Artificial Intelligence System for the Detection and Counting of Horizontal Spools in Carts using Object Detection
Keywords:
Artificial intelligence, Object detection, Machine Vision, YOLOv7Abstract
In an era where industrial manufacturing is increasingly embracing automation and artificial intelligence (AI) to enhance efficiency, accuracy and reduce labour dependency, one persistent challenge in textile factories is the manual counting of yarn tubes on carts which is a task that demands high precision but remains time-consuming and reliant on human workers. This research presents the design and development of an AI-powered system for counting yarn tubes on carts, tailored for industrial applications. The system utilises an Nvidia Jetson Nano board and YOLOv7 object detection algorithm to identify and count yarn tubes positioned both at a 45-degree angle and horizontally. The development process involved collecting image data, training the models and validating their performance. The model demonstrated a Precision of 99.99%, Recall of 99.99% and mAP@0.5 of 99.97%. The system achieved an F1-score of 100% for both 45-degree and horizontal yarn tubes. In real-world industrial testing, the model achieved an F1-score of 100% in all test cases. When comparing the performance of the AI system to that of human workers, the AI took only 505 millisecond per round to count, whereas human workers took an average of 4.28 seconds for angled tubes and 50.4 seconds for horizontal tubes.
References
Leng, J., Sha, W., Wang, B., Zheng, P., Zhuang, C., Liu, Q., Wuest, T., Mourtzis, D., & Wang, L. (2024). Unlocking the power of industrial artificial intelligence towards Industry 5.0: Insights, pathways, and challenges. Journal of Manufacturing Systems, vol. 73, pp. 349–363.
Sharma, M., Tomar, A., & Hazra, A. (2024). Edge computing for Industry 5.0: Fundamental, applications and research challenges. IEEE Internet of Things Journal, vol. 11(11), pp. 19070–19093.
Vyhmeister, E., and Castane, G. G. (2024, March). When Industry meets trustworthy AI: A systematic review of AI for Industry 5.0.
Martini, B., Bellisario, D., Coletti, P. (2024). Human-centered and sustainable artificial intelligence in Industry 5.0: Challenges and perspectives. Sustainability, vol. 16(13), pp. 1–24.
Wang, Z., and Yan, J. (2024). Deep learning–based assembly process action recognition and progress prediction facing human-centric intelligent manufacturing. Computers & Industrial Engineering, vol. 196, p. 109381.
Rame, I., Purwanto, P., & Sudarno, S. (2024). Industry 5.0 and sustainability: An overview of emerging trends and challenges for a green future. Innovation and Green Development. vol. 3(4), p. 100173.
Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y. M. (2025). WongKinYiu /yolov7: Implementation of paper – YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors [Computer software]. GitHub.
Singh, R., and Gill, S. S. (2023). Edge AI: A survey. Journal of Information Security and Applications, vol. 70, p. 103308.
Bin Rashid, A., and Kausik, M. A. K. (2024). AI revolutionizing industries worldwide: A comprehensive overview of its diverse applications. Hybrid Advances, vol. 7, p. 100277.
Fosso-Wamba, S., and Guthrie, C. (2024). Artificial intelligence and Industry 4.0 and 5.0: A bibliometric study and research agenda. Procedia Computer Science, vol. 235, pp. 718–725.
López-González, C. I., Gómez-Silva, M. J., Besada-Portas, E., Pajares, G. (2024). Analyzing and interpreting convolutional neural networks using latent space topology. Neurocomputing, vol. 593, p. 127713.
Lakshmi Narayana, C., & Venkata Ramana, K. (2023). An efficient real-time weed detection technique using YOLOv7. International Journal of Advanced Computer Science and Applications, vol. 14(2), pp. 550-556.
Hu, J., Fan, C., Wang, Z., Ruan, J., Wu, S. (2023). Fruit detection and counting in apple orchards based on improved YOLOv7 and multi-object tracking methods. Sensors, vol. 23(13), p. 5931.
Tang, X., Ruan, C., Li, X., Li, B., Fu, C. (2024). MSC-YOLO: Improved YOLOv7 based on multi-scale spatial context for small object detection in UAV-view. Computers, Materials & Continua, vol. 79(1), pp. 983–1003.
Anjomshoae, S., Omeiza, D., Jiang, L. (2021). Context-based image explanations for deep neural networks. Image and Vision Computing, vol. 116, p. 104337.
Rouf, A., Iwahori, Y., Wu, Q., Wu, H., Yu, X., Wang, A. (2023). Real-time vehicle detection, tracking and counting system based on YOLOv7. Embedded Self Organizing Systems, vol.10(7), pp. 4-8.
Wang, C.-Y., Bochkovskiy, A., & Liao, H.-Y. M. (2022). YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. arXiv.
Bello, A.-W., & Oladipo, M. A. (2024). Mask YOLOv7-based drone vision system for automated cattle detection and counting. Artificial Intelligence and Applications. vol. 2(2), pp. 115-125.
Li, Z., Zhu, Y., Sui, S., Zhao, Y., Liu, P., Li, X. (2024). Real-time detection and counting of wheat ears based on improved YOLOv7. Computers and Electronics in Agriculture, vol. 218, p. 108544.
Vamshi, M., Marupaka, N., Nallamothu, S. C., Naureen, A. (2023). A deep learning approach – Monkey detection using YOLOv7. In Proceedings of the 2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques (EASCT 2023). IEEE.
Chen, X., Li, Y., Zhang, Y., Wang, H., Liu, Z. (2023). An efficient method for monitoring birds based on object detection and multi-object tracking networks. Animals, vol. 13(10), p. 1713.
Yang, D., Miao, C., Liu, Y., Wang, Y., Zheng, Y. (2024). Improved foreign object tracking algorithm in coal for belt conveyor gangue selection robot with YOLOv7 and DeepSORT. Measurement, vol. 228, p. 114178.
Zhou, J., Yang, D., Song, T., Ye, Y., Zhang, X., & Song, Y. (2024). Improved YOLOv7 models based on modulated deformable convolution and Swin transformer for object detection in fisheye images. Image and Vision Computing, vol. 144, p. 104876.
Downloads
Published
How to Cite
Issue
Section
Categories
License
Copyright (c) 2026 Journal of Engineering and Innovative Research
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
