Real-time image processing for autonomous vehicles: a GPU-accelerated approach in ubuntu
DOI:
https://doi.org/10.29210/8815601Keywords:
Autonomous Vehicles, GPU, UbuntuAbstract
Autonomous vehicles heavily rely on real-time image processing for navigation and decision-making. However, performing real-time processing of high-resolution images presents a significant computational challenge that might hinder the advancement of autonomous vehicle technology. Computational requirements associated with image processing could act as a constraining factor in the advancement of autonomous vehicles. This study introduces an innovative GPU-accelerated method tailored for real-time image processing on Ubuntu, specifically designed for autonomous vehicle tasks. The approach capitalizes on the CUDA programming paradigm to exploit the parallel processing capabilities of NVIDIA GPUs, resulting in substantial performance boosts when compared to typical CPU-centric techniques. The findings of this study carry substantial implications for the evolution of autonomous vehicles, facilitating quicker and more effective image processing to enhance safety and operational efficiency. Additionally, they highlight the potential of GPU-accelerated image processing in the domain of self-driving cars by facilitating faster and more effective management of visual information.References
Allusse, A., Horain, P., Agarwal, A., & Saipulla, A. (2008). *GpuCV: A GPU-accelerated framework for image processing and computer vision*. Proceedings of the 2008 IEEE International Conference on Multimedia and Expo, 9–12. IEEE. [https://doi.org/10.1109/ICME.2008.4607575](https://doi.org/10.1109/ICME.2008.4607575)
Bojarski, M., Del Testa, D., Dworakowski, D., Firner, B., Flepp, B., Goyal, P., ... & Zhang, X. (2016). End to end learning for self-driving cars. arXiv preprint arXiv:1604.07316.
Chen, H., & Wang, J. (2020). Thermal management for high-performance computing in autonomous vehicles. IEEE Transactions on Vehicular Technology, 69(8), 8192-8205.
Choi, S., Lee, D., & Kim, J. (2019). A survey on sensor fusion techniques for autonomous vehicles. Journal of Sensors, 2019, 1-15.
Chuttur, Y. ., Kaudeerally, R., & Nazurally, A. (2023). Lane Reconstruction for Self-Driving Vehicles on Dynamic Road Networks. Journal of Telecommunication, Electronic and Computer Engineering (JTEC), 15(2), 29–36. https://doi.org/10.54554/jtec.2023.15.02.004
Dakić, P., & Živković, M. (2021). An overview of the challenges for developing software within the field of autonomous vehicles. In Proceedings of the 7th Conference on the Engineering of Computer Based Systems (ECBS ’21) (pp. 1–6). Association for Computing Machinery. https://doi.org/10.1145/3459960.3459972
Duarte, F. (2018). The impact of autonomous vehicles on urban transportation systems. Journal of Urban Technology, 25(4), 3-18.
Fernandes, S., Duseja, D., & Muthalagu, R. (2021). Application of image processing techniques for autonomous cars. Proceedings of Engineering and Technology Innovation, 17, 01-12. https://doi.org/10.46604/peti.2021.6074
Gerdes, J. C., & Thrun, S. (2018). The challenges of real-world deployment for autonomous driving. Science Robotics, 3(24), eaat7144.
Glamočić, D., Lalić, B., & Milanović, D. (2019). *GPU-enabled integral image computation for automotive platforms*
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
Han, T., Li, W., & Zhang, J. (2021). GPU performance optimization for deep learning: A survey. Journal of Parallel and Distributed Computing, 148, 12-25.
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444. https://doi.org/10.1038/nature14539
Lee, J., Kim, H., & Park, S. (2020). A framework for safety assurance of autonomous driving systems. Journal of Advanced Transportation, 2020, 1-12.
Membarth, R., Hannig, F., Teich, J., & Körner, M. (2011). *Frameworks for GPU acceleration: Evaluation of RapidMind, PGI Accelerator, HMPP Workbench, OpenCL, and CUDA*. International Journal of Parallel Programming, 39(5), 417–444. [https://doi.org/10.1007/s10766-010-0162-7](https://doi.org/10.1007/s10766-010-0162-7)
NVIDIA. (2023). CUDA: The parallel computing platform and programming model. Retrieved from https://developer.nvidia.com/cuda-toolkit
Padmaraja, V. P., Rohith, R., & Chittesh, S. (2023). Lane detection using image processing for autonomous vehicles. In 2023 2nd International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA) (pp. 1–6). IEEE. https://doi.org/10.1109/ICAECA56562.2023.10200663
Papadimitriou, G., Tsiotras, P., & Vamvoudakis, K. G. (2021). Real-time safety assurance for autonomous systems. IEEE Transactions on Control Systems Technology, 29(5), 2097-2109.
Patterson, D. A., & Hennessy, J. L. (2018). Computer organization and design: The hardware/software interface. Morgan Kaufmann.
Pendleton, S. D., Andersen, H., Du, X., Shen, X., Meghjani, M., Eng, Y. H., Rus, D., & Ang, M. H. (2017). *Perception, planning, control, and coordination for autonomous vehicles*. Machines, 5(1), 6. [https://doi.org/10.3390/machines5010006](https://doi.org/10.3390/machines5010006)
Qualcomm. (2025). *Advanced driver assistance systems: Reducing accidents with AEB and safety features*. Qualcomm Technologies Inc. [https://www.qualcomm.com/](https://www.qualcomm.com/) [replace with direct page URL if available]
Saoudi, F. (2022). *Open-source operating systems in autonomous vehicle development: Ubuntu as a case study*.
Shevenell, G. (1984). *Optical and acoustic imaging systems for vehicle control applications*.
Sun, W., & Min, Y. (2023). Research on a driving assistance system for lane changes on foggy highways. Sustainability, 15(13), Article 10032. https://doi.org/10.3390/su151310032
Ubuntu. (2023). The world's most popular free operating system. Retrieved from https://ubuntu.com
Wang, L., Chen, Y., & Liu, Z. (2022). Real-time object detection and tracking with GPU acceleration. IEEE Transactions on Intelligent Vehicles, 7(1), 125-136.
Yang, J. (2018). *Safety-critical real-time GPU principles in NVIDIA-based autonomous systems*.
Downloads
Published
Issue
Section
License
IJTIH is an Open Access Journal. The authors who publish the manuscript in this journal agree to the following terms:
IJTIH is licensed under a Creative Commons Attribution 4.0 International License. This permits anyone to copy, redistribute, remix, transmit and adapt the work provided the original work and source is appropriately cited.
This means:
IJTIH is licensed under a Creative Commons Attribution 4.0 International License.
(1) Under the CC-BY license, authors retain ownership of the copyright for their article, but authors grant others permission to use the content of publications in IJTIH in whole or in part provided that the original work is properly cited. Users (redistributors) of IJTIH are required to cite the original source, including the author's names, IJTIH as the initial source of publication, year of publication, volume number, issue, and Digital Object Identifier (DOI); (2) Authors grant IJTIH the right of first publication. Although authors remain the copyright owner.
