A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation

@article{Sindagi2018ASO,
  title={A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation},
  author={Vishwanath A. Sindagi and Vishal M. Patel},
  journal={Pattern Recognit. Lett.},
  year={2018},
  volume={107},
  pages={3-16}
}
CNN-based Density Estimation and Crowd Counting: A Survey
TLDR
Over 220 works are surveyed to comprehensively and systematically study the crowd counting models, mainly CNN-based density map estimation methods to make reasonable inference and prediction for the future development of crowd counting and to provide feasible solutions for the problem of object counting in other fields.
An Empirical Evaluation of Cross-scene Crowd Counting Performance
TLDR
This work focuses on real-world, challenging application scenarios when no annotated crowd images from a given target scene are available, and evaluates the cross-scene effectiveness of several regression-based state-of-the-art crowd counting methods, including CNN-based ones, through extensive cross-data set experiments.
An Auto-adaptive CNN for Crowd Counting in Monitor Image
TLDR
An auto-adaptive deep convolutional neural network for crowd counting based on density is presented, and PlayGround Crowd Dataset, a new set of person annotations on top of the playground dataset is introduced.
Wide-Area Crowd Counting via Ground-Plane Density Maps and Multi-View Fusion CNNs
  • Qi Zhang, Antoni B. Chan
  • Computer Science
    2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
TLDR
A deep neural network framework for multi-view crowd counting, which fuses information from multiple camera views to predict a scene-level density map on the ground-plane of the 3D world is proposed.
A Deeply-Recursive Convolutional Network For Crowd Counting
TLDR
A deeply-recursive network (DR-ResNet) based on ResNet blocks for crowd counting that makes the network deeper while keeping the number of parameters unchanged, which enhances network capability to capture statistical regularities in the context of the crowd.
Crowd density estimation based on classification activation map and patch density level
TLDR
A network named Patch Scale Discriminant Regression Network (PSDR) and a person classification activation map (CAM) method, which provides person location information and guides the generation of the entire density map in the final stage, which performs better than state-of-the-art methods.
Video-Based Crowd Counting Using a Multi-scale Optical Flow Pyramid Network
TLDR
A novel architecture is proposed that exploits the spatiotemporal information captured in a video stream by combining an optical flow pyramid with an appearance-based CNN that can be formalized as the regression problem of learning a mapping from an input image to an output crowd density map.
Aggregated context network for crowd counting
  • Si-yue Yu, Jian Pu
  • Computer Science
    Frontiers of Information Technology & Electronic Engineering
  • 2020
TLDR
This work builds a fully convolutional network with two tasks, i.e., main density map estimation and auxiliary semantic segmentation, and demonstrates that the network has better accuracy of estimation and higher robustness on three challenging datasets compared with state-of-the-art methods.
...
...

References

SHOWING 1-10 OF 129 REFERENCES
Dense crowd counting from still images with convolutional neural networks
Fully Convolutional Crowd Counting on Highly Congested Scenes
TLDR
The state-of-the-art for crowd counting in high density scenes is advanced by further exploring the idea of a fully convolutional crowd counting model introduced by (Zhang et al., 2016), and a training set augmentation scheme that minimises redundancy among training samples to improve model generalisation and overall counting performance is developed.
Beyond Counting: Comparisons of Density Maps for Crowd Analysis Tasks—Counting, Detection, and Tracking
TLDR
Evaluating density maps generated by density estimation methods on a variety of crowd analysis tasks, including counting, detection, and tracking finds that the lower-resolution density maps sometimes have better counting performance, and proposes several metrics for measuring the quality of a density map.
CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting
TLDR
A novel end-to-end cascaded network of CNNs to jointly learn crowd count classification and density map estimation achieves lower count error and better quality density maps as compared to the recent state-of-the-art methods.
Single-Image Crowd Counting via Multi-Column Convolutional Neural Network
TLDR
With the proposed simple MCNN model, the method outperforms all existing methods and experiments show that the model, once trained on one dataset, can be readily transferred to a new dataset.
Crossing-Line Crowd Counting with Two-Phase Deep Neural Networks
TLDR
This paper proposes a deep Convolutional Neural Network for counting the number of people across a line-of-interest (LOI) in surveillance videos and shows that the proposed method is robust to variations of crowd density, crowd velocity, and directions of the LOI, and outperforms state- of-the-art LOI counting methods.
Recent survey on crowd density estimation and counting for visual surveillance
Deep People Counting in Extremely Dense Crowds
TLDR
This paper proposes an end-to-end deep convolutional neural networks (CNN) regression model for counting people of images in extremely dense crowds that achieves superior performance than the state-of-the-arts in term of the mean and variance of absolute difference.
Cross-scene crowd counting via deep convolutional neural networks
TLDR
A deep convolutional neural network is proposed for crowd counting, and it is trained alternatively with two related learning objectives, crowd density and crowd count, to obtain better local optimum for both objectives.
Switching Convolutional Neural Network for Crowd Counting
TLDR
A novel crowd counting model that maps a given crowd scene to its density and switch convolutional neural network that leverages variation of crowd density within an image to improve the accuracy and localization of the predicted crowd count is proposed.
...
...