Abstract
Crowd counting is a technique used to estimate the number of people in an image at a particular instance. Accurate and quick estimation of crowd counts is a challenging yet meaningful task which has a wide range of applications in diverse fields. A CNN-based crowd counting approach which utilizes the first 13 layers of pre-trained VGG-16 model and dilated convolutional layers to generate quality density maps is proposed. The dilated layers allow for larger receptive fields without increasing the amount of computation. In addition, a federated learning-based approach involving the federated averaging algorithm is adopted to decentralize the training process, reduce the time taken and preserve privacy. The problem of domain-adaptation in crowd counting is also addressed by training a model using the abundant labelled data available in the source domain and transferring the parameters learnt to a target domain with relatively fewer labelled data using neuron linear transformation, thereby minimizing the domain gap and improving performance.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Dollar, P., Wojek, C., Schiele, B., Perona, P.: Pedestrian detection: an evaluation of the state of the art. IEEE Trans. Pattern Anal. Mach. Intell. 34(4), 743–761 (2012)
Chen, K., Loy, C., Gong, S., Xiang, T.: Feature mining for localised crowd counting. In: Proceedings of the British Machine Vision Conference (2012)
Pham, V., Kozakaya, T., Yamaguchi, O., Okada, R.: COUNT forest: CO-voting uncertain number of targets using random forest for crowd density estimation. In: IEEE International Conference on Computer Vision (ICCV) (2015)
Boominathan, L., Kruthiventi, S., Babu, R.: CrowdNet: a deep convolutional network for dense crowd counting. In: Proceedings of the 24th ACM international conference on Multimedia (2016)
Sam, D., Surya, S., Babu, R.: Switching convolutional neural network for crowd counting. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-image crowd counting via multi-column convolutional neural network. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)
Wang, J., Wang, L., Yang, F.: Counting crowd with fully convolutional networks. In: 2017 2nd International Conference on Multimedia and Image Processing (ICMIP) (2017)
Hossain, M., Reddy, M., Cannons, K., Xu, Z., Wang, Y.: Domain adaptation in crowd counting. In: 2020 17th Conference on Computer and Robot Vision (CRV) (2020)
Li, Y., Zhang, X., Chen, D.: CSRNet: dilated convolutional neural networks for understanding the highly congested scenes. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (2018)
Wang, Q., Han, T., Gao, J., Yuan, Y.: Neuron linear transformation: modeling the domain shift for crowd counting. IEEE Transactions on Neural Networks and Learning Systems, pp. 1–13 (2021)
Hrushi, P., Tapan, D. and Jeya, R.: Federated learning for image classification using federated averaging algorithm. Annals of RSCB, pp. 5610–5615 (2021)
Yang, Q., Liu, Y., Chen, T., Tong, Y.: Federated machine learning. ACM Trans. Intell. Syst. Technol. 10(2), 1–19 (2019)
Chen, X., Bin, Y., Sang, N., Gao, C.: Scale pyramid network for crowd counting. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) (2019)
Kong, D., Gray, D., Tao, H.: A viewpoint invariant approach for crowd counting. In: 18th International Conference on Pattern Recognition (ICPR 2006) (2006)
Wang, Q., Gao, J., Lin, W., Yuan, Y.: Learning from synthetic data for crowd counting in the wild. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Simonyan, K., Zisserman, A.: Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv:1409.1556 (2014)
Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.: DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans. Pattern Anal. Mach. Intell. 40(4), 834–848 (2018)
VGG16 - Convolutional Network for Classification and Detection. https://neurohive.io/en/popular-networks/vgg16. Accessed 12 July 2022w
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Senthilkumar, R., Ritika, S., Manikandan, M., Shyam, B. (2022). Crowd Counting Using Federated Learning and Domain Adaptation. In: Badica, C., Paprzycki, M., Kharb, L., Chahal, D. (eds) Information, Communication and Computing Technology. ICICCT 2022. Communications in Computer and Information Science, vol 1670. Springer, Cham. https://doi.org/10.1007/978-3-031-20977-2_8
Download citation
DOI: https://doi.org/10.1007/978-3-031-20977-2_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20976-5
Online ISBN: 978-3-031-20977-2
eBook Packages: Computer ScienceComputer Science (R0)