowd image to its crowd density map, and then obtained the head count by integration. The geometry adaptive kernels were adopted to generate high-quality density maps which were used as ground truths for network training. The deconvolution technique was used to achieve the fusion of high-level and low-level features to get richer features, and two loss functions, i.e., density map loss and absolute count loss, were used for joint optimization. In order to increase the sample diversity, the original images were cropped with a random cropping method for each iteration. The experimental results of FF-CNN on the ShanghaiTech public dataset showed that the fusion of low-level and high-level features can extract richer features to improve the precision of density map estimation, and further improve the accuracy of crowd counting.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Fire Detection and Safety Systems · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education, Chongqing University, Chongqing 40004, China
School of Big Data & Software Engineering, Chongqing University, Chongqing 401331, China
Funding
National Key R&D Program of China
References (30)
Show source-provided references
1. Fruin, J.J. (1971). Pedestrian Planning and Design, Metropolitan Association of Urban Designers & Environmental Planners.
2. Crowd analysis: A survey10.1007/s00138-008-0132-4 ↗
3. Zeng, L., Xu, X., Cai, B., Qiu, S., and Zhang, T. (2017, January 17–20). Multi-scale convolutional neural networks for crowd counting. Proceedings of the IEEE International Conference on Image Processing, Beijing, China.10.1109/ICIP.2017.8296324 ↗
4. Zhang, C., Li, H., Wang, X., and Yang, X. (2015, January 8–10). Cross-scene crowd counting via deep convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.
5. Leibe, B., Seemann, E., and Schiele, B. (2005, January 20–26). Pedestrian detection in crowded scenes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA.
6. Segmentation and tracking of multiple humans in crowded environments10.1109/TPAMI.2007.70770 ↗
7. Ge, W., and Collins, R.T. (2009, January 20–25). Marked point processes for crowd counting. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Miami, FL, USA.10.1109/CVPRW.2009.5206621 ↗
8. Chan, A.B., Liang, Z.S.J., and Vasconcelos, N. (2008, January 24–26). Privacy preserving crowd monitoring: Counting people without people models or tracking. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.10.1109/CVPR.2008.4587569 ↗
9. Ryan, D., Denman, S., Fookes, C., and Sridharan, S. (2009, January 1–3). Crowd counting using multiple local features. Proceedings of the Digital Image Computing: Techniques and Applications, Melbourne, Australia.10.1109/DICTA.2009.22 ↗
10. Chan, A.B., and Vasconcelos, N. (October, January 27). Bayesian poisson regression for crowd counting. Proceedings of the IEEE 12th International Conference on Computer Vision, Kyoto, Japan.
11. Lempitsky, V., and Zisserman, A. (2010, January 6–9). Learning to count objects in images. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada.
12. Pham, V.Q., Kozakaya, T., Yamaguchi, O., and Okada, R. (2015, January 7–13). Count forest: Co-voting uncertain number of targets using random forest for crowd density estimation. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.372 ↗
13. Wang, C., Zhang, H., Yang, L., Liu, S., and Cao, X. (2015, January 26–30). Deep people counting in extremely dense crowds. Proceedings of the 23rd ACM International Conference on Multimedia, Brisbane, Australia.10.1145/2733373.2806337 ↗
14. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–6). Imagenet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA.
15. Schmidhuber, J., Meier, U., and Ciresan, D. (2012, January 16–21). Multi-column deep neural networks for image classification. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Providence, RI, USA.
16. Zhang, Y., Zhou, D., Chen, S., Gao, S., and Ma, Y. (2016, January 27–30). Single-image crowd counting via multi-column convolutional neural network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.70 ↗
17. Sam, D.B., Surya, S., and Babu, R.V. (2017, January 21–26). Switching convolutional neural network for crowd counting. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.429 ↗
18. Simonyan, K., and Zisserman, A. (arXiv, 2014). Very Deep Convolutional Networks for Large-Scale Image Recognition, arXiv.
19. Kumagai, S., Hotta, K., and Kurita, T. (arXiv, 2017). Mixture of Counting CNNs: Adaptive Integration of CNNs Specialized to Specific Appearance for Crowd Counting, arXiv.10.1007/s00138-018-0955-6 ↗
20. Zhang, L., Shi, M., and Chen, Q. (2018, January 12–14). Crowd counting via scale-adaptive convolutional neural network. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Lake Tahoe, NV, USA.10.1109/WACV.2018.00127 ↗
21. Low-Rank and Sparse Based Deep-Fusion Convolutional Neural Network for Crowd Counting10.1155/2017/5046727 ↗
22. Han, K., Wan, W., Yao, H., and Hou, L. (arXiv, 2017). Image Crowd Counting Using Convolutional Neural Network and Markov Random Field, arXiv.10.20965/jaciii.2017.p0632 ↗
23. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
24. Zeiler, M.D., Krishnan, D., Taylor, G.W., and Fergus, R. (2010, January 13–18). Deconvolutional networks. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, San Francisco, CA, USA.10.1109/CVPR.2010.5539957 ↗
25. Zeiler, M.D., and Fergus, R. (2014, January 6–12). Visualizing and understanding convolutional networks. Proceedings of the European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10590-1_53 ↗
26. Yang, B., Yan, J., Lei, Z., and Li, S.Z. (2015, January 13–16). Convolutional channel features. Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile.10.1109/ICCV.2015.18 ↗
27. Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11–13). Deep sparse rectifier neural networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA.
28. Long, J., Shelhamer, E., and Darrell, T. (2015, January 8–10). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
29. Marsden, M., McGuinness, K., Little, S., and O’Connor, N.E. (March, January 27). Fully convolutional crowd counting on highly congested scenes. Proceedings of the 12th International Conference on Computer Vision Theory and Applications, Porto, Portugal.10.5220/0006097300270033 ↗
30. Sindagi, V.A., and Patel, V.M. (September, January 29). Cnn-based cascaded multi-task learning of high-level prior and density estimation for crowd counting. Proceedings of the IEEE International Conference on In Advanced Video and Signal Based Surveillance, Lecce, Italy.