Detecting the exact location and density of crowds in crowded scenes is crucial for a variety of applications, such as crowd management, event planning, and public safety. In this paper, we propose a novel method to accurately determine the location and density of crowds in crowded scenes. Our proposed approach utilizes a combination of computer vision techniques, such as object detection and semantic segmentation, and deep learning-based methods to detect and classify the regions with high crowd density. The proposed method includes two main steps: crowd region detection and crowd density estimation. In the crowd region detection step, we use object detection and semantic segmentation algorithms to identify the regions with high crowd density. In the crowd density estimation step, we use a deep learning-based method to estimate the crowd density in each of the identified regions. The proposed method is evaluated on a challenging dataset, and the results demonstrate its effectiveness in accurately detecting the location and density of crowds in crowded scenes. The proposed method has the potential to be used in a variety of applications, such as crowd management, urban planning, and event management, among others