Crowd counting Using DRL-based segmentation and RL-based density estimation
Author | Elharrouss, Omar |
Author | Almaadeed, Noor |
Author | Al-Maadeed, Somaya |
Author | Abualsaud, Khalid |
Author | Mohamed, Amr |
Author | Khattab, Tamer |
Available date | 2023-02-23T09:13:03Z |
Publication Date | 2022 |
Publication Name | AVSS 2022 - 18th IEEE International Conference on Advanced Video and Signal-Based Surveillance |
Resource | Scopus |
Abstract | 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. |
Sponsor | This research work was made possible by research grant support (QUEX-CENG-SCDL-19/20-1 ) from Supreme Committee for Delivery and Legacy (SC) in Qatar. |
Language | en |
Publisher | Institute of Electrical and Electronics Engineers Inc. |
Subject | Computer vision deep reinforcement learning (DRL) Crowd managements Density estimation Deep Q-network (DQN) Learning-based segmentation |
Type | Conference Paper |
Pagination | - |
Files in this item
Files | Size | Format | View |
---|---|---|---|
There are no files associated with this item. |
This item appears in the following Collection(s)
-
Computer Science & Engineering [2284 items ]