Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN

@article{Sam2018DivideAG,
  title={Divide and Grow: Capturing Huge Diversity in Crowd Images with Incrementally Growing CNN},
  author={Deepak Babu Sam and Neeraj N. Sajjan and R. Venkatesh Babu},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={3618-3626}
}
Automated counting of people in crowd images is a challenging task. The major difficulty stems from the large diversity in the way people appear in crowds. In fact, features available for crowd discrimination largely depend on the crowd density to the extent that people are only seen as blobs in a highly dense scene. We tackle this problem with a growing CNN which can progressively increase its capacity to account for the wide variability seen in crowd scenes. Our model starts from a base CNN… 

Figures and Tables from this paper

Learning Multi-Level Density Maps for Crowd Counting
TLDR
An effective multi-level convolutional neural network (MLCNN) architecture that first adaptively learnsMulti-level density maps and then fuses them to predict the final output to tackle the large variation in people size is proposed.
Crowd counting with crowd attention convolutional neural network
Almost Unsupervised Learning for Dense Crowd Counting
TLDR
Grid Winner-Take-All (GWTA) autoencoder is developed to learn several layers of useful filters from unlabeled crowd images to achieve superior results compared to other unsupervised methods and stays reasonably close to the accuracy of supervised baseline.
Locate, Size, and Count: Accurately Resolving People in Dense Crowds via Detection
TLDR
This work introduces a detection framework for dense crowd counting and eliminates the need for the prevalent density regression paradigm, and shows that LSC-CNN not only has superior localization than existing density regressors, but outperforms in counting as well.
Boosting Crowd Counting with Transformers
TLDR
A pure transformer is used to extract features with global information from overlapping image patches to predict the total person count of the image through regression-token module (RTM) and proposes a tokenattention module (TAM) to recalibrate encoded features through channel-wise attention informed by the context token.
Learning From Synthetic Data for Crowd Counting in the Wild
TLDR
A data collector and labeler is developed which can generate the synthetic crowd scenes and simultaneously annotate them without any manpower, and a crowd counting method via domain adaptation is proposed, which can free humans from heavy data annotations.
Multi-Scale Attention Network for Crowd Counting
TLDR
A novel multi-branch scale-aware attention network is proposed that exploits the hierarchical structure of convolutional neural networks and generates, in a single forward pass, multi-scale density predictions from different layers of the architecture.
HADF-Crowd: A Hierarchical Attention-Based Dense Feature Extraction Network for Single-Image Crowd Counting
TLDR
A CNN-based dense feature extraction network for accurate crowd counting is proposed and to exploit the class-specific response between background and foreground, CAM is incorporated at the end to obtain high-level features along channel dimensions for better counting accuracy.
Crowd Counting with Spatial Normalization Network
  • Pengcheng Xia, Dapeng Zhang
  • Computer Science
    2020 IEEE 16th International Conference on Automation Science and Engineering (CASE)
  • 2020
TLDR
A novel framework named Spatial Normalization Network (SNNet), which normalizes multi-scale features from parallel subnetworks to a particular scale and then fuse them to acquire rich spatial information for final accurate density map predictions and a novel normalization layer called Spatial Group Normalization (SGN), which firstly split feature maps along the spatial dimension and then perform group-wise normalization.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 26 REFERENCES
Top-Down Feedback for Crowd Counting Convolutional Neural Network
TLDR
This work proposes top-down feedback to correct the initial prediction of the CNN for crowd counting and evaluates the performance of the model on all major crowd datasets and shows the effectiveness of top- down feedback.
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.
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.
CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
TLDR
This work uses a combination of deep and shallow, fully convolutional networks to predict the density map for a given crowd image, and shows that this combination is used for effectively capturing both the high-level semantic information and the low-level features, necessary for crowd counting under large scale variations.
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.
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.
Network of Experts for Large-Scale Image Categorization
TLDR
A tree-structured network architecture for large-scale image classification that can be built from any existing convolutional neural network (CNN) and demonstrates its generality by adapting 4 popular CNNs for image categorization into the form of networks of experts.
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.
Towards Perspective-Free Object Counting with Deep Learning
TLDR
A novel convolutional neural network solution, named Counting CNN (CCNN), formulated as a regression model where the network learns how to map the appearance of the image patches to their corresponding object density maps, able to estimate object densities in different very crowded scenarios.
Multi-source Multi-scale Counting in Extremely Dense Crowd Images
TLDR
This work relies on multiple sources such as low confidence head detections, repetition of texture elements, and frequency-domain analysis to estimate counts, along with confidence associated with observing individuals, in an image region, and employs a global consistency constraint on counts using Markov Random Field.
...
1
2
3
...