Crowd Flow Prediction for Irregular Regions with Semantic Graph Attention Network

Li, Fuxian; Yan, Huan; Jin, Depeng; Li, Yong

doi:10.1145/3501805

Cited by 11 publications

(5 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these methods fail to capture the complex temporal and spatial dependencies despite several feature engineering techniques. To cope with complex dependencies, deep learning methods including CNN (Song et al 2020), LSTM (Li et al 2019), and graph neural networks (GNNs) (Li et al 2022) have been proposed. Although multimodal data can be used for predicting crowds, a sufficient quantity of such datasets does not exist.…”

Section: Methods and State-of-the-artmentioning

confidence: 99%

See 1 more Smart Citation

Visual crowd analysis: Open research problems

Khan,

Menouar,

Hamila

2023

AI Magazine

View full text Add to dashboard Cite

Over the last decade, there has been a remarkable surge in interest in automated crowd monitoring within the computer vision community. Modern deep‐learning approaches have made it possible to develop fully automated vision‐based crowd‐monitoring applications. However, despite the magnitude of the issue at hand, the significant technological advancements, and the consistent interest of the research community, there are still numerous challenges that need to be overcome. In this article, we delve into six major areas of visual crowd analysis, emphasizing the key developments in each of these areas. We outline the crucial unresolved issues that must be tackled in future works, in order to ensure that the field of automated crowd monitoring continues to progress and thrive. Several surveys related to this topic have been conducted in the past. Nonetheless, this article thoroughly examines and presents a more intuitive categorization of works, while also depicting the latest breakthroughs within the field, incorporating more recent studies carried out within the last few years in a concise manner. By carefully choosing prominent works with significant contributions in terms of novelty or performance gains, this paper presents a more comprehensive exposition of advancements in the current state‐of‐the‐art.

show abstract

Section: Methods and State-of-the-artmentioning

confidence: 99%

“…2019), and graph neural networks (GNNs) (Li et al. 2022) have been proposed. Although multimodal data can be used for predicting crowds, a sufficient quantity of such datasets does not exist.…”

Section: Crowd Predictionmentioning

confidence: 99%

Visual crowd analysis: Open research problems

Khan,

Menouar,

Hamila

2023

AI Magazine

View full text Add to dashboard Cite

show abstract

“…Using CNN in image processing allows features to be extracted automatically and avoids the use of manually designed input features [18]. The input data for the CNN is typically structured in the form of a grid with multiple channels, allowing for the preservation of strong spatial dependencies within local grid are [19]. The convolution layer plays a crucial role in extracting discriminative features from the input data by applying learned weights to connectors.…”

Section: Methods 21 Convolutional Neural Networkmentioning

confidence: 99%

Footprint biometric authentication using SqueezeNet

Safie

Ramli

2023

IJEECS

View full text Add to dashboard Cite

Biometric authentication is a process of identity verification once an identity is claimed by an individual. It uses unique features on the human body. Footprints are a new biometric feature that has sparked interest among researchers, as this feature is universal, easy to extract and has not changed throughout time. The focus of researchers in this field is to improve the recognition rate. Various techniques have been developed for this purpose, but the accuracy percentage is at 98% with an equal error rate (EER) of 6.1%. This paper proposes the use of a new technique called SqueezeNet in classifying footprint images. SqueezeNet belongs to the convolutional neural network (CNN) family. In this study, 300 footprint images were used from 15 individuals. The 70% of these images were used to train the proposed SqueezeNet network, while the rest were used for testing. At the end of this simulation, SqueezeNet has achieved an accuracy of 98.67% with an EER of 2.1%.

show abstract

“…For example, ref. [11] proposed a crowd flow prediction model for irregular regions. This method not only extracts hierarchical spatial-temporal correlation, but also captures dynamic and semantic information among the regions.…”

Section: Related Workmentioning

confidence: 99%

Deep Convolutional Neural Network for Indoor Regional Crowd Flow Prediction

Teng,

Sun,

Song

et al. 2023

Electronics

View full text Add to dashboard Cite

Crowd flow prediction plays a vital role in modern city management and public safety prewarning. However, the existing approaches related to this topic mostly focus on single sites or road segments, and indoor regional crowd flow prediction has yet to receive sufficient academic attention. Therefore, this paper proposes a novel prediction model, named the spatial–temporal attention-based crowd flow prediction network (STA-CFPNet), to forecast the indoor regional crowd flow volume. The model has four branches of temporal closeness, periodicity, tendency and external factors. Each branch of this model takes a convolutional neural network (CNN) as its principal component, which computes spatial correlations from near to distant areas by stacking multiple CNN layers. By incorporating the output of the four branches into the model’s fusion layer, it is possible to utilize ensemble learning to mine the temporal dependence implicit within the data. In order to improve both the convergence speed and prediction performance of the model, a building block based on spatial–temporal attention mechanisms was designed. Furthermore, a fully convolutional structure was applied to the external factors branch to provide globally shared external factors contexts for the research area. The empirical study demonstrates that STA-CFPNet outperforms other well-known crowd flow prediction methods in processing the experimental datasets.

show abstract

Crowd Flow Prediction for Irregular Regions with Semantic Graph Attention Network

Cited by 11 publications

References 18 publications

Visual crowd analysis: Open research problems

Visual crowd analysis: Open research problems

Footprint biometric authentication using SqueezeNet

Deep Convolutional Neural Network for Indoor Regional Crowd Flow Prediction

Contact Info

Product

Resources

About