Citation :

Kuhanraj Kandarsamy, Amirul Syafiq Sadun, Noor Hafizah Sulaiman, Muhammad Inam Abbasi, Suziana Ahmad, "Real-Time Automated Monitoring of Manual Process Efficiency in Production Line using Camera Vision Systems," International Journal of Engineering Trends and Technology (IJETT), vol. 74, no. 4, pp. 170-179, 2026. Crossref, https://doi.org/10.14445/22315381/IJETT-V74I4P113

Abstract

This research work presents a low-cost camera vision-based system for real-time monitoring of manual production processes. Traditional human inspection techniques are frequently inefficient, inconsistent, and time-consuming, and also possess limited effectiveness in modern manufacturing. To overcome these limitations, a real-time monitoring system is proposed using Python with integrated OpenCV, MediaPipe, and Tkinter based on a graphical interface. The proposed system uses a single RGB webcam to capture marker-less operator motion, trace assembly cycle time, and determine workflow efficiency without the requirement for hardware or wearable sensors. This system can automatically identify production bottlenecks and assess operator performance based on motion patterns, and provide real-time visual feedback to support immediate operator improvement in production efficiency, human error reduction, resource utilization improvement, and process traceability enhancement through data capture. The experimental results show that the proposed method provides high monitoring efficiency exceeding 90% for most test subjects with effective detection out of range occasions and workflow variations. The novelty of this work includes the integration of real-time human motion monitoring, efficiency assessment, and insightful visualization within a simple and affordable framework. Overall, this work establishes the potential of camera vision technology to support practical, accessible, and human-centered monitoring of manual production processes in modern manufacturing systems.

Keywords

Camera Vision Technology, Operational Efficiency, Real-Time Monitoring, OpenCV Python, Programming, System GUI.

References

[1] Daniel Osezua Aikhuele, and Faiz Mohd Turan, “Proposal for a Conceptual Model for Evaluating Lean Product Development Performance: A Study of LPD Enablers in Manufacturing Companies,” IOP Conference Series: Materials Science and Engineering, vol. 14, no. 1, pp. 1-5, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Nur Soliha Sahimi, Faiz Mohd Turan, and Kartina Johan, “Framework of Sustainability Assessment (FSA) Method for Manufacturing Industry in Malaysia,” IOP Conference Series: Materials Science and Engineering, vol. 342, no. 1, pp. 1-7, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Daniel Osezua Aikhuele, and Faiz Bin Mohd Turan, “An Improved Methodology for Multi-Criteria Evaluations in the Shipping Industry,” Brodogradnja: An International Journal of Naval Architecture and Ocean Engineering for Research and Development, vol. 67, no. 3, pp. 59-72, 2016.
[CrossRef] [Google Scholar] [Publisher Link]

[4] D.O. Aikhuele et al., “Interval-Valued Intuitionistic Fuzzy Topsis-based Model for Troubleshooting Marine Diesel Engine Auxiliary System,” The International Journal of Maritime Engineering, vol. 159, no. A1, pp. 107-114, 2017.
[CrossRef] [Google Scholar] [Publisher Link]

[5] Yi Bao et al., “A Detection Device for Quality Assessment of High-Speed Moving Filter Rods based on Machine Vision,” 2024 2^nd International Conference on Artificial Intelligence and Automation Control (AIAC), Guangzhou, China, pp. 254-258, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Semi-Automated Material Handling Systems 101, REB Storage Systems International, 2022. [Online], Available: https://rebstorage.com/articles-white-papers/semi-automated-material-handling-systems/  

[7] Doyun Lee, Guang-Yu Nie, and Kevin Han, “Vision-based Inspection of Prefabricated Components using Camera Poses: Addressing Inherent Limitations of Image- based 3D Reconstruction,” Journal of Building Engineering, vol. 64, pp. 1-32, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Ahmed Elhayek et al., “Efficient ConvNet-based Marker-Less Motion Capture in General Scenes with a Low Number of Cameras,” 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA, pp. 3810-3818, 2015.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Andrzej Sioma, “Vision System in Product Quality Control Systems,” Applied Sciences, vol. 13, no. 2, pp. 1-13, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Ufuk Dag, Vision Defect Detection Systems, Plugger.ai, 2022. [Online]. Available: https://www.plugger.ai/blog/vision-defect-detection-systems  

[11] Thomas Hellsten et al., “The Potential of Computer Vision-based Marker-Less Human Motion Analysis for Rehabilitation,” Advances in Rehabilitation Science and Practice, vol. 10, pp. 1-12, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[12] Marcello Urgo, Walter Terkaj, and Gabriele Simonetti, “Monitoring Manufacturing Systems using AI: A Method based on a Digital Factory Twin to Train CNNs on Synthetic Data,” CIRP Journal of Manufacturing Science and Technology, vol. 50, pp. 249-268, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Tobias Fuertjes et al., Data Monitoring and Management for Machine Tools, Twin-Control, Springer, Cham, pp. 123-136, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Jinwoo Kim, and Seokho Chi, “Multi-Camera Vision-based Productivity Monitoring of Earthmoving Operations,” Automation in Construction, vol. 112, pp. 1-14, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Yuan Gua, Yu Sun, Kai Wu, “Research and Development of Monitoring System and Data Monitoring System and Data Acquisition of CNC Machine Tool in Intelligent Manufacturing,” International Journal of Advanced Robotic Systems, vol. 17, no. 2, pp. 1-12, 2020.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Wenhao Yan et al., “A Review of Real-Time Fault Diagnosis Methods for Industrial Smart Manufacturing,” Processes, vol. 11, no. 2, pp. 1-23, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Andrew Walker, Daisuke Maeda, and Joydeep Acharya, “Lightweight Video Analytics for Cycle Time Detection in Manufacturing,” 2021 IEEE International Conference on Big Data (Big Data), Orlando, FL, USA, pp. 3615-3618, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[18] Maurizio Faccio et al., “Real-Time Assistance to Manual Assembly Through Depth Camera and Visual Feedback,” Procedia CIRP, vol. 81, pp. 1254-1259, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[19] Ismail Taifa, and Tosifbhai Vhora, “Cycle Time Reduction for Productivity Improvement in the Manufacturing Industry,” Journal of Industrial Engineering and Management Studies (JIEMS), vol. 6, no. 2, pp. 147-164, 2019.
[Google Scholar]

[20] Bi-Foua Tanguy Emmanuel Lorou et al., “Performance Improvement of Truck Assembly Line Through Modelling and Simulation using Arena Software,” Open Journal of Optimization, vol. 10, no. 3, pp. 88-100, 2021.
[CrossRef] [Google Scholar] [Publisher Link]