A Smart Crime Reporting Bot Using YOLO-Based Weapon Detection And RNN-Based Text Analysis
Keywords:
Crimes, Security systems, Image detection, Deep learning, RNN, YOLO, NLPAbstract
Home invasion crimes in South Korea, though relatively rare, still occur, particularly in urban areas like Seoul, where property crimes such as burglary and robbery are more prevalent. Despite low violent crime rates, the rise in property crimes has prompted many households to adopt advanced security systems, including CCTV cameras. The police respond quickly to such incidents, often using surveillance footage and data analysis, although the lack of physical evidence or witnesses can complicate investigations. This paper proposes a smart security system that combines YOLO for real-time weapon detection and RNN-family models (RNN, LSTM, GRU) for processing emergency messages. Evaluation results demonstrate the system's effectiveness in detecting weapons, tracking intruders, and generating timely reports, showcasing the potential of deep learning techniques to enhance home security. By integrating advanced object detection and message analysis, the proposed system offers a promising solution to improve response times and reduce the risks associated with home invasions.
References
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016). You only look once: Unified, real-time object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 779-788. https:// doi.org/10.1109/CVPR.2016.91
Hochreiter, S., & Schmidhuber, J. (1997). Long short- term memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
Cho, K., van Merriënboer, B., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning phrase
representations using RNN encoder-decoder for statistical machine translation. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP 2014), 1724-1734.
Zhang, Y., Zhao, Y., & Guo, Y. (2019). Real-time object detection with YOLOv3. Journal of Computer Science and Technology, 34(3), 633-642. https://doi.org/10.1007/ s11390-019-1941-x
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. Proceedings of the 2014 NIPS Workshop on Deep Learning and Representation Learning.
Li, X., & Lin, J. (2018). RNN for sequence learning and time-series prediction. Journal of Artificial Intelligence Research, 59(1), 1-22. https://doi.org/10.1613/jair.5720
Girshick, R. (2015). Fast R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV 2015), 1440-1448. https://doi.org/10.1109/ICCV.2015.169
Wu, Y., & He, K. (2016). Group normalization. Proceedings of the 2018 European Conference on Computer Vision (ECCV), 3-19.
Papernot, N., McDaniel, P., & Goodfellow, I. (2016). Transferability in machine learning: from phenomena to black-box attacks using adversarial examples. Proceedings of the 2016 IEEE European Symposium on Security and Privacy (EuroS&P), 32-46. https://doi.org/10.1109/ EuroSP.2016.29
Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015).
