AI-Based Detection of Pilgrims Using Convolutional Neural Networks
📝 Original Paper Info
- Title: AI-based Pilgrim Detection using Convolutional Neural Networks- ArXiv ID: 1911.07509
- Date: 2020-02-20
- Authors: Marwa Ben Jabra, Adel Ammar, Anis Koubaa, Omar Cheikhrouhou, Habib Hamam
📝 Abstract
Pilgrimage represents the most important Islamic religious gathering in the world where millions of pilgrims visit the holy places of Makkah and Madinah to perform their rituals. The safety and security of pilgrims is the highest priority for the authorities. In Makkah, 5000 cameras are spread around the holy for monitoring pilgrims, but it is almost impossible to track all events by humans considering the huge number of images collected every second. To address this issue, we propose to use artificial intelligence technique based on deep learning and convolution neural networks to detect and identify Pilgrims and their features. For this purpose, we built a comprehensive dataset for the detection of pilgrims and their genders. Then, we develop two convolutional neural networks based on YOLOv3 and Faster-RCNN for the detection of Pilgrims. Experiments results show that Faster RCNN with Inception v2 feature extractor provides the best mean average precision over all classes of 51%.💡 Summary & Analysis
This paper focuses on developing an AI-based pilgrim detection system for the massive Hajj event in Makkah and Madinah using deep learning and convolutional neural networks (CNN). The goal is to automatically detect and identify pilgrims' locations and characteristics. Given that millions of pilgrims participate, ensuring their safety through real-time monitoring is crucial but impractical with human-operated cameras alone.To address this issue, the researchers developed a comprehensive dataset for detecting pilgrims and identifying their genders. Two CNN-based models, YOLOv3 and Faster-RCNN, were used to detect pilgrims in images collected from surveillance systems. The experiments demonstrated that Faster RCNN with Inception v2 feature extractor provided the best mean average precision of 51% across all classes.
This study highlights the potential for AI-driven solutions in managing large crowds and ensuring safety during events such as religious gatherings or public festivals, opening up new possibilities for real-time monitoring and security applications.
📄 Full Paper Content (ArXiv Source)
📊 논문 시각자료 (Figures)
