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{189872,
        author = {Guru Kiran C S and Darshan A J and Lakshmish K S and Gowtham D K and Mr Shreyan Jain},
        title = {AI-Based Traffic Police Gesture Recognition System},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {183-186},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189872},
        abstract = {Manual traffic control using hand gestures is still widely practiced in urban areas, especially during peak hours, emergencies, or signal malfunctions. Interpreting these gestures automatically is essential for intelligent transportation systems and autonomous vehicles. This project presents a real-time traffic police hand gesture recognition system developed using deep learning techniques. MediaPipe is employed to extract human pose and skeletal keypoints from live video streams, while a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) units analyzes temporal motion patterns for accurate gesture classification. The proposed system demonstrates reliable real-time performance with low latency and high recognition accuracy under varying environmental conditions. The results indicate that the system can effectively support intelligent traffic management and autonomous driving applications.},
        keywords = {Traffic Police Gesture Recognition, Computer Vision, MediaPipe, RNN, LSTM, Deep Learning, Intelligent Transportation Systems, Real-Time Processing.},
        month = {January},
        }