TY - GEN
T1 - Crowd counting Using DRL-based segmentation and RL-based density estimation
AU - Elharrouss, Omar
AU - Almaadeed, Noor
AU - Al-Maadeed, Somaya
AU - Abualsaud, Khalid
AU - Mohamed, Amr
AU - Khattab, Tamer
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - People counting is one of the computer vision tasks that can be useful for crowd management. In addition, estimating the crowdedness of a surveilled scene for crowd behavior analysis is one of the prominent challenges in video surveillance systems. With the introduction of deep learning, this operation has become doable with a convincing performance. However, this task still represents a challenge for these methods. In this regard, we propose a combination of deep reinforcement learning (DRL) networks and deep learning architecture for crowd counting. DRL network used the Context-Aware Attention (CAA) module for segmenting the crowd region, Then, on the segmented results, the crowd density estimation is performed using an encoder-decoder. The proposed method is evaluated and compared with and without the segmentation parts on the existing datasets including UCF-QNRF, UCF-CC-50, ShangaiTech-(A, B), while the obtained results in terms of MAE metric achieved 84,8, 179.2, 44.6, and 8.2 respectively.
AB - People counting is one of the computer vision tasks that can be useful for crowd management. In addition, estimating the crowdedness of a surveilled scene for crowd behavior analysis is one of the prominent challenges in video surveillance systems. With the introduction of deep learning, this operation has become doable with a convincing performance. However, this task still represents a challenge for these methods. In this regard, we propose a combination of deep reinforcement learning (DRL) networks and deep learning architecture for crowd counting. DRL network used the Context-Aware Attention (CAA) module for segmenting the crowd region, Then, on the segmented results, the crowd density estimation is performed using an encoder-decoder. The proposed method is evaluated and compared with and without the segmentation parts on the existing datasets including UCF-QNRF, UCF-CC-50, ShangaiTech-(A, B), while the obtained results in terms of MAE metric achieved 84,8, 179.2, 44.6, and 8.2 respectively.
UR - http://www.scopus.com/inward/record.url?scp=85143907715&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85143907715&partnerID=8YFLogxK
U2 - 10.1109/AVSS56176.2022.9959690
DO - 10.1109/AVSS56176.2022.9959690
M3 - Conference contribution
AN - SCOPUS:85143907715
T3 - AVSS 2022 - 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance
BT - AVSS 2022 - 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance, AVSS 2022
Y2 - 29 November 2022 through 2 December 2022
ER -