Application of Convolutional Neural Networks in Autonomous Driving Scene Understanding
DOI:
https://doi.org/10.71451/er8shr54Keywords:
Autonomous driving; CNN; Scene understanding; Image processing; Deep learningAbstract
With the rapid development of autonomous driving technology, environmental perception and scene understanding have become key factors to ensure safe driving. As a powerful deep learning algorithm, convolutional neural network (CNN) has demonstrated outstanding capabilities in image processing and visual perception. This paper explores the application of CNN in scene understanding of autonomous driving, and analyzes its advantages in image classification, object detection, semantic segmentation, etc., especially its performance in real-time environmental perception. Through multi-level feature extraction, CNN can identify and understand important information such as road signs, pedestrians, and vehicles from complex traffic scenes, providing accurate decision support for autonomous driving systems. The article also explores the combination of CNN with other technologies such as RNN, reinforcement learning, and multimodal data fusion, looks forward to the development trend of autonomous driving technology in the future, and discusses the challenges faced by the technology and corresponding solutions. Through the research of this paper, it is hoped that a theoretical basis and practical guidance will be provided to further improve the intelligence level and safety of autonomous driving systems.
References
[1] Liu, X., Yan, W. Q., & Kasabov, N. (2024). Moving vehicle tracking and scene understanding: A hybrid approach. Multimedia Tools and Applications, 83(17), 51541-51558. DOI: https://doi.org/10.1007/s11042-023-17618-6
[2] Cao, Z., Gao, Y., Bai, J., Qin, Y., Zheng, Y., & Jia, L. (2024). Efficient dual-stream fusion network for real-time railway scene understanding. IEEE Transactions on Intelligent Transportation Systems. DOI: https://doi.org/10.1109/TITS.2024.3377187
[3] Liao, G., Li, J., & Ye, X. (2024, March). VLM2Scene: Self-supervised image-text-LiDAR learning with foundation models for autonomous driving scene understanding. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 38, No. 4, pp. 3351-3359). DOI: https://doi.org/10.1609/aaai.v38i4.28121
[4] Zhao, T., Chen, G., Gatewongsa, T., & Busababodhin, P. (2024). Forecasting Agricultural Trade Based on TCN-LightGBM Models: A Data-Driven Decision. Research on World Agricultural Economy, 6(1), 207–221. https://doi.org/10.36956/rwae.v6i1.1429 DOI: https://doi.org/10.36956/rwae.v6i1.1429
[5] Sahoo, L. K., & Varadarajan, V. (2025). Deep learning for autonomous driving systems: technological innovations, strategic implementations, and business implications-a comprehensive review. Complex Engineering Systems, 5(1), N-A. DOI: https://doi.org/10.20517/ces.2024.83
[6] Li, H., Chu, H. K., & Sun, Y. (2024). Temporal consistency for RGB-thermal data-based semantic scene understanding. IEEE Robotics and Automation Letters. DOI: https://doi.org/10.1109/LRA.2024.3458594
[7] Tirumalapudi, R., & Sirisha, J. (2024). Onward And Autonomously: Expanding The Horizon Of Image Segmentation For Self-Driving Cars Through Machine Learning. Scalable Computing: Practice and Experience, 25(4), 3163-3171. DOI: https://doi.org/10.12694/scpe.v25i4.2869
[8] Salman, H. A., & Kalakech, A. (2024). Image enhancement using convolution neural networks. Babylonian Journal of Machine Learning, 2024, 30-47. DOI: https://doi.org/10.58496/BJML/2024/003
[9] Zhang, Y., & Tang, Q. (2024). Accelerating autonomy: an integrated perception digital platform for next generation self-driving cars using faster R-CNN and DeepLabV3. Soft Computing, 28(2), 1633-1652. DOI: https://doi.org/10.1007/s00500-023-09510-0
[10] Abdullahi, M., Oyelade, O. N., Kana, A. F. D., Bagiwa, M. A., Abdullahi, F. B., Junaidu, S. B., ... & Chiroma, H. (2024). A systematic literature review of visual feature learning: deep learning techniques, applications, challenges and future directions. Multimedia Tools and Applications, 1-58. DOI: https://doi.org/10.1007/s11042-024-19823-3
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Scientific Technical and Economic Research
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
This work is licensed under the Creative Commons Attribution International License (CC BY 4.0).
