Enhancing Zebra Crossing Safety with Edge- Enabled Deep Learning for Pedestrian Dynamics Prediction
Article Sidebar
Main Article Content
Abstract
Current static safety measures at zebra crossings often struggle to adapt to dynamic pedestrian-vehicle interactions in urban environments. This research proposes a novel approach utilizing edge computing and fusion-based deep learning models to enhance pedestrian safety. Our system leverages real-time data from multiple sensors (cameras, optional LiDAR or infrared) to predict pedestrian behavior and enable proactive interventions. These interventions can include dynamic signage, automated barriers, and traffic light integration. We evaluate the framework's effectiveness using real-world zebra crossing datasets, focusing on metrics like pedestrian behavior prediction accuracy. The proposed system aims to significantly reduce pedestrian accidents by bridging the gap between static measures and dynamic, predictive safety systems, ultimately promoting safer interactions between pedestrians and vehicles in urban areas.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
IJCERT Policy:
The published work presented in this paper is licensed under the Creative Commons Attribution 4.0 International (CC BY 4.0) license. This means that the content of this paper can be shared, copied, and redistributed in any medium or format, as long as the original author is properly attributed. Additionally, any derivative works based on this paper must also be licensed under the same terms. This licensing agreement allows for broad dissemination and use of the work while maintaining the author's rights and recognition.
By submitting this paper to IJCERT, the author(s) agree to these licensing terms and confirm that the work is original and does not infringe on any third-party copyright or intellectual property rights.
References
Ahuja, S., & Singh, P. (2019). A survey on edge computing: Issues, challenges, and opportunities. Journal of Network and Computer Applications, 132, 54-72.
Bell, R., & Emmerson, P. (2017). Deep learning architectures for predicting pedestrian behavior. IEEE Transactions on Intelligent Transportation Systems, 18(2), 315-324.
Chen, Z., He, Y., & Hu, L. (2020). Pedestrian trajectory prediction using LSTM networks. Pattern Recognition Letters, 129, 35-40.
Das, A., & Mohan, R. (2018). Real-time pedestrian detection with deep learning. Computer Vision and Image Understanding, 176, 89-96.
Ebrahimi, M., & Reinhardt, S. (2021). Fusion-based deep learning methods for multimodal pedestrian detection. Neurocomputing, 414, 235-245.
Fu, H., & Zhang, J. (2019). Edge computing in smart cities: Challenges and opportunities. IEEE Communications Magazine, 57(6), 16-23.
Gupta, A., & Varshney, A. (2020). Enhancing pedestrian safety through real-time analytics and machine learning. Transportation Research Part C: Emerging Technologies, 118, 102674.
Han, J., & Liu, Q. (2018). A comparative study on pedestrian detection using different deep learning frameworks. IEEE Access, 6, 59355-59368.
Jain, A., & Varma, R. (2020). Real-time pedestrian tracking using edge devices. Journal of Systems Architecture, 104, 101689.
Kim, H., & Park, Y. (2019). Pedestrian movement prediction using fusion-based CNN and RNN models. Sensors, 19(12), 2730.
Lee, S., & Kim, J. (2018). Deep learning approaches for pedestrian detection in urban environments. IEEE Transactions on Intelligent Vehicles, 3(1), 136-145.
Li, W., & Tang, Z. (2020). Edge computing for smart transportation: A survey. Future Internet, 12(3), 44.
Lin, Y., & Huang, C. (2019). Real-time pedestrian prediction using hybrid deep learning models. Journal of Artificial Intelligence Research, 65, 435-452.
Liu, X., & Wang, J. (2020). Advances in pedestrian detection and tracking in real-world environments. Pattern Recognition, 101, 107196.
Park, S., & Choi, Y. (2019). Pedestrian dynamics prediction using convolutional neural networks. Applied Sciences, 9(10), 2098.
Sharma, V., & Singh, R. (2021). The role of edge computing in enhancing urban mobility. IEEE Internet of Things Journal, 8(9), 7412-7421.
Sun, Y., & Xu, B. (2018). Real-time pedestrian detection with deep learning on edge devices. ACM Transactions on Intelligent Systems and Technology, 9(4), 36.
Tan, S., & Nguyen, H. (2019). Fusion-based deep learning for robust pedestrian detection. IEEE Sensors Journal, 19(20), 9618-9626.
Wang, F., & Zhang, Y. (2020). Edge computing frameworks for intelligent transportation systems. IEEE Network, 34(2), 188-193.
Zhou, X., & Li, H. (2018). A survey of pedestrian detection and tracking methods using deep learning. IEEE Transactions on Neural Networks and Learning Systems, 29(10), 4553-4571.