Gender-based crowd-counting is a complex and important area of research thus appealing to a wider research community, which has notable applications in fields such as security surveillance, worship places, hotels etc. which is vital for the comprehension of demographics, public safety and city planning efficiently. This research incorporates an advanced deep learning algorithm YOLOv8 famous for its high accuracy and efficiency for object detection. The dataset was annotated considering various demographic factors, such as ethnic diversity and attire variations to have robustness and reliability in gender classification. The main purpose of the developed method is to improve how the crowd is analyzed commissioning advanced methods of computer vision aiming to improve the decision-making process in urban management, enhancing recourses allocation in event planning. The proposed method paves the way for more advanced crowd analysis techniques for practical scenarios.

Index Terms- Crowd Counting, Gender Classification