CrowdNet: A Deep Convolutional Network for Dense Crowd Counting

By Lokesh Boominathan, Srinivas S. S. Kruthiventi, R. Venkatesh Babu. 2016

575 citations recorded by the source corpus.

Our work proposes a novel deep learning framework for estimating crowd density from static images of highly dense crowds. We use a combination of deep and shallow, fully convolutional networks to predict the density map for a given crowd image. Such a combination is used for effectively capturing both the high-level semantic information (face/body detectors) and the low-level features (blob detectors), that are necessary for crowd counting under large scale variations. As most crowd datasets have limited training samples (<100 images) and deep learning based approaches require large amounts of training data, we perform multi-scale data augmentation. Augmenting the training samples in such a manner helps in guiding the CNN to learn scale invariant representations. Our method is tested on the challenging UCF_CC_50 dataset, and shown to outperform the state of the art methods.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Domain Adaptation for Traffic Density Estimation (2021, background): “The first work that employed a pure CNN to estimate the density and count people in crowded contexts is presented by (Boominathan et al., 2016).”
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (2020, methodology): “Recent advances in CNNs have been exploited for the task of crowd counting and these methods [4, 5, 6, 7, 7, 22, 23, 52, 53, 54, 55, 56] have demonstrated significant improvements over the traditional methods.”
CNN-Based cascaded multi-task learning of high-level prior and density estimation for crowd counting (2017, background): “Inspired by the success of Convolutional Neural Networks (CNNs) for various computer vision tasks, many CNN-based methods have been developed to address the problem of crowd counting [2, 1, 31].”
Unsupervised vehicle counting via multiple camera domain adaptation (2020, unknown): “Concerning vehicle counting in urban spaces, where images are of very low resolution, and most objects are partially occluded, density-based methods have a clear advantage on detection methods [15, 6, 8, 3].”
Counting Out Time: Class Agnostic Video Repetition Counting in the Wild (2020, background): “Counting objects and people in images [3, 7, 24, 28, 49] is an active area in computer vision.”
Leveraging Unlabeled Data for Crowd Counting by Learning to Rank (2018, background): “The importance of multi-scale processing of crowd data was also noted in [2].”
A Survey of Recent Advances in CNN-based Single Image Crowd Counting and Density Estimation (2017, methodology): “…and counting, they however cover only traditional methods that use hand-crafted features and do not take into account the recent advancements driven primarily by CNN-based approaches [87, 39, 113, 11, 85, 97, 4, 98, 111, 107, 70, 88] and creation of new challenging crowd datasets [106, 107, 111].”
DecideNet: Counting Varying Density Crowds Through Attention Guided Detection and Density Estimation (2017, methodology): “Recent regression based works improve the performance with Convolutional Neural Network (CNN) [2, 28, 42, 21, 22] to output density maps of image patches.”
Crowd Counting and Density Estimation by Trellis Encoder-Decoder Networks (2019, methodology): “In scenes with severe occlusions and scale variations, CNN features are widely employed to enhance the feature encoding performance [53, 1, 27, 40, 2, 22].”
Scale Aggregation Network for Accurate and Efficient Crowd Counting (2018, background): “[31] combined shallow and deep networks for generating density map.”
CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes (2018, methodology): “In CrowdNet [19], the authors directly carve the ﬁrst 13 layers from VGG-16 and add a 1 × 1 convolutional layer as output layer.”
Attention Scaling for Crowd Counting (2020, methodology): “Recent years have witnessed progressive improvement in crowd counting from traditional methods [7, 10, 26, 39, 2] to CNN based methods [1, 24, 13, 14, 23, 29, 25].”
Learning Multi-Level Density Maps for Crowd Counting (2020, methodology): “Over the last few years, a variety of approaches have been proposed to tackle crowd counting problem in images and videos, including traditional methods [17]–[21] and CNN-based ones [12], [13], [15], [22]–[25].”
Switching Convolutional Neural Network for Crowd Counting (2017, methodology): “Transfer learning is employed by [2] using a VGG network employing dilated layers complemented by a shallow network with different receptive field and field of view.”
Crowd Counting via Adversarial Cross-Scale Consistency Pursuit (2018, background): “As discussed in Section 1, recent state-of-the-art meth-ods [34, 37, 3, 20, 25] dominantly choose L2 based loss function to regress crowd density map.”
Generating High-Quality Crowd Density Maps Using Contextual Pyramid CNNs (2017, background): “Boominathan et al . in [1] proposed to tackle the issue of scale variation using a combination of shallow and deep networks along with an extensive data augmentation by sampling patches from multi-scale image representations.”
Counting Vehicles with Cameras (2018, background): “Some works that use CNNs are [4] and [3] for crowd counting, and [12] for the vehicles counting task.”