Head-Aware Density Adaptation Networks for Cross-Domain Crowd Counting

被引：0
作者：
Cai Y. [1 ]
Ma Z. [2 ]
Wang T. [3 ]
Lyu C. [4 ]
Wang C. [1 ]
He G. [1 ]
机构：
[1] School of Computer Science and Technology, East China Normal University, Shanghai
[2] School of Information Science and Engineering, East China University of Science and Technology, Shanghai
[3] Shanghai Starriver Bilingual School, Shanghai
[4] School of Mathematical Sciences, East China Normal University, Shanghai
来源：
Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics | 2021年 / 33卷 / 10期
关键词：
Crowd counting; Density map; Domain adaptation; Style transfer; Unsupervised learning;
D O I：
10.3724/SP.J.1089.2021.18794
中图分类号：
O24 [计算数学];
学科分类号：
070102 ;
摘要：
The crowd counting based on the domain adaptive method is an effective unsupervised learning strategy, which does not rely on labeled samples. However, the existing methods easily cause information loss in the head region or over counting errors in the background region. A head-aware density adaptive network (HADAN) is proposed for cross-domain crowd counting to solve these problems. In style transform part, the ground-truth of the source domain dataset is firstly used to generate the mask of the head area and background area, and then a head-aware cycle loss based on the mask is designed to prevent the confusion between the head area and the background area during the style transform process. Simultaneously, the density adaptation part further maps the features of both the source domain and the target domain to the same latent space using the discriminator, enhancing the consistency of the density map distribution. Proposed network trains style transfer and density adaptation parts in an end-to-end way, and they learn iteratively and benefit from each other. The experimental results on the synthetic data set GCC and three real-world datasets show that the MAE value of the algorithm is reduced by 9% on average, and the MSE value is reduced by 7%. Proposed method achieves robust cross-domain crowd counting in unlabeled target scenes. © 2021, Beijing China Science Journal Publishing Co. Ltd. All right reserved.
引用
收藏
页码：1514 / 1523
页数：9
相关论文
共 27 条
  • [1] Zhang C, Li H S, Wang X G, Et al., Cross-scene crowd counting via deep convolutional neural networks, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 833-841, (2015)
  • [2] Zhang Y Y, Zhou D, Chen S Q, Et al., Single-image crowd counting via multi-column convolutional neural network, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 589-597, (2016)
  • [3] Sam D B, Surya S, Babu R V., Switching convolutional neural network for crowd counting, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4031-4039, (2017)
  • [4] Zhao M M, Zhang J, Porikli F, Et al., Learning a perspective-embedded deconvolution network for crowd counting, Proceedings of the IEEE International Conference on Multimedia and Expo, pp. 403-408, (2017)
  • [5] Sam D B, Sajjan N N, Venkatesh Babu R, Et al., Divide and grow: capturing huge diversity in crowd images with incrementally growing CNN, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3618-3626, (2018)
  • [6] Li Y H, Zhang X F, Chen D M., CSRNet: dilated convolutional neural networks for understanding the highly congested scenes, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 1091-1100, (2018)
  • [7] Zhao S S, Fu H, Gong M M, Et al., Geometry-aware symmetric domain adaptation for monocular depth estimation, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 9788-9798, (2019)
  • [8] Wang Q, Gao J Y, Lin W, Et al., Learning from synthetic data for crowd counting in the wild, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8198-8207, (2019)
  • [9] Li M, Zhang Z X, Huang K Q, Et al., Estimating the number of people in crowded scenes by MID based foreground segmentation and head-shoulder detection, Proceedings of the 19th IEEE Conference on Computer Vision and Pattern Recognition, pp. 1-4, (2008)
  • [10] Fiaschi L, Nair R, Koethe U, Et al., Learning to count with regression forest and structured labels, Proceedings of the IEEE Conference on International Conference on Pattern Recognition, pp. 2685-2688, (2012)
123