A Comparative Analysis of the Usability of Consumer Graphics Cards for Deep Learning in the Aspects of Inland Navigational Signs Detection for Vision Systems
Source abstract
Abstract
Consumer-grade graphics processing units (GPUs) offer a potentially affordable and energy-efficient alternative to enterprise-class hardware for real-time image processing tasks, but systematic multi-criteria analyses of their suitability remain rare. This article fills that gap by evaluating the performance, power consumption, and cost-effectiveness of GPUs from three leading vendors, AMD, Intel, and Nvidia, in an inland water transport (ITW) context. The main objective is to assess the feasibility of using consumer GPUs for deep learning tasks involving navigational sign detection, a critical component for ensuring safe and efficient inland transportation. The evaluation includes the use of image datasets of inland water transport signs processed by widely used detector and classifier models such as YOLO (you only look once), ResNet (residual neural network l), and MobileNet. To achieve this, we propose a multi-criteria framework based on a weighted scoring method (WSM), covering 21 different characteristics such as compatibility, resting power, energy efficiency in learning and inference, and the financial threshold for technology adoption. The results confirm that consumer-grade GPUs can deliver competitive performance with lower initial costs and lower power consumption. The findings underscore the enduring value of our analysis, as its framework can be adapted for ongoing comparisons of evolving GPU technologies using the proposed methodology.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Maritime Navigation and Safety · IoT and GPS-based Vehicle Safety Systems · Advanced Neural Network Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Maritime University of Szczecin, Faculty of Navigation, Waly Chrobrego 1-2, 70-500 Szczecin, Poland
Funding
Maritime University of Szczecin
References (78)
Show source-provided references
1. ST-Seq2Seq: A Spatio-Temporal Feature-Optimized Seq2Seq Model for Short-Term Vessel Trajectory Prediction10.1109/ACCESS.2020.3041762 ↗
2. Deep Learning-Based Vehicle Behavior Prediction for Autonomous Driving Applications: A Review10.1109/TITS.2020.3012034 ↗
3. Azimi, S., Salokannel, J., Lafond, S., Lilius, J., Salokorpi, M., and Porres, I. (2025, February 12). A Survey of Machine Learning Approaches for Surface Maritime Navigation. Available online: http://hdl.handle.net/2117/329714.
4. Donandt, K., Böttger, K., and Söffker, D. (2022, January 8–12). Short-Term Inland Vessel Trajectory Prediction with Encoder-Decoder Models. Proceedings of the 2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC), Macau, China.10.1109/ITSC55140.2022.9922148 ↗
5. Agorku, G., Hernandez, S., Falquez, M., Poddar, S., and Amankwah-Nkyi, K. (2024). Traffic Cameras to Detect Inland Waterway Barge Traffic: An Application of Machine Learning, Computer Vision and Pattern Recognition. arXiv.
6. Vessel-Following Model for Inland Waterways Based on Deep Reinforcement Learning10.1016/j.oceaneng.2023.114679 ↗
7. Vanneste, A., Vanneste, S., Vasseur, O., Janssens, R., Billast, M., Anwar, A., Mets, K., De Schepper, T., Mercelis, S., and Hellinckx, P. (2022, January 17–20). Safety Aware Autonomous Path Planning Using Model Predictive Reinforcement Learning for Inland Waterways. Proceedings of the IECON 2022–48th Annual Conference of the IEEE Industrial Electronics Society, Brussels, Belgium.10.1109/IECON49645.2022.9968678 ↗
8. Survey of Deep Learning for Autonomous Surface Vehicles in Marine Environments10.1109/TITS.2023.3235911 ↗
9. SIGNI (2018). European Code for Signs and Signals on Inland Waterways: Resolution No. 90, United Nations.
10. Shipping Safety Management on Polish Inland Waterways
11. Vessel-Bridge Collisions: Accidents, Analysis, and Protection
12. Agorku, G., Hernandez, S., Falquez, M., Poddar, S., and Amankwah-Nkyi, K. (2024). Real-Time Barge Detection Using Traffic Cameras and Deep Learning on Inland Waterways. Transp. Res. Rec.10.1177/03611981241263574 ↗
13. Automatic Watercraft Recognition and Identification on Water Areas Covered by Video Monitoring as Extension for Sea and River Traffic Supervision Systems10.2478/pomr-2018-0016 ↗
14. Restrepo-Arias, J.F., Branch-Bedoya, J.W., Zapata-Cortes, J.A., Paipa-Sanabria, E.G., and Garnica-López, M.A. (2022). Industry 4.0 Technologies Applied to Inland Waterway Transport: Systematic Literature Review. Sensors, 22.10.3390/s22103708 ↗
15. Wawrzyniak, N., Hyla, T., and Popik, A. (2019). Vessel Detection and Tracking Method Based on Video Surveillance. Sensors, 19.10.3390/s19235230 ↗
16. Liu, X., Hu, Y., Ji, H., Zhang, M., and Yu, Q. (2023). A Deep Learning Method for Ship Detection and Traffic Monitoring in an Offshore Wind Farm Area. J. Mar. Sci. Eng., 11.10.20944/preprints202304.0401.v1 ↗
17. Li, J., Sun, J., Li, X., Yang, Y., Jiang, X., and Li, R. (2023). LFLD-CLbased NET: A Curriculum-Learning-Based Deep Learning Network with Leap-Forward-Learning-Decay for Ship Detection. J. Mar. Sci. Eng., 11.10.3390/jmse11071388 ↗
18. Ship Recognition and Tracking System for Intelligent Ship Based on Deep Learning Framework
19. Shi, K., He, S., Shi, Z., Chen, A., Xiong, Z., Chen, J., and Luo, J. (2024). Radar and Camera Fusion for Object Detection and Tracking: A Comprehensive Survey. arXiv.
20. Wei, P., Cagle, L., Reza, T., Ball, J., and Gafford, J. (2018). LiDAR and Camera Detection Fusion in a Real-Time Industrial Multi-Sensor Collision Avoidance System. Electronics, 7.10.3390/electronics7060084 ↗
21. Hoehner, F., Langenohl, V., Akyol, S., el Moctar, O., and Schellin, T.E. (2024). Object Detection and Tracking in Maritime Environments in Case of Person-Overboard Scenarios: An Overview. J. Mar. Sci. Eng., 12.10.3390/jmse12112038 ↗
22. Comparison of Algorithms for the Detection of Marine Vessels with Machine Vision
23. Heller, D., Rizk, M., Douguet, R., Baghdadi, A., and Diguet, J.-P. (2022, January 13). Marine Objects Detection Using Deep Learning on Embedded Edge Devices. Proceedings of the RSP 2022, Shanghai, China.10.1109/RSP57251.2022.10039025 ↗
24. Folarin, A., Munin-Doce, A., Ferreno-Gonzalez, S., Ciriano-Palacios, J.M., and Diaz-Casas, V. (2024). Real Time Vessel Detection Model Using Deep Learning Algorithms for Controlling a Barrier System. J. Mar. Sci. Eng., 12.10.3390/jmse12081363 ↗
25. Integration of Stereo Vision and MOOS-IvP for Enhanced Obstacle Detection and Navigation in Unmanned Surface Vehicles10.1109/ACCESS.2023.3332032 ↗
26. Hao, G., Xiao, W., Huang, L., Chen, J., Zhang, K., and Chen, Y. (2024). The Analysis of Intelligent Functions Required for Inland Ships. J. Mar. Sci. Eng., 12.10.3390/jmse12050836 ↗
27. Li, Y., Hu, Y., Rigo, P., Lefler, F.E., and Zhao, G. (2023). Proceedings of PIANC Smart Rivers 2022: Green Waterways and Sustainable Navigations, Lecture Notes in Civil Engineering; Springer.10.1007/978-981-19-6138-0 ↗
28. Hammedi, W. (2022). Smart River: Towards Efficient Cooperative Autonomous Inland Navigation. [Ph.D. Thesis, Université Bourgogne Franche-Comté]. Available online: https://theses.hal.science/tel-03614827.
29. Review of Deep Learning: Concepts, CNN Architectures, Challenges, Applications, Future Directions10.1186/s40537-021-00444-8 ↗
30. Sharma, O. (2019, January 14–16). Deep Challenges Associated with Deep Learning. Proceedings of the International Conference on Machine Learning, Big Data, Cloud and Parallel Computing: Trends, Perspectives and Prospects (COMITCon 2019), Faridabad, India.10.1109/COMITCon.2019.8862453 ↗
31. Tsimenidis, S. (2020). Limitations of Deep Neural Networks: A Discussion of G. Marcus’ Critical Appraisal of Deep Learning. arXiv.
32. Nia, V.P., Zhang, G., Kobyzev, I., Metel, M.R., Li, X., Sun, K., Hemati, S., Asgharian, M., Kong, L., and Liu, W. (2023). Mathematical Challenges in Deep Learning. arXiv, Available online: http://arxiv.org/abs/2303.15464.
33. Patterson, D.A., and Hennessy, J.L. (2012). Computer Architecture: A Quantitative Approach, Morgan Kaufmann. [5th ed.].
34. GPU Computing10.1109/JPROC.2008.917757 ↗
35. McClure, N. (2017). TensorFlow Machine Learning Cookbook, Packt Publishing.
36. Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., and Isard, M. (2016). TensorFlow: A System for Large-Scale Machine Learning. arXiv.
37. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., and Antiga, L. (2019). PyTorch: An Imperative Style, High-Performance Deep Learning Library. arXiv.
38. Manakitsa, N., Maraslidis, G.S., Moysis, L., and Fragulis, G.F. (2024). A Review of Machine Learning and Deep Learning for Object Detection, Semantic Segmentation, and Human Action Recognition in Machine and Robotic Vision. Technologies, 12.10.3390/technologies12020015 ↗
39. Benchmark Analysis of Representative Deep Neural Network Architectures10.1109/ACCESS.2018.2877890 ↗
40. Shi, S., Wang, Q., and Chu, X. (2016). Performance Modeling and Evaluation of Distributed Deep Learning Frameworks on GPUs. arXiv.
41. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
42. Ren, Y., Yoo, S., and Hoisie, A. (2019, January 18). Performance Analysis of Deep Learning Workloads on Leading-edge Systems. Proceedings of the 2019 IEEE/ACM Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS), Denver, CO, USA.10.1109/PMBS49563.2019.00017 ↗
43. Markidis, S., Chien, S.W.D., Laure, E., Peng, I.B., and Vetter, J.S. (2018, January 21–25). NVIDIA Tensor Core Programmability. Proceedings of the 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), Vancouver, BC, Canada.
44. Otterness, N., and Anderson, J.H. (2025, January 12). AMD GPUs as an Alternative to NVIDIA for Supporting Real-Time Workloads. Leibniz Int. Proc. Inform., Available online: https://www.cs.unc.edu/~anderson/papers/ecrts20a.pdf.
45. You, Y., Zhang, Z., Hsieh, C.-J., Demmel, J., and Keutzer, K. (2018, January 13–16). ImageNet Training in Minutes. Proceedings of the 47th International Conference on Parallel Processing (ICPP), Eugene, OR, USA.10.1145/3225058.3225069 ↗
46. Gyawali, D. (2023). Comparative Analysis of CPU and GPU Profiling for Deep Learning Models. arXiv.
47. A Comparative Study of GPU Programming Models and Architectures Using Neural Networks10.1007/s11227-011-0631-3 ↗
48. Jadhav, A., and Sonar, R. (2009, January 16–18). Analytic Hierarchy Process (AHP), Weighted Scoring Method (WSM), and Hybrid Knowledge Based System (HKBS) for Software Selection: A Comparative Study. Proceedings of the 2nd International Conference on Emerging Trends in Engineering and Technology (ICETET 2009), Nagpur, India.10.1109/ICETET.2009.33 ↗
49. Sapkota, R., Qureshi, R., Flores-Calero, M., Badgujar, C., Nepal, U., Poulose, A., Zeno, P., Vaddevolu, U.B.P., Khan, S., and Shoman, M. (2025). YOLO11 to Its Genesis: A Decadal and Comprehensive Review of The You Only Look Once (YOLO) Series. arXiv.10.36227/techrxiv.171995313.38075268/v1 ↗
50. Valve Corporation (2024, November 15). Steam Hardware Survey 2024. Available online: https://store.steampowered.com/hwsurvey/.
51. Advanced Micro Devices, Inc (2025, February 11). AMD RX 7900XT Datasheet. Available online: https://www.amd.com/en/products/graphics/desktops/radeon/7000-series/amd-radeon-rx-7900xt.html.
52. Intel Corporation (2025, February 11). Intel ARC A750 Graphics Datasheet. Available online: https://www.intel.com/content/www/us/en/products/sku/227954/intel-arc-a750-graphics/specifications.html.
53. Nvidia Corporation (2025, February 11). Nvidia ADA GPU Architecture Whitepaper, v2.1. Available online: https://images.nvidia.com/aem-dam/Solutions/Data-Center/l4/nvidia-ada-gpu-architecture-whitepaper-v2.1.pdf.
54. Advanced Micro Devices, Inc (2025, February 11). ROCm Library Compatibility Matrix. Available online: https://rocm.docs.amd.com/en/docs-6.2.2/compatibility/compatibility-matrix.html.
55. Nvidia Corporation (2025, February 11). CUDA Installation Guide for Linux. Available online: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/.
56. Intel Corporation (2025, February 11). Intel ARC A750 Graphics Driver Support. Available online: https://www.intel.com/content/www/us/en/products/sku/227954/intel-arc-a750-graphics/downloads.html.
57. Kwack, J., Tramm, J.R., Bertoni, C., Ghadar, Y., Homerding, B., Rangel, E., Knight, C., and Parker, S. (2021, January 14). Evaluation of Performance Portability of Applications and Mini-Apps across AMD, Intel and NVIDIA GPUs. Proceedings of the 2021 International Workshop on Performance, Portability and Productivity in HPC (P3HPC), St. Louis, MO, USA. Available online: https://api.semanticscholar.org/CorpusID:245542693.10.1109/P3HPC54578.2021.00008 ↗
58. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., and Chen, L.-C. (2019). MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv.10.1109/CVPR.2018.00474 ↗
59. Geetha, A.S. (2025). YOLOv4: A Breakthrough in Real-Time Object Detection. arXiv.
60. Tan, M., and Le, Q.V. (2020). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv.
61. Advanced Micro Devices, Inc (2025, February 11). AMD System Management Interface (AMD SMI) Library. Available online: https://github.com/ROCm/amdsmi.
62. Intel Corporation (2025, February 11). Intel XPU Manager and XPU System Management Interface. Available online: https://github.com/intel/xpumanager.
63. Nvidia Corporation (2025, February 11). Nvidia System Management Interface Program. Available online: https://docs.nvidia.com/deploy/nvidia-smi/index.html.
64. Python Software Foundation (2025, February 11). Venv–Creation of Virtual Environments. Available online: https://docs.python.org/3/library/venv.html.
65. Advanced Micro Devices, Inc (2025, February 11). AMD Radeon Product Lineup. Available online: https://www.amd.com/en/products/graphics/desktops/radeon.html#specifications.
66. Intel Corporation (2025, February 11). Intel Arc A-Series Graphics Product Lineup. Available online: https://www.intel.com/content/www/us/en/products/details/discrete-gpus/arc/arc-a-series/products.html.
67. Nvidia Corporation (2025, February 11). Nvidia GeForce RTX 40 Series Product Lineup. Available online: https://www.nvidia.com/en-us/geforce/graphics-cards/40-series/.
68. (2024, November 11). CENEO.PL. Available online: https://www.ceneo.pl/.
69. Scikit-Learn Developers (2025, February 12). Frequently Asked Questions. Available online: https://scikit-learn.org/stable/faq.html#will-you-add-gpu-support.
70. Numba (2025, February 12). Tools for Using AMD ROCm with Numba. Available online: https://github.com/numba/roctools.
71. Unified Acceleration Foundation (2025, February 12). Bringing Nvidia and AMD Support to oneAPI. Available online: https://oneapi.io/blog/bringing-nvidia-and-amd-support-to-oneapi/.
72. Advanced Micro Devices, Inc (2025, February 12). Numba HIP–Repository Providing ROCm HIP Backend for Numba. Available online: https://github.com/ROCm/numba-hip.
73. Intel Corporation (2025, February 12). Introduction to the Xe-HPG Architecture. Available online: https://cdrdv2-public.intel.com/758302/introduction-to-the-xe-hpg-architecture-white-paper.pdf.
74. Intel Corporation (2025, February 12). Intel Extension for PyTorch–GPU-Specific Issues. Available online: https://intel.github.io/intel-extension-for-pytorch/xpu/2.1.10+xpu/tutorials/performance_tuning/known_issues.html.
75. Intel Corporation (2025, February 12). Intel Extension for TensorFlow–Release Notes. Available online: https://github.com/intel/intel-extension-for-tensorflow/releases.
76. The Kernel Development Community (2025, February 12). GPU Power/Thermal Controls and Monitoring. Available online: https://docs.kernel.org/gpu/amdgpu/thermal.html.
77. Intel Corporation (2025, February 12). Intel Core Ultra 9 285K Processor Datasheet. Available online: https://www.intel.com/content/www/us/en/products/sku/241060/intel-core-ultra-9-processor-285k-36m-cache-up-to-5-70-ghz/specifications.html.
78. On Global Electricity Usage of Communication Technology: Trends to 203010.3390/challe6010117 ↗