Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{172165,
        author = {Md Rayyan Jafri and Md Muqtesham Sumaid and Md Abu Sufiyan Alam},
        title = {Crowd Counting Using CNN: A Deep Learning Approach for Accurate Estimation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {2037-2041},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=172165},
        abstract = {Crowd counting is a critical task in computer vision, with applications spanning surveillance, crowd management, and urban planning. This mini project aims to develop an effective crowd counting method using convolutional neural networks (CNNs). CNNs are chosen for their ability to learn and capture complex spatial relationships within images, making them ideal for handling the varying densities and distributions of people in crowd scenes. In this project, the CNN-based model is trained on a dataset of annotated images with manually created ground truth density maps. The training process involves minimizing the mean squared error between the predicted and ground truth density maps through back-propagation. The proposed method is evaluated on several publicly available datasets, demonstrating competitive performance and achieving promising results compared to existing crowd counting techniques. This project highlights the potential of CNNs in accurately estimating crowd sizes, contributing to advancements in real-world applications.},
        keywords = {Crowd Counting, Convolutional Neural Networks, Deep Learning, Computer Vision, Image Processing},
        month = {January},
        }