Real-time population density detection or crowd detection refers to the continuous monitoring and analysis of crowd sizes and distributions in a given area. This process involves capturing visual data through surveillance cameras or other imaging devices and processing this data to estimate the number of individuals present. Traditional methods, such as manual counting or using simple threshold-based techniques, of- ten fall short in terms of accuracy and scalability. Advanced approaches leverage machine learning algorithms, particularly convolutional neural networks (CNNs), to enhance detection accuracy and provide real-time insights. Visualization of crowd metrics is a crucial aspect of real-time population density management. Dashboards and graphical interfaces offer an intuitive way to monitor and analyse crowd behavior. Key metrics, such as crowd size and density maps, are displayed in real time, enabling prompt decision-making and response. The accuracy obtained through CSRNet is 0.9915 for a group of five images each with a total count of 20 images.