SPORTS ITEM DETECTION USING MOBILENETV2 WITH SINGLE SHOT DETECTOR
DOI:
https://doi.org/10.24191/mjoc.v8i2.22641Keywords:
Deep Learning, Machine Learning, MobilenetV2, Object Detection, Single Shot DetectorAbstract
Object detection can be applied in various situations and systems. In this research, object detection was specifically applied to build a lending system for tracking the details of sports items in a students' dormitory. The current sports item lending system with a manually recording of data was time consuming, and are more prone to human errors. This inspires the researcher to build a real-time object detection web-based sports item lending system. The system was trained using Single Shot Detector (SSD) with Mobilenet V2 technique to detect the sports item in the warehouse. A total of 960 self-collected sports item image data was applied in four different experiments with the same batch-size configuration and learning rate value of 0.02. From the experiments, several models with different number of training iterations and training data were built to find the best model to be implemented in the sports item lending system. The best model was obtained from the second experiment with a high accuracy of 0.93 mean average precision (mAP), a confidence of 97%, and a total loss of 0.28. For future work, it is recommended to increase the volume of training data, include other variations of objects in order to further improve the results, and apply other object detection techniques for comparison purposes.
References
Admin. (2017). The Cost of Human Error. https://www.gammasolutions.com/gammachat/cost-human-error/
Amin, P., S., A. B., Shetty, B. B., K., K., & Shetty, L. (2019). Object Detection using Machine Learning Technique. International Research Journal of Engineering and Technology (IRJET), 6(5), 4. https://irjet.org/volume-6-issue-05
ArcGIS. (n.d.). How single-shot detector (SSD) works?https://developers.arcgis.com/python/guide/how-ssd-works/
Barone, A. (2020, 19 August 2020). Lender. https://www.investopedia.com/terms/l/lender.asp
Bhavsar, P. (2019). Object Detection with Convolutional Neural Networks. https://medium.com/datadriveninvestor/object-detection-with-convolutional-neuralnetworks-dde190eb7180
Breitmeyer, R. (2015, 21 July 2015). What are the 7 disadvantages to a manual system ?https://www.linkedin.com/pulse/what-7-disadvantages-manual-system-richardbreitmeyer
Brick, B. (2018, 21 August 2018). The Disadvantages of a Manual Operating System in a Library. https://bizfluent.com/12746087/the-disadvantages-of-a-manual-operatingsystem-in-a-library.
Cheng, C., "Real-Time Mask Detection Based on SSD MobileNetV2," 2022 IEEE 5th International Conference on Automation, Electronics and Electrical Engineering (AUTEEE), Shenyang, China, 2022, pp. 761-767, doi: 10.1109/AUTEEE56487.2022.9994442.
Dhar, M., Jena, A. R., & Saha, P. (2023, September). Caption an object using the pre-trained deep learning model for single shot multi-box detector. In AIP Conference Proceedings (Vol. 2876, No. 1). AIP Publishing
Frankenfield, J. (2020). Artificial Neural Network (ANN).https://www.investopedia.com/terms/a/artificial-neural-networks-ann.asp
Gupta, N. D., Rajoo, R., & Jacob, P. J. (2023). Driver drowsiness detection system through facial expression using Convolutional Neural Networks (CNN). Malaysian Journal of Computing (MJoC), 8(1), 1375-1387.
Howard, A. G., Wang, W., Zhu, M., Weyand, T., Andreetto, M., Adam, H., Chen, B., & Kalenichenko, D. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications.
Hui, J. (2018). SSD object detection: Single Shot MultiBox Detector for real-time processing. Jonathan Hui.–URL: https://jonathan-hui.medium.com/ssd-objectdetection-single-shot-multibox-detector-for-real-time-processing-9bd8deac0e06 (date of application: 10.10. 2021).
Hutt, D. (2016). Man V machine : Overcoming human error in the workplace. https://southeastasiaglobe.com/human-error/
Khandelwal, R. (2019). SSD : Single Shot Detector for object detection using MultiBox. Towards data science. Retrieved 3/1/2021 from https://towardsdatascience.com/ssdsingle-shot-detector-for-object-detection-using-multibox-1818603644ca
Masurekar, O., Jadhav, O., Kulkarni, P., & Patil, S. (2020). Real Time Object Detection Using YOLOv3. International Research Journal of Engineering and Technology (IRJET), 7(3).
Naim, M. M. H., Amrin, R., Ali, M. R., Zubaer, A. A., & Islam, M. A. (2020). Object Detection from Images using Convolutional Neural Network based on Deep Learning. International Journal Of Engineering Research & Technology (IJERT), Volume 09(Issue 09).
Narayan, T. (2019). Object Detection : A Comparison of performance of Deep learning Models on Edge Using Intel Movidius Neural Compute Stick and Raspberry PI3. https://medium.com/intel-student-ambassadors/object-detection-a-comparison-ofperformance-of-deep-learning-models-on-edge-using-intel-f66eb7f45b17
Patel, A. (2020, 11 Jun 2020). What is Object Detection? https://medium.com/ml-researchlab/what-is-object-detection-51f9d872ece7
Peterson, D. (2018, November 2018). Maximize Efficiency: How Automation Can Improve Your Loan Origination Process. https://www.moodysanalytics.com/articles/2018/maximize-efficiency-how-automation-can-improve-your-loan-origination-process
Pokhrel, S. (2020). Real-Time Vehicle Detection with MobileNet SSD and Xailient. https://www.xailient.com/post/real-time-vehicle-detection-with-mobilenet-ssd-andxailient
Queensland Government. (2016, 29 June). Electronic and manual record keeping. https://www.business.qld.gov.au/running-business/finances-cashflow/records/electronic-manual
Redmon, J., & Farhadi, A. (2018). Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767.
Rosebrock, A. (2020). YOLO and Tiny-YOLO object detection on the Raspberry Pi and Movidius NCS.
Rouse, M. (2020). Machine Learning. https://searchenterpriseai.techtarget.com/definition/machine-learning-ML (SearchEnterpriseAI)
Söderholm, J. (2018). Borrowing and lending tools: The materiality of x-lending libraries (Doctoral dissertation, Högskolan i Borås).
Tonioni, A., Serra, E., & Di Stefano, L. (2018, December). A deep learning pipeline for product recognition on store shelves. In 2018 IEEE International Conference on Image Processing, Applications and Systems (IPAS) (pp. 25-31). IEEE.
Vaishali, S. S. (2019). Real-time object detection system using caffe model. Int Res J Eng Technol, 6(5), 5727-5732.
Younis, A., Shixin, L., Jn, S., & Hai, Z. (2020, January). Real time object detection using pretrained deep learning models MobileNet-SSD. In Proceedings of 2020 the 6th international conference on computing and data engineering (pp. 44-48).
Zhang, A., Lipton, Z. C., Li, M., & Smola, A. J. (2021). Dive into deep learning. arXiv preprint arXiv:2106.11342.
Benallal, M. A., & Tayeb, M. S. (2023). An image-based convolutional neural network system for road defects detection. IAES International Journal of Artificial Intelligence, 12(2), 577.
Chandankhede, P., Kumar, A. (2022). Guiding Aid For Visually Impaired. IJEM, 2(12), 34-40. https://doi.org/10.5815/ijem.2022.02.04
Deng, X., & Li, S. (2023, March). An Improved SSD Object Detection Algorithm Based on Attention Mechanism and Feature Fusion. In Journal of Physics: Conference Series (Vol. 2450, No. 1, p. 012088). IOP Publishing.
Qaddoura, R., M. Al-Zoubi, A., Faris, H., & Almomani, I. (2021). A multi-layer classification approach for intrusion detection in iot networks based on deep learning. Sensors, 21(9), 2987.
Roy, B., Nandy, S., Ghosh, D., Dutta, D., Biswas, P., & Das, T. (2020). MOXA: A deep learning based unmanned approach for real-time monitoring of people wearing medical masks. Transactions of the Indian National Academy of Engineering, 5, 509-518.
Susanto, S., Budiarjo, D. D., Hendrawan, A., & Pungkasanti, P. T. (2021). The implementation of intelligent systems in automating vehicle detection on the road. IAES International Journal of Artificial Intelligence, 10(3), 571.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Aiman Haziq Ab Yazik, Siti Nur Kamaliah Kamarudin, Yuzi Mahmud, Azliza Mohd Ali
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
