|
|
基于双分支自注意力的密集人群计数算法
|
Abstract:
及时、准确的进行人流监控及预警是公共安全管理的迫切需求，使用基于计算机视觉的人群计数方法是满足该需求的主要方法之一。针对现有计数模型对人员前景特征和背景特征的关联不够的问题，设计基于双分支自注意力机制的密集人群计数算法。在视觉主干网络之后使用双分支自注意力模块，以促使网络关注有效的人员区域，提升主干网络的特征精炼能力。在Shanghai Tech PART B和UCF-QNRF数据集上进行大量的实验，消融实验的结果证明所提出的模块提升了人群计数的准确性。此外，实验结果表明所提出方法获得比其他经典方法更好的实验结果。
The urgent need for public safety management is timely and accurate crowd monitoring and early warning. The use of crowd counting methods based on computer vision is one of the main methods to meet this need. To tackle the problem that existing counting models do not adequately correlate people’s foreground features and background features, a dense crowd counting algorithm based on a dual-branch self-attention mechanism is designed. A dual-branch self-attention module is used after the visual backbone network to prompt the network to focus on effective person areas and improve the feature refining capabilities of the backbone network. A large number of experiments were conducted on Shanghai Tech PART B and UCF-QNRF data sets, and the results of ablation experiments proved that the proposed modules improved the accuracy of crowd counting. Furthermore, experimental results show that the proposed method obtains better experimental results than other classical methods.
| [1] | Zhang, Y., Zhou, D., Chen, S., et al. (2016) Single-Image Crowd Counting via Multi-Column Convolutional Neural Network. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 589-597. https://doi.org/10.1109/CVPR.2016.70 |
| [2] | Boominathan, L., Kruthiventi, S.S.S. and Babu, R.V. (2016) CrowdNet: A Deep Convolutional Network for Dense Crowd Counting. Proceedings of the 24th ACM International Conference on Multimedia, 640-644. https://doi.org/10.1145/2964284.2967300 |
| [3] | Cao, X., Wang, Z., Zhao, Y., et al. (2018) Scale Aggregation Network for Accurate and Efficient Crowd Counting. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Computer Vision—ECCV 2018, Lecture Notes in Computer Science, Vol. 11209, Springer, Cham, 734-750. https://doi.org/10.1007/978-3-030-01228-1_45 |
| [4] | Zeng, L., Xu, X., Cai, B., et al. (2017) Multi-Scale Convolutional Neural Networks for Crowd Counting. 2017 IEEE International Conference on Image Processing, Beijing, 17-20 September 2017, 465-469. https://doi.org/10.1109/ICIP.2017.8296324 |
| [5] | Li, Y., Zhang, X. and Chen, D. (2018) CSRNET: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 1091-1100. https://doi.org/10.1109/CVPR.2018.00120 |
| [6] | Hossain, M., Hosseinzadeh, M., Chanda, O., et al. (2019) Crowd Counting Using Scale-Aware Attention Networks. 2019 IEEE Winter Conference on Applications of Computer Vision, Waikoloa, 7-11 January 2019, 1280-1288. https://doi.org/10.1109/WACV.2019.00141 |
| [7] | Vaswani, A., Shazeer, N., Parmar, N., et al. (2017) Attention Is All You Need. Advances in Neural Information Processing Systems, 30. |
| [8] | Chen, L., Zhang, H., Xiao, J., et al. (2017) SCA-CNN: Spatial and Channel-Wise Attention in Convolutional Networks for Image Captioning. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 5659-5667. https://doi.org/10.1109/CVPR.2017.667 |
| [9] | Hu, J., Shen, L. and Sun, G. (2018) Squeeze-and-Excitation Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018,7132-7141. https://doi.org/10.1109/CVPR.2018.00745 |
| [10] | Wang, Q., Wu, B., Zhu, P., et al. (2020) ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, 13-19 June 2020, 11534-11542. https://doi.org/10.1109/CVPR42600.2020.01155 |
| [11] | Wang, X., Girshick, R., Gupta, A., et al. (2018) Non-Local Neural Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 7794-7803. https://doi.org/10.1109/CVPR.2018.00813 |
| [12] | Dai, J., Qi, H., Xiong, Y., et al. (2017) Deformable Convolutional Networks. Proceedings of the IEEE International Conference on Computer Vision, Venice, 22-29 October 2017, 764-773. https://doi.org/10.1109/ICCV.2017.89 |
| [13] | Srivastava, R.K., Greff, K. and Schmidhuber, J. (2015) Training Very Deep Networks. Advances in Neural Information Processing Systems, 28. |
| [14] | Chen, Y., Dai, X., Liu, M., et al. (2020) Dynamic Convolution: Attention over Convolution Kernels. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, 13-19 June 2020, 11030-11039. https://doi.org/10.1109/CVPR42600.2020.01104 |
| [15] | Sindagi, V.A. and Patel, V.M. (2017) CNN-Based Cascaded Multi-Task Learning of High-Level Prior and Density Estimation for Crowd Counting. IEEE International Conference on Advanced Video and Signal Based Surveillance, Lecce, 29 August 2017, 1-6. https://doi.org/10.1109/AVSS.2017.8078491 |
| [16] | Sam, D.B., Surya, S. and Babu, R.V. (2017) Switching Convolutional Neural Network for Crowd Counting. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, 21-26 July 2017, 5744-5752. https://doi.org/10.1109/CVPR.2017.429 |
| [17] | Liang, D., Chen, X., Xu, W., et al. (2022) Transcrowd: Weakly-Supervised Crowd Counting with Transformers. Science China Information Sciences, 65, Article No. 160104. https://doi.org/10.1007/s11432-021-3445-y |
| [18] | Gao, J., Wang, Q. and Yuan, Y. (2019) SCAR: Spatial-/Channel-Wise Attention Regression Networks for Crowd Counting. Neurocomputing, 363, 1-8. https://doi.org/10.1016/j.neucom.2019.08.018 |
| [19] | Liu, J., Gao, C., Meng, D., et al. (2018) Decidenet: Counting Varying Density Crowds through Attention Guided Detection and Density Estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, 18-23 June 2018, 5197-5206. https://doi.org/10.1109/CVPR.2018.00545 |
| [20] | Zhou, Y., Yang, J., Li, H., et al. (2020) Adversarial Learning for Multiscale Crowd Counting under Complex Scenes. IEEE Transactions on Cybernetics, 51, 5423-5432. https://doi.org/10.1109/TCYB.2019.2956091 |
| [21] | Simonyan, K. and Zisserman, A. (2014) Very Deep Convolutional Networks for Large-Scale Image Recognition. |
| [22] | He, K., Zhang, X., Ren, S., et al. (2016) Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, 27-30 June 2016, 770-778. https://doi.org/10.1109/CVPR.2016.90 |
| [23] | Idrees, H., Tayyab, M., Athrey, K., et al. (2018) Composition Loss for Counting, Density Map Estimation and Localization in Dense Crowds. In: Ferrari, V., Hebert, M., Sminchisescu, C. and Weiss, Y., Eds., Computer Vision—ECCV 2018, Lecture Notes in Computer Science, Vol. 11206, Springer, Cham, 532-546. https://doi.org/10.1007/978-3-030-01216-8_33 |
| [24] | Wang, Q., Gao, J., Lin, W., et al. (2019) Learning from Synthetic Data for Crowd Counting in the Wild. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, 15-20 June 2019, 8198-8207. https://doi.org/10.1109/CVPR.2019.00839 |
| [25] | Gao, J., Lin, W., Zhao, B., et al. (2019) C^ 3 Framework: An Open-Source Pytorch Code for Crowd Counting. https://arxiv.org/abs/1907.02724 |
