Abstract
Crowd localization, predicting head positions, is a more practical and high-level task than simply counting. Existing methods employ pseudo-bounding boxes or pre-designed localization maps, relying on complex post-processing to obtain the head positions. In this paper, we propose an elegant, end-to-end Crowd Localization TRansformer named CLTR that solves the task in the regression-based paradigm. The proposed method views the crowd localization as a direct set prediction problem, taking extracted features and trainable embeddings as input of the transformer-decoder. To reduce the ambiguous points and generate more reasonable matching results, we introduce a KMO-based Hungarian matcher, which adopts the nearby context as the auxiliary matching cost. Extensive experiments conducted on five datasets in various data settings show the effectiveness of our method. In particular, the proposed method achieves the best localization performance on the NWPU-Crowd, UCF-QNRF, and ShanghaiTech Part A datasets.
Project page at https://dk-liang.github.io/CLTR/.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Here, we ignore the \(\hat{C_j}\) for simply illustrating since heads usually report similar confidence score.
References
Abousamra, S., Hoai, M., Samaras, D., Chen, C.: Localization in the crowd with topological constraints. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)
Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213–229. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_13
Chen, Y., Liang, D., Bai, X., Xu, Y., Yang, X.: Cell localization and counting using direction field map. IEEE J. Biomed. Health Inf. 26(1), 359–368 (2021)
Dosovitskiy, A., et al.: An image is worth 16\(\times \)16 words: transformers for image recognition at scale. In: Proceedings of International Conference on Learning Representations (2020)
Du, D., et al.: VisDrone-CC2020: the vision meets drone crowd counting challenge results. In: Bartoli, A., Fusiello, A. (eds.) ECCV 2020. LNCS, vol. 12538, pp. 675–691. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-66823-5_41
Gao, J., Gong, M., Li, X.: Congested crowd instance localization with dilated convolutional swin transformer. arXiv preprint arXiv:2108.00584 (2021)
Gao, J., Han, T., Wang, Q., Yuan, Y.: Domain-adaptive crowd counting via inter-domain features segregation and gaussian-prior reconstruction. arXiv preprint arXiv:1912.03677 (2019)
Gao, J., Han, T., Yuan, Y., Wang, Q.: Learning independent instance maps for crowd localization. arXiv preprint arXiv:2012.04164 (2020)
Gao, J., Wang, Q., Yuan, Y.: Scar: spatial-/channel-wise attention regression networks for crowd counting. Neurocomputing 363, 1–8 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2016)
Hu, P., Ramanan, D.: Finding tiny faces. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2017)
Hu, Y., et al.: NAS-count: counting-by-density with neural architecture search. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12367, pp. 747–766. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58542-6_45
Idrees, H., et al.: Composition loss for counting, density map estimation and localization in dense crowds. In: Proceedings of European Conference on Computer Vision (2018)
Kuhn, H.W.: The Hungarian method for the assignment problem. Naval Res. Logist. Q. 2(1–2), 83–97 (1955)
Laradji, I.H., Rostamzadeh, N., Pinheiro, P.O., Vazquez, D., Schmidt, M.: Where are the blobs: counting by localization with point supervision. In: Proceedings of European Conference on Computer Vision (2018)
Li, Y., Zhang, X., Chen, D.: CSRNet: dilated convolutional neural networks for understanding the highly congested scenes. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2018)
Liang, D., Chen, X., Xu, W., Zhou, Y., Bai, X.: Transcrowd: weakly-supervised crowd counting with transformers. Sci. China Inf. Sci. 65(6), 1–14 (2022)
Liang, D., Xu, W., Zhu, Y., Zhou, Y.: Focal inverse distance transform maps for crowd localization and counting in dense crowd. arXiv preprint arXiv:2102.07925 (2021)
Liu, C., Weng, X., Mu, Y.: Recurrent attentive zooming for joint crowd counting and precise localization. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2019)
Liu, L., Lu, H., Zou, H., Xiong, H., Cao, Z., Shen, C.: Weighing counts: sequential crowd counting by reinforcement learning. In: Proceedings of European Conference on Computer Vision (2020)
Liu, L., Qiu, Z., Li, G., Liu, S., Ouyang, W., Lin, L.: Crowd counting with deep structured scale integration network. In: Proceedings of IEEE International Conference on Computer Vision (2019)
Liu, W., Salzmann, M., Fua, P.: Context-aware crowd counting. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2019)
Liu, X., et al.: End-to-end temporal action detection with transformer. IEEE Trans. Image Process. 31, 5427–5441 (2022)
Liu, Y., Shi, M., Zhao, Q., Wang, X.: Point in, box out: beyond counting persons in crowds. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2019)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of IEEE International Conference on Computer Vision, pp. 10012–10022 (2021)
Liu, Z., et al.: Visdrone-cc2021: the vision meets drone crowd counting challenge results. In: Proceedings of IEEE International Conference on Computer Vision, pp. 2830–2838 (2021)
Ma, Z., Wei, X., Hong, X., Gong, Y.: Bayesian loss for crowd count estimation with point supervision. In: Proceedings of IEEE International Conference on Computer Vision (2019)
Meng, D., et al.: Conditional detr for fast training convergence. In: Proceedings of IEEE International Conference on Computer Vision, pp. 3651–3660 (2021)
Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. In: Proceedings of Advances in Neural Information Processing Systems (2015)
Ribera, J., Güera, D., Chen, Y., Delp, E.J.: Locating objects without bounding boxes. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2019)
Sam, D.B., Peri, S.V., Sundararaman, M.N., Kamath, A., Radhakrishnan, V.B.: Locate, size and count: accurately resolving people in dense crowds via detection. IEEE Trans. Pattern Anal. Mach. Intell. 43, 2739–2751 (2020)
Sindagi, V.A., Patel, V.M.: Multi-level bottom-top and top-bottom feature fusion for crowd counting. In: Proceedings of IEEE International Conference on Computer Vision (2019)
Sindagi, V.A., Yasarla, R., Patel, V.M.: Jhu-crowd++: large-scale crowd counting dataset and a benchmark method. IEEE Trans. Pattern Anal. Mach. Intell. 44, 2594–2609 (2020)
Song, Q., et al.: Rethinking counting and localization in crowds: a purely point-based framework. In: Proceedings of IEEE International Conference on Computer Vision, pp. 3365–3374 (2021)
Sun, G., Liu, Y., Probst, T., Paudel, D.P., Popovic, N., Van Gool, L.: Boosting crowd counting with transformers. arXiv preprint arXiv:2105.10926 (2021)
Tian, Y., Chu, X., Wang, H.: Cctrans: simplifying and improving crowd counting with transformer. arXiv preprint arXiv:2109.14483 (2021)
Touvron, H., Cord, M., Douze, M., Massa, F., Sablayrolles, A., Jégou, H.: Training data-efficient image transformers & distillation through attention. In: Proceedings of International Conference on Machine Learning, pp. 10347–10357. PMLR (2021)
Wan, J., Chan, A.: Modeling noisy annotations for crowd counting. Adv. Neural Inf. Process. Syst. 33, 3386–3396 (2020)
Wan, J., Liu, Z., Chan, A.B.: A generalized loss function for crowd counting and localization. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1974–1983 (2021)
Wan, J., Wang, Q., Chan, A.B.: Kernel-based density map generation for dense object counting. IEEE Trans. Pattern Anal. Mach. Intell. 44, 1357–1370 (2020)
Wang, B., Liu, H., Samaras, D., Hoai, M.: Distribution matching for crowd counting. In: Proceedings of Advances in Neural Information Processing Systems (2020)
Wang, Q., Gao, J., Lin, W., Li, X.: Nwpu-crowd: a large-scale benchmark for crowd counting and localization. IEEE Trans. Pattern Anal. Mach. Intell. 43, 2141–2149 (2020)
Wang, Q., Gao, J., Lin, W., Yuan, Y.: Learning from synthetic data for crowd counting in the wild. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2019)
Wang, Y., Hou, J., Hou, X., Chau, L.P.: A self-training approach for point-supervised object detection and counting in crowds. IEEE Trans. Image Process. 30, 2876–2887 (2021)
Wen, L., et al.: Detection, tracking, and counting meets drones in crowds: a benchmark. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, pp. 7812–7821 (2021)
Xu, C., et al.: Autoscale: learning to scale for crowd counting. Int. J. Comput. Vision 130, 1–30 (2022)
Xu, C., Qiu, K., Fu, J., Bai, S., Xu, Y., Bai, X.: Learn to scale: generating multipolar normalized density map for crowd counting. In: Proceedings of IEEE International Conference on Computer Vision (2019)
Zhang, Y., Zhou, D., Chen, S., Gao, S., Ma, Y.: Single-image crowd counting via multi-column convolutional neural network. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition (2016)
Acknowledgment
This work was supported by National Key R &D Program of China (Grant No. 2018YFB1004602).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Liang, D., Xu, W., Bai, X. (2022). An End-to-End Transformer Model for Crowd Localization. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13661. Springer, Cham. https://doi.org/10.1007/978-3-031-19769-7_3
Download citation
DOI: https://doi.org/10.1007/978-3-031-19769-7_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19768-0
Online ISBN: 978-3-031-19769-7
eBook Packages: Computer ScienceComputer Science (R0)