AI-Powered Video Analysis for Objective Maritime Skills Evaluation and Performance Enhancement
DOI:
https://doi.org/10.55123/ijisit.v3i1.64Keywords:
Computer Vision, Automated Assessment, Maritime Training, Practical Skills Evaluation, Deep LearningAbstract
Maritime practical skills assessment relies on instructor subjective observation prone to 30-40% inter-rater reliability variance, creating fairness concerns and limiting detailed performance analytics essential for competency-based training. This research presents the design and validation of computer vision systems analyzing video recordings of maritime practical assessments to automatically evaluate student performance against STCW competency rubrics, identify safety violations, assess teamwork dynamics, and provide objective scoring reducing instructor subjectivity bias. Employing design science research methodology with qualitative stakeholder evaluation, the study engaged maritime skills instructors (n=14), assessment coordinators (n=6), and students (n=18) through structured interviews examining evaluation accuracy, fairness perceptions, and feedback utility. Deep learning computer vision models incorporating pose estimation, object detection, action recognition, and multi-person tracking achieved 82% agreement with expert human evaluators while generating detailed performance analytics impossible through manual observation including spatial positioning accuracy, procedure timing analysis, and team coordination metrics. Thematic analysis revealed strong support for AI-assisted assessment, identifying critical themes of evaluation objectivity, performance feedback detail, and instructor workload reduction. Pilot implementation with 340 practical assessments across mooring operations, firefighting, lifeboat drills, and bridge communication exercises demonstrated 91% student satisfaction with detailed feedback, 68% reduction in assessment administration time, and 89% standardized evaluation consistency, contributing validated computer vision architectures and empirical evidence supporting intelligent assessment automation in maritime vocational training contexts addressing subjectivity challenges and scalability constraints.
Downloads
References
[1] International Maritime Organization, STCW Including 2010 Manila Amendments. London, UK: IMO Publishing, 2017.
[2] A. Manuel and T. Baumler, "Digital transformation in maritime education," WMU Journal of Maritime Affairs, vol. 19, pp. 495-513, 2020.
[3] STIP Jakarta, Institutional Self-Evaluation Report 2024. Jakarta: STIP Jakarta, 2024.
[4] M. B. Simanjuntak, T. Handayani, and S. Soejatminah, "Multiliteracy pedagogy for maritime English," Journal of Maritime Education, vol. 12, no. 3, pp. 45-62, 2023.
[5] Ministry of Transportation Republic of Indonesia, Maritime Education Development Strategic Plan 2020-2030. Jakarta: Directorate General of Sea Transportation, 2020.
[6] A. R. Hevner, S. T. March, J. Park, and S. Ram, "Design science in information systems research," MIS Quarterly, vol. 28, no. 1, pp. 75-105, 2004.
[7] Z. Cao, G. Hidalgo, T. Simon, S. Wei, and Y. Sheikh, "OpenPose: Realtime multi-person 2D pose estimation," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 43, no. 1, pp. 172-186, 2021.
[8] J. Redmon et al., "You only look once: Unified, real-time object detection," in Proc. IEEE Conf. CVPR, Las Vegas, NV, 2016, pp. 779-788.
[9] D. Gašević, S. Dawson, and G. Siemens, "Let's not forget: Learning analytics are about learning," TechTrends, vol. 59, no. 1, pp. 64-71, 2015.
[10] J. W. Creswell and V. L. Plano Clark, Designing and Conducting Mixed Methods Research, 3rd ed. Thousand Oaks, CA: SAGE, 2018.
[11] C. Piech et al., "Deep knowledge tracing," in Proc. 28th Int. Conf. NeurIPS, Montreal, Canada, 2015, pp. 505-513.
[12] S. Dawson, D. Gašević, G. Siemens, and S. Joksimovic, "Current state and future trends," in Proc. 4th Int. Conf. LAK, Indianapolis, IN, 2014, pp. 231-240.
[13] M. Fullan, The New Meaning of Educational Change, 5th ed. New York: Teachers College Press, 2016.
[14] A. Pardo and G. Siemens, "Ethical and privacy principles for learning analytics," British Journal of Educational Technology, vol. 45, no. 3, pp. 438-450, 2014.
[15] J. Hattie and H. Timperley, "The power of feedback," Review of Educational Research, vol. 77, no. 1, pp. 81-112, 2007.
[16] K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning," in Proc. IEEE Conf. CVPR, Las Vegas, NV, 2016, pp. 770-778.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Winarno Winarno, Titis Ari Wibowo, Marihot Simanjuntak
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish their manuscripts in the International Journal of Computer Science and Information Technology agree to the following terms:
Copyright: Copyright on any article in the International Journal of Computer Science and Information Technology is fully retained by its authors under the Creative Commons Attribution-ShareAlike 4.0 International License / CC BY SA 4.0, with the following provisions:
- First Publication Right: Authors acknowledge that the International Journal of Computer Science and Information Technology has the right of first publication under the CC BY-SA 4.0 license.
- Non-Exclusive Distribution: Authors may enter the writing separately, arrange non-exclusive distribution of the published manuscript in this journal into other versions (e.g., submit to the author's institutional repository, publish in a book, etc.), acknowledging that the manuscript was first published in the International Journal of Computer Science and Information Technology.
- Reader's Rights: Readers are allowed to download, use, and adopt the contents of the article as long as they cite the article by mentioning the title, author, and the name of this journal. Such citations are made for the advancement of science and humanity and must not violate applicable laws.
