Real-Time Machine State Monitoring via CCTV: A Comprehensive Approach
DOI:
https://doi.org/10.17010/ijcs/2024/v9/i3/174148Keywords:
CCTV
, Computer Vision, Machine Learning, Machine State Detection.Paper Submission Date
, April 10, 2024, Paper sent back for Revision, April 23, Paper Acceptance Date, April 26, Paper Published Online, June 5, 2024.Abstract
Monitoring industrial machinery helps to reduce downtime and raises production. Direct device engagement-based sensor systems are costly, sophisticated, risky for limited access. We investigate closed-circuit television, strong computer vision, and deep learning approaches for machine state identification. Strategic CCTV cameras are a non-intrusive, scalable, reasonably cost solution since they can detect machine states and operating status without physical interaction.
Motion detecting and CNNs help to improve video state recognition. This method reduces the need of large sensor networks by offering a complete visual background of machine activity for anomaly identification and failure prediction. Automated email alerts and real-time status video recording enable systems to be more manageable and responsive.
The study underlines the increasing importance of CCTV in monitoring as well as in visual feedback limits and cost control of IoT-based devices. Deep learning plus CCTV boosts machine state detection accuracy and efficiency according to tests displaying above 99% accuracy.
Highly strong industrial equipment monitoring based on real-time, non-intrusive CCTV condition monitoring is scalable. Using multimodal data to investigate enhanced deep learning models can help to increase system performance and predictive maintenance capacity.
Downloads
Published
How to Cite
Issue
Section
References
J. Tiwari, A. Deshmukh, G. Godepure, U. Kolekar, and K. Upadhyaya, "Real time traflBc management using Machine Learning," in 2020 Int. Conf. Emerging Trends Inf. Technol. Eng., Vellore, India, Feb. 2020, pp. 1-5, doi: 10.1109/ic-ETITE47903.2020.462.
J. H. Jeong, H. H. Jung,Y. H. Choi, S. H. Park, and M. S. Kim, "Intelligent complementary multi-modal fusion for anomaly surveillance and security system," Sensors, vol. 23, no. 22, p. 9214, Nov. 2023, doi: https://doi.org/10.3390/s23229214.
K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," in 2016 IEEE Conf. Comput. Vision Pattern Recognit., Las Vegas, NV, USA, 2016, pp. 770-778, doi: 10.1109/CVPR.2016.90.
M. Syafhidin, G. Alfian, N. L. Fitriyani, and J. Rhee, "Performance analysis of loT-based sensor. Big Data processing, and Machine Learning model for real-time monitoring system in automotive manufacturing," Sensors, vol. 18, no. 9, Art. no. 2946, 2018, doi: 10.3390/sl 8092946.
J. Xie, Y. Zheng, R. Du, W. Xiong, Y. Cao, Z. Ma, D. Cao, and J. Guo, "Deep learning-based computer vision for surveillance in ITS: Evaluation of state-of-the-art methods," IEEE Trans. Veh. Technol, vol. 70, no. 4, pp. 3027-3042 , Apr. 2021, doi: 10.1109/TVT.2021.3065250.
H. Zhang, C. Luo, and Q. Wang, "A novel infrared video surveillance system using deep learning based techniques," Multimedia Tools AppL, vol. 77, pp. 26657-26676,2018, doi: 10.1007/sll042-018-5883-y.
