Plug-and-Play Rescaling Based Crowd Counting in Static Images

Sajid, Usman; Wang, Guanghui

doi:10.1109/wacv45572.2020.9093561

Cited by 19 publications

(35 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [56], Sajid et al proposed a plug-and-play-based patch rescaling module (PRM) to address the problem of crowd diversity in the scene. As shown in Figure 7, the PRM module takes a patch image as input and then rescales it using the appropriate scaler (Up-scaler or Down-scaler) according to its crowd density level, which is computed by the classifier before using PRM.…”

Section: Patch-based Inferencementioning

confidence: 99%

Advances in Convolution Neural Networks Based Crowd Counting and Density Estimation

Gouiaa

Akhloufi

Shahbazi

2021

BDCC

View full text Add to dashboard Cite

Automatically estimating the number of people in unconstrained scenes is a crucial yet challenging task in different real-world applications, including video surveillance, public safety, urban planning, and traffic monitoring. In addition, methods developed to estimate the number of people can be adapted and applied to related tasks in various fields, such as plant counting, vehicle counting, and cell microscopy. Many challenges and problems face crowd counting, including cluttered scenes, extreme occlusions, scale variation, and changes in camera perspective. Therefore, in the past few years, tremendous research efforts have been devoted to crowd counting, and numerous excellent techniques have been proposed. The significant progress in crowd counting methods in recent years is mostly attributed to advances in deep convolution neural networks (CNNs) as well as to public crowd counting datasets. In this work, we review the papers that have been published in the last decade and provide a comprehensive survey of the recent CNNs based crowd counting techniques. We briefly review detection-based, regression-based, and traditional density estimation based approaches. Then, we delve into detail regarding the deep learning based density estimation approaches and recently published datasets. In addition, we discuss the potential applications of crowd counting and in particular its applications using unmanned aerial vehicle (UAV) images.

show abstract

Section: Patch-based Inferencementioning

confidence: 99%

Advances in Convolution Neural Networks Based Crowd Counting and Density Estimation

Gouiaa

Akhloufi

Shahbazi

2021

BDCC

View full text Add to dashboard Cite

show abstract

“…Furthermore, to alleviate the effects of background objects for foreground crowd counting, foreground mask-based crowd counting networks [ 50 , 51 , 52 , 53 ] have been designed. Although the above methods achieved promising results, they rely on training data, and therefore their generalization ability is limited to new scenarios.…”

Section: Related Workmentioning

confidence: 99%

Congested Crowd Counting via Adaptive Multi-Scale Context Learning

Zhang

Zhao

Duan

et al. 2021

Sensors

View full text Add to dashboard Cite

In this paper, we propose a novel congested crowd counting network for crowd density estimation, i.e., the Adaptive Multi-scale Context Aggregation Network (MSCANet). MSCANet efficiently leverages the spatial context information to accomplish crowd density estimation in a complicated crowd scene. To achieve this, a multi-scale context learning block, called the Multi-scale Context Aggregation module (MSCA), is proposed to first extract different scale information and then adaptively aggregate it to capture the full scale of the crowd. Employing multiple MSCAs in a cascaded manner, the MSCANet can deeply utilize the spatial context information and modulate preliminary features into more distinguishing and scale-sensitive features, which are finally applied to a 1 × 1 convolution operation to obtain the crowd density results. Extensive experiments on three challenging crowd counting benchmarks showed that our model yielded compelling performance against the other state-of-the-art methods. To thoroughly prove the generality of MSCANet, we extend our method to two relevant tasks: crowd localization and remote sensing object counting. The extension experiment results also confirmed the effectiveness of MSCANet.

show abstract

“…These methods give unsatisfactory results in the high-density crowd scenarios. The DReg models [39,41,52,40,52] directly regress the crowd number using CNN-based structures. Wang et al [52] deployed the AlexNet [26] variant for direct crowd regression.…”

Section: Related Workmentioning

confidence: 99%

“…Wang et al [52] deployed the AlexNet [26] variant for direct crowd regression. Recently, Sajid et al designed two different types of direct-regression counting methods [41,40] that use the patch-rescaling module (PRM) and branch structure to deal with varying crowd levels. But these models fail to utilize the valuable density-map based computation.…”

Section: Related Workmentioning

confidence: 99%

“…It finds many applications in realworld scenarios, e.g., better management of crowd gatherings, safety and security, and circumventing any undesirable incident. Many deep learning-based image-only schemes [39,42,41,17,41,19,60,32] have been proposed to date, ranging from single and multi-branch networks [60,39,41], multi-regressors [42] based to trellis networks [19]. Although they show reasonable performance in regular images, they fail to generalize well in many practical scenarios such as low illumination and lighting conditions, noise, severe occlusion, and low-resolution images, where visual…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Audio-Visual Transformer Based Crowd Counting

Sajid

Chen

Sajid

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Crowd estimation is a very challenging problem. The most recent study tries to exploit auditory information to aid the visual models, however, the performance is limited due to the lack of an effective approach for feature extraction and integration. The paper proposes a new audiovisual multi-task network to address the critical challenges in crowd counting by effectively utilizing both visual and audio inputs for better modalities association and productive feature extraction. The proposed network introduces the notion of auxiliary and explicit image patch-importance ranking (PIR) and patch-wise crowd estimate (PCE) information to produce a third (run-time) modality. These modalities (audio, visual, run-time) undergo a transformer-inspired cross-modality co-attention mechanism to finally output the crowd estimate. To acquire rich visual features, we propose a multi-branch structure with transformer-style fusion in-between. Extensive experimental evaluations show that the proposed scheme outperforms the state-of-the-art networks under all evaluation settings with up to 33.8% improvement. We also analyze and compare the vision-only variant of our network and empirically demonstrate its superiority over previous approaches.

show abstract

Plug-and-Play Rescaling Based Crowd Counting in Static Images

Cited by 19 publications

References 32 publications

Advances in Convolution Neural Networks Based Crowd Counting and Density Estimation

Advances in Convolution Neural Networks Based Crowd Counting and Density Estimation

Congested Crowd Counting via Adaptive Multi-Scale Context Learning

Audio-Visual Transformer Based Crowd Counting

Contact Info

Product

Resources

About