Copyright © 2026 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{171275,
        author = {B.S. Prakash and B. Tamilsudar and B. Ananthi},
        title = {AI – Enhanced Surveillance for Identifying and Recognizing Crowd    Behavior – A Survey},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {7},
        pages = {4088-4095},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=171275},
        abstract = {Deep learning techniques in AI-enhanced surveillance systems for identifying and recognizing crowd behavior. The paper reviews recent advancements in computer vision and neural network architectures, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformers, which are pivotal for tasks like crowd density estimation, activity recognition, and anomaly detection. Key topics include supervised and unsupervised learning approaches, transfer learning for domain adaptation, and multimodal data fusion for improving accuracy and robustness. The survey also highlights real-time processing capabilities enabled by advancements in hardware, such as GPUs and edge computing devices. Challenges such as data scarcity, model interpretability, and addressing biases in crowd behavior datasets are discussed. This survey aims to provide a detailed understanding of the field, supporting researchers and practitioners in the development of more effective and ethical crowd monitoring systems.},
        keywords = {Deep Learning, AI-enhanced Surveillance, Crowd Behavior Analysis, Anomaly Detection, Real-time Processing.},
        month = {January},
        }