This title appears in the Scientific Report :
2023
Please use the identifier:
http://hdl.handle.net/2128/33797 in citations.
Please use the identifier: http://dx.doi.org/10.1109/AICCSA56895.2022.10017883 in citations.
A Fast Hybrid Deep Neural Network Model for pushing behavior detection in human crowds
A Fast Hybrid Deep Neural Network Model for pushing behavior detection in human crowds
Deep learning technology is regarded as one of the latest advances in data science and analytics due to its learning abilities from the data. As a result, deep learning is widely applied in the human crowd analysis domain. Although it has achieved remarkable success in this area, a fast and robust m...
Saved in:
Personal Name(s): | Alia, Ahmed (Corresponding author) |
---|---|
Maree, Mohammed / Chraibi, Mohcine | |
Contributing Institute: |
Zivile Sicherheitsforschung; IAS-7 |
Imprint: |
IEEE
2023
|
Physical Description: |
1-2 |
DOI: |
10.1109/AICCSA56895.2022.10017883 |
Conference: | 2022 IEEE/ACS 19th International Conference on Computer Systems and Applications, Zayed University, Abu Dhabi (U Arab Emirates), 2022-12-05 - 2022-12-07 |
Document Type: |
Contribution to a conference proceedings |
Research Program: |
Pilotprojekt zur Entwicklung eines palästinensisch-deutschen Forschungs- und Promotionsprogramms 'Palestinian-German Science Bridge' Domain-Specific Simulation & Data Life Cycle Labs (SDLs) and Research Groups |
Link: |
Get full text OpenAccess |
Publikationsportal JuSER |
Please use the identifier: http://dx.doi.org/10.1109/AICCSA56895.2022.10017883 in citations.
Deep learning technology is regarded as one of the latest advances in data science and analytics due to its learning abilities from the data. As a result, deep learning is widely applied in the human crowd analysis domain. Although it has achieved remarkable success in this area, a fast and robust model for pushing behavior detection in the human crowd is unavailable. This paper proposes a model that allows crowd-monitoring systems to detect pushing behavior early, helping organizers make timely decisions before dangerous situations appear. This particularly becomes more challenging when applied to real-time video streams of crowded events, which the proposed model accomplishes with reasonable time latency. To achieve this, the model employs a hybrid deep neural network. |