Published on Mon Dec 07 2020

PSCNet: Pyramidal Scale and Global Context Guided Network for Crowd Counting

Guangshuai Gao, Qingjie Liu, Qi Wen, Yunhong Wang

Crowd counting aims to accurately count the number of objects in an image. Challenges from severely occlusion, large scale variation, complex background interference and non-uniform density distribution, limit the crowd number estimation accuracy. This paper proposes avel crowd counting approach based on pyramidal scale module (PSM)

0
0
0
Abstract

Crowd counting, which towards to accurately count the number of the objects in images, has been attracted more and more attention by researchers recently. However, challenges from severely occlusion, large scale variation, complex background interference and non-uniform density distribution, limit the crowd number estimation accuracy. To mitigate above issues, this paper proposes a novel crowd counting approach based on pyramidal scale module (PSM) and global context module (GCM), dubbed PSCNet. Moreover, a reliable supervision manner combined Bayesian and counting loss (BCL) is utilized to learn the density probability and then computes the count exception at each annotation point. Specifically, PSM is used to adaptively capture multi-scale information, which can identify a fine boundary of crowds with different image scales. GCM is devised with low-complexity and lightweight manner, to make the interactive information across the channels of the feature maps more efficient, meanwhile guide the model to select more suitable scales generated from PSM. Furthermore, BL is leveraged to construct a credible density contribution probability supervision manner, which relieves non-uniform density distribution in crowds to a certain extent. Extensive experiments on four crowd counting datasets show the effectiveness and superiority of the proposed model. Additionally, some experiments extended on a remote sensing object counting (RSOC) dataset further validate the generalization ability of the model. Our resource code will be released upon the acceptance of this work.

Sun Oct 04 2020
Machine Learning
Multi-Resolution Fusion and Multi-scale Input Priors Based Crowd Counting
Crowd counting in still images is a challenging problem in practice due to huge crowd-density variations, large perspective changes, severe occlusion, and variable lighting conditions. The proposed approach outperforms all state-of-the-art models under the RMSE evaluation metric.
0
0
0
Mon Apr 26 2021
Computer Vision
Dense Point Prediction: A Simple Baseline for Crowd Counting and Localization
0
0
0
Sun Jul 30 2017
Computer Vision
CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting
Estimating crowd count in densely crowded scenes is an extremely challenging task due to non-uniform scale variations. In this paper, we propose a novel end-to-end cascaded network of CNNs to jointly learn crowd count classification and density map estimation.
0
0
0
Tue May 12 2020
Computer Vision
Adaptive Mixture Regression Network with Local Counting Map for Crowd Counting
The crowd counting task aims at estimating the number of people located in an image or a frame from videos. Existing methods widely adopt density maps as the training targets to optimize the point-to-point loss. The proposed method reports better performances on the typical datasets.
0
0
0
Wed Aug 07 2019
Computer Vision
Attend To Count: Crowd Counting with Adaptive Capacity Multi-scale CNNs
Crowd counting is a challenging task due to the large variations in crowd distributions. Previous methods tend to tackle the whole image with a single fixed structure. We propose the Adaptive Capacity Multi-scale convolutional neural networks (ACM-CNN)
0
0
0
Thu Jul 29 2021
Computer Vision
Cascaded Residual Density Network for Crowd Counting
Crowd counting is a challenging task due to scale and perspective variation. We propose a novel Cascaded Residual Density Network (CRDNet) to generate the high-quality density map for crowd counting.
6
0
0