FDCNet: Frontend-Backend Fusion Dilated Network Through Channel-Attention Mechanism
Source abstract
Abstract
Crowd counting has attracted much attention in computer vision owing to its fundamental contribution in public security. But due to occlusions, perspective distortions, scale variations, and background interference it faces a great challenge. In this paper we propose a novel model to count crowds, named FDCNet: frontend-backend fusion dilated network through channel-attention mechanism. It merges the frontend feature map with the backend feature map, achieving a fusion of various scale features without additional branches or extra subtasks. The fusion is fed into the channel-attention block to optimize the procedure and to conduct feature recalibration to use global and spatial information. Furthermore, we utilize dilated layers to obtain a high-quality density map, and the SSIM-based loss function is added to compare the local correlation between the estimated density map and the ground truth. Our FDCNet is verified in four common datasets and gets a brilliant estimation.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Video Surveillance and Tracking Methods · Anomaly Detection Techniques and Applications · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China
References (33)
Show source-provided references
1. Detecting humans in dense crowds using locally-consistent scale prior and global occlusion reasoning10.1109/TPAMI.2015.2396051 ↗
2. Idrees, H., Saleemi, I., Seibert, C., and Shah, M. (2013, January 25–27). Multi-source multi-scale counting in extremely dense crowd images. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA.10.1109/CVPR.2013.329 ↗
3. Yang, J., Zhou, Y., and Kung, S.Y. (2018, January 20–24). Multi-scale generative adversarial networks for crowd counting. Proceedings of the IEEE International Conference on Pattern Recognition, Beijing, China.10.1109/ICPR.2018.8545683 ↗
4. Olmschenk, G., Tang, H., and Zhu, Z. (2018, January 12–15). Crowd counting with minimal data using generative adversarial networks for multiple target regression. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Lake Tahoe, CA, USA.10.1109/WACV.2018.00131 ↗
5. Liu, L., Wang, H., Li, G., Ouyang, W., and Lin, L. (2018, January 13–19). Counting using Deep Recurrent Spatial-Aware Network. Proceedings of the International Joint Conference on Artificial Intelligence, Stockholm, Sweden.10.24963/ijcai.2018/118 ↗
6. Sindagi, V.A., and Patel, V.M. (2017, January 22–29). Generating high-quality crowd density maps using contextual pyramid cnns. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.206 ↗
7. Cao, X., Wang, Z., Zhao, Y., and Su, F. (2018, January 8–14). Scale aggregation network for accurate and efficient crowd counting. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01228-1_45 ↗
8. 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 ↗
9. Sindagi, V.A., and Patel, V.M. (September, January 29). Cnn-based cascaded multitask learning of high-level prior and density estimation for crowd counting. Proceedings of the IEEE International Conference on Advanced Video and Signal Based Surveillance, Lecce, Italy.
10. Hu, J., Shen, L., and Sun, G. (2018, January 18–22). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
11. Li, Y., Zhang, X., and Chen, D. (2018, January 18–22). 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, UT, USA.10.1109/CVPR.2018.00120 ↗
12. Zhang, L., Shi, M., and Chen, Q. (2018, January 12–15). Crowd counting via scale-adaptive convolutional neural network. Proceedings of the IEEE Winter Conference on Applications of Computer Vision, Lake Tahoe, CA, USA.10.1109/WACV.2018.00127 ↗
13. Idrees, H., Tayyab, M., Athrey, K., Zhang, D., Al-Maadeed, S., Rajpoot, N., and Shah, M. (2018, January 8–14). Composition loss for counting, density map estimation and localization in dense crowds. Proceedings of the European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01216-8_33 ↗
14. Liu, X., van de Weijer, J., and Bagdanov, A.D. (2018, January 18–22). Leveraging unlabeled data for crowd counting by learning to rank. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00799 ↗
15. Shi, M., Yang, Z., Xu, C., and Chen, Q. (2018, January 29–31). Perspective-Aware CNN for Crowd Counting. Proceedings of the 21st IEEE International Conference on Electronics, Bucharest, Romania.
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. Pedestrian detection: An evaluation of the state of the art10.1109/TPAMI.2011.155 ↗
18. Robust real-time face detection10.1023/B:VISI.0000013087.49260.fb ↗
19. Dalal, N., and Triggs, B. (2005, January 20–26). Histograms of oriented gradients for human detection. Proceedings of the Computer Vision and Pattern Recognition, San Diego, CA, USA.
20. Object detection with discriminatively trained part-based models10.1109/TPAMI.2009.167 ↗
21. Chan, A.B., and Vasconcelos, N. (October, January 27). Bayesian poisson regression for crowd counting. Proceedings of the IEEE 12th International Conference, Kyoto, Japan.
22. Lempitsky, V., and Zisserman, A. (2010). Learning to count objects in images. Advances in Neural Information Processing Systems, The MIT Press.
23. 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 Computer Vision IEEE International Conference, Santiago, Chile.10.1109/ICCV.2015.372 ↗
24. Zhang, C., Li, H., Wang, X., and Yang, X. (2015, January 7–12). Cross-scene crowd counting via deep convolutional neural networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.
25. Boominathan, L., Kruthiventi, S.S., and Babu, R.V. (2016, January 15–19). Crowdnet: A deep convolutional network for dense crowd counting. Proceedings of the ACM on Multimedia Conference, Amsterdam, The Netherlands.10.1145/2964284.2967300 ↗
26. Wang, Q., Gao, J., Lin, W., and Yuan, Y. (2019, January 15–21). Learning from synthetic data for crowd counting in the wild. Proceedings of the Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00839 ↗
27. Liu, W., Salzmann, M., and Fua, P. (2019, January 15–21). Context-aware crowd counting. Proceedings of the Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00524 ↗
28. Liu, C., Weng, X., and Mu, Y. (2019, January 15–21). Recurrent attentive zooming for joint crowd counting and precise localization. Proceedings of the Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00131 ↗
29. Chaudhari, S., Polatkan, G., Ramanath, R., and Mithal, V. (2019, April 05). An Attentive Survey of Attention Models. Available online: https://arxiv.org/abs/1904.02874.
30. Chan, A.B., Liang, Z.S.J., and Vasconcelos, N. (2008, January 23–28). Privacy preserving crowd monitoring: Counting people without people models or tracking. Proceedings of the Computer Vision and Pattern Recognition, Anchorage, AK, USA.10.1109/CVPR.2008.4587569 ↗
31. Chen, K., Loy, C.C., Gong, S., and Xiang, T. (2012, January 3–7). Feature mining for localized crowd counting. Proceedings of the British Machine Vision Conference, Surrey, UK.10.5244/C.26.21 ↗
32. Dai, J., Li, Y., He, K., and Sun, J. (2016, January 5–10). R-fcn: Object detection via region-based fully convolutional networks. Proceedings of the Neural Information Processing Systems, Barcelona, Spain.
33. Wang, Y., and Zou, Y. (2016, January 25–28). Fast visual object counting via example-based density estimation. Proceedings of the 2016 IEEE International Conference on Image Processing, Phoenix, AZ, USA.10.1109/ICIP.2016.7533041 ↗