TY - JOUR
T1 - PaDNet
T2 - Pan-Density Crowd Counting
AU - Tian, Yukun
AU - Lei, Yiming
AU - Zhang, Junping
AU - Wang, James Z.
N1 - Funding Information:
Manuscript received February 27, 2019; revised August 3, 2019 and September 20, 2019; accepted October 22, 2019. Date of publication November 12, 2019; date of current version January 23, 2020. The work of Y. Tian, Y. Lei, and J. Zhang was supported in part by the National Key R&D Program of China under Grant 2018YFB1305104, in part by the National Natural Science Foundation of China under Grant NSFC 61673118, in part by the Shanghai Municipal Science and Technology Major Project under Grant 2018SHZDZX01, and in part by ZJLab. The work of J. Z. Wang was supported by The Pennsylvania State University. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Soma Biswas. (Corresponding author: Junping Zhang.) Y. Tian, Y. Lei, and J. Zhang are with the Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai 200433, China (e-mail: [email protected]; [email protected]; [email protected]).
Funding Information:
He was a recipient of the National Science Foundation Career Award (2004).
Publisher Copyright:
© 1992-2012 IEEE.
PY - 2020
Y1 - 2020
N2 - Crowd counting is a highly challenging problem in computer vision and machine learning. Most previous methods have focused on consistent density crowds, i.e., either a sparse or a dense crowd, meaning they performed well in global estimation while neglecting local accuracy. To make crowd counting more useful in the real world, we propose a new perspective, named pan-density crowd counting, which aims to count people in varying density crowds. Specifically, we propose the Pan-Density Network (PaDNet) which is composed of the following critical components. First, the Density-Aware Network (DAN) contains multiple subnetworks pretrained on scenarios with different densities. This module is capable of capturing pan-density information. Second, the Feature Enhancement Layer (FEL) effectively captures the global and local contextual features and generates a weight for each density-specific feature. Third, the Feature Fusion Network (FFN) embeds spatial context and fuses these density-specific features. Further, the metrics Patch MAE (PMAE) and Patch RMSE (PRMSE) are proposed to better evaluate the performance on the global and local estimations. Extensive experiments on four crowd counting benchmark datasets, the ShanghaiTech, the UCF_CC_50, the UCSD, and the UCF-QNRF, indicate that PaDNet achieves state-of-the-art recognition performance and high robustness in pan-density crowd counting.
AB - Crowd counting is a highly challenging problem in computer vision and machine learning. Most previous methods have focused on consistent density crowds, i.e., either a sparse or a dense crowd, meaning they performed well in global estimation while neglecting local accuracy. To make crowd counting more useful in the real world, we propose a new perspective, named pan-density crowd counting, which aims to count people in varying density crowds. Specifically, we propose the Pan-Density Network (PaDNet) which is composed of the following critical components. First, the Density-Aware Network (DAN) contains multiple subnetworks pretrained on scenarios with different densities. This module is capable of capturing pan-density information. Second, the Feature Enhancement Layer (FEL) effectively captures the global and local contextual features and generates a weight for each density-specific feature. Third, the Feature Fusion Network (FFN) embeds spatial context and fuses these density-specific features. Further, the metrics Patch MAE (PMAE) and Patch RMSE (PRMSE) are proposed to better evaluate the performance on the global and local estimations. Extensive experiments on four crowd counting benchmark datasets, the ShanghaiTech, the UCF_CC_50, the UCSD, and the UCF-QNRF, indicate that PaDNet achieves state-of-the-art recognition performance and high robustness in pan-density crowd counting.
UR - http://www.scopus.com/inward/record.url?scp=85078543838&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85078543838&partnerID=8YFLogxK
U2 - 10.1109/TIP.2019.2952083
DO - 10.1109/TIP.2019.2952083
M3 - Article
C2 - 31725380
AN - SCOPUS:85078543838
SN - 1057-7149
VL - 29
SP - 2714
EP - 2727
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
M1 - 8897143
ER -