Loading...
Dr. R. Padmavathy is an Assistant Professor in the Department of Electronics and Communication Engineering at Dr. NGP Institute of Technology, Coimbatore, Tamil Nadu, India. Her areas of interest include Deep Learning, Image Processing, Wireless Communication, Computer Vision, and Intelligent Surveillance Systems.
The swift expansion of urban populations, extensive public assemblies, and smart city projects has heightened the demand for sophisticated crowd monitoring systems to guarantee public safety, security, and optimal resource management. Conventional crowd monitoring methods frequently encounter difficulties in managing dynamic and densely populated settings. Deep Learning (DL) has become a potent tool for intelligent crowd analysis, facilitating automated crowd detection, counting, density estimate, behaviour recognition, anomaly detection, and real-time monitoring. Utilising sophisticated models like Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM) networks, Vision Transformers (ViTs), and hybrid architectures, intelligent crowd monitoring systems can deliver precise and scalable insights from video streams and sensor data. This chapter examines the principles, techniques, architectures, applications, problems, and future trajectories of deep learning-based crowd surveillance systems, emphasising their significance in improving public safety and smart city management.