Efficient Crowd Counting via Structured Knowledge Transfer

Liu, Lingbo; Chen, Jiaqi; Wu, Hefeng; Chen, Tianshui; Li, Guanbin; Li, Lin

doi:10.1145/3394171.3413938

Cited by 47 publications

(42 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the performance of the proposed method on the proposed dataset as well as on the existing datasets, we compared the obtained results with the state-of-the-art methods while the code is available. The list of methods used in the comparison are: CSRNET [10], SPN [11], ASNet [49], MCNN [50], SANet [51], CANNet [25], SCAR [26], Mo-bileCount [23], SKT [21], and DENet [24]. The comparison is performed using quantitative and qualitative results of all methods including the results of the proposed FSCNet.…”

Section: Resultsmentioning

confidence: 99%

“…The use of these backbones can increase the computational cost, especially on large-scale datasets. In order to reduce the number of parameters and the size of a network, the authors in [21] proposed a lightweight generation network method named Structured Knowledge Transfer (SKT) using two modules: teacher module that used Intra-Layer Pattern Transfer and student exploited Inert-Layer Relation Transfer. In another research paper, the authors used MobileNetV2 backbone to reduce the FLOPs and implemented a Lightweight encoder-decoder crowd counting model [23].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

FSC-Set: Counting, Localization of Football Supporters Crowd in the Stadiums

et al. 2022

View full text Add to dashboard Cite

Counting the number of people in a crowd has gained attention in the last decade. Due to its benefit to many applications such as crowd behavior analysis, crowd management, and video surveillance systems, etc. Counting crowded scenes, like stadiums, represents a challenging task due to the inherent occlusions and density of the crowd inside and outside the stadiums. Finding a pattern to control thousands of people and counting them is a challenging task. With the introduction of Convolutional Neural Networks (CNN), enables performing this task with acceptable performance. The accuracy of a CNN-based method is related to the size of data used for training. The availability of the dataset is sparse. In particular, there is no dataset in the literature that can be used for training applications for crowd scene. This paper proposes two main contributions including a new dataset for crowd counting, and a CNN-based method for counting the number of people and generating the crowd density maps. The proposed dataset for Football Supporters Crowd (FSC-Set) is composed of 6000 annotated images (manually) of different types of scenes that contain thousands of people gathering in or around the stadiums. FSC-Set contains more than 1.5 Million individuals. The collected images are captured under varying Fields of Views (FOV), illuminations, resolutions, and scales. The proposed dataset can also be utilized for other applications, such as individual's localization and face detection as well as team recognition from supporter images. Further, we propose a CNN-based method named FSCNet for crowd counting exploiting context-aware attention, spatial-wise attention, and channel-wise attention modules. The proposed method is evaluated on our established FSC-Set and other existing datasets then compared to state-of-the-art methods. The obtained results show satisfactory performances on all the datasets. The dataset is made publicly available and can be requested using the following link: https://sites.google.com/view/fscrowd-dataset/ INDEX TERMS Crowd Counting, Football Supporters Crowd, Density map, Crowd management.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

FSC-Set: Counting, Localization of Football Supporters Crowd in the Stadiums

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Following [24,43,23], we adopt the Root Mean Square Error (RMSE) as an evaluation metric. Moreover, Grid Average Mean Absolute Error (GAME [11]) is utilized to evaluate the performance in different regions.…”

Section: Implementation Details and Evaluation Metricmentioning

confidence: 99%

Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting

Liu

Chen

et al. 2021

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

100

View full text Add to dashboard Cite

Crowd counting is a fundamental yet challenging problem, which desires rich information to generate pixel-wise crowd density maps. However, most previous methods only utilized the limited information of RGB images and may fail to discover the potential pedestrians in unconstrained environments. In this work, we find that incorporating optical and thermal information can greatly help to recognize pedestrians. To promote future researches in this field, we introduce a large-scale RGBT Crowd Counting (RGBT-CC) benchmark, which contains 2,030 pairs of RGB-thermal images with 138,389 annotated people. Furthermore, to facilitate the multimodal crowd counting, we propose a cross-modal collaborative representation learning framework, which consists of multiple modalityspecific branches, a modality-shared branch, and an Information Aggregation-Distribution Module (IADM) to fully capture the complementary information of different modalities. Specifically, our IADM incorporates two collaborative information transfer components to dynamically enhance the modality-shared and modality-specific representations with a dual information propagation mechanism. Extensive experiments conducted on the RGBT-CC benchmark demonstrate the effectiveness of our framework for RGBT crowd counting. Moreover, the proposed approach is universal for multimodal crowd counting and is also capable to achieve superior performance on the ShanghaiTechRGBD [21] dataset.

show abstract

“…In video processing, the temporal information is encoded to boost the counting performance [34]. Recently, researchers also pay attention to the light-weight counting models [35,36]. Apart from the density map estimation, there are many other counting approaches.…”

Section: A Counting Modelsmentioning

confidence: 99%

A Two-Path Network for Cell Counting

2021

IEEE Access

View full text Add to dashboard Cite

The density map is an effective manner to infer how many cells a cell image contains, and it carries valuable information. However, a fine-grained density map requires rich spatial information to recover the distribution details. In this paper, we propose a cell counting network with two paths, i.e. detail path and context path, which respectively extract spatial details and semantics. The detail path encodes the spatial information with small convolutional kernels. The context path rapidly enlarges the receptive field and extracts multi-scale features with an atrous spatial pyramid pooling. At the end of the two paths, we design a feature fusion module to merge the high-level feature maps from the two paths. To decrease the parameters and computation, we directly upsample the fused feature maps to the input size and decode them to obtain the density map. The proposed model is evaluated on three cell datasets and a popular crowd dataset Shanghaitech Part-B. The experiments illustrated that the proposed model not only achieves superior performance on cell datasets but also generalizes well on the crowd dataset.INDEX TERMS Cell counting, density map, bilateral path.

show abstract

Efficient Crowd Counting via Structured Knowledge Transfer

Cited by 47 publications

References 60 publications

FSC-Set: Counting, Localization of Football Supporters Crowd in the Stadiums

FSC-Set: Counting, Localization of Football Supporters Crowd in the Stadiums

Cross-Modal Collaborative Representation Learning and a Large-Scale RGBT Benchmark for Crowd Counting

A Two-Path Network for Cell Counting

Contact Info

Product

Resources

About