Exploiting Optimized Depthwise Separable Convolutions for Traffic Signal Recognition
DOI:
https://doi.org/10.22399/ijcesen.1812Keywords:
DepthwiseSeparable, Convolutions, ConvolutionalNeural Networks, depthwise convolution, pointwise convolutions, autonomous vehiclesAbstract
Traffic signal recognition using Optimized Depthwise Separable Convolutions (ODSCs) is more proficient than established Convolutional Neural Networks (CNNs) for ongoing projects such as self-drive car and intelligent transportation systems. Efficiency of Optimized Depthwise Separable Convolutions is improved in two modest steps are depthwise convolutions and pointwise convolutions, these operation uses effectively utilize the memory, reduces the processing time and supports scalability. Prediction of traffic sign using ODSCs improves accuracy rate compare to CNNs and also increases the speed of the computations, consumption of energy is less and reduced model size. ODSCs are well suited for device with minimum resource such as embedded system in transportation, intelligent city infrastructures to recognition of traffic signals.
References
[1] W. Marcin, A. Zielonka, A. (2022). Sikora, Driving support by type-2 fuzzy logic control model, Expert Syst. Appl. 207 , 117798. DOI: https://doi.org/10.1016/j.eswa.2022.117798
[2] G. Yao, T. Lei, J. Zhong, (2019). A review of convolutional-neural-network-based action recognition, Pattern Recogn. Lett. 118; 14–22. DOI: https://doi.org/10.1016/j.patrec.2018.05.018
[3] Z. Wei, H. Gu, R. Zhang, J. Peng, S. Qui, (2021). Convolutional neural networks for traffic sign recognition, CICTP 399–409. DOI: https://doi.org/10.1061/9780784483565.039
[4] X. Bangquan, W.X. Xiong,(2019) . Real-time embedded traffic sign recognition using efficient convolutional neural network, IEEE Access 7;53330–53346. DOI: https://doi.org/10.1109/ACCESS.2019.2912311
[5] Lin, J., et al. (2023). Intelligent Transportation Systems. IEEE Transactions, 24(3);1821–1830. DOI: https://doi.org/10.1109/TITS.2023.3245782
[6] F. Khan et al., (2023). Novel deep learning model for traffic sign detection using capsule networks. Pattern Recognition Letters, 167;14–23,
[7] Zhang, Baochang, et al. (2023). Binary Neural Networks: Algorithms, Architectures, and Applications. CRC Press, . DOI: https://doi.org/10.1201/9781003376132
[8] Wang, Bingxuan, and Gengzhao Wang. (2024). A Lightweight Model for Road Sign Detection Based on Improved-YOLOv8. 2024 9th International Conference on Electronic Technology and Information Science (ICETIS). IEEE. DOI: https://doi.org/10.1109/ICETIS61828.2024.10593701
[9] Manzari, Omid Nejati et al. (2022). Pyramid Transformer for Traffic Sign Detection.. 2022 12th International Conference on Computer and Knowledge Engineering (ICCKE) : 112-116. DOI: https://doi.org/10.1109/ICCKE57176.2022.9960090
[10] Wu, Zongzong, et al. (2022). SR-DSFF and FENet-ReID: A Two-Stage Approach for Cross Resolution Person Re-Identification. Computational Intelligence and Neuroscience, 2022, Article ID 4398727. DOI: https://doi.org/10.1155/2022/4398727
[11] Lee, Dong Jae, and Sunwoong Choi. (2023). A Review on Multimodal Fusion Method for Gesture Recognition. Proceedings of the 2023 Fourteenth International Conference on Ubiquitous and Future Networks (ICUFN), pp. 694-696. DOI: https://doi.org/10.1109/ICUFN57995.2023.10199787
[12] Li, J., Wang, H., Zhang, Y., & Liu, X. (2021). A two-stage object detection algorithm with multi-scale feature fusion and prime sample attention for traffic sign recognition. IEEE Transactions on Intelligent Transportation Systems. https://ieeexplore.ieee.org/document/9308917.
[13] Zhang, Q., Chen, L., Wang, Z., & Li, M. (2022). Traffic sign recognition using deep learning for circular sign detection and classification. IEEE Access. https://ieeexplore.ieee.org/document/8997240
[14] Toshniwal, S., Sharma, P., & Patel, D. (2024). Optimized CNNs for traffic sign detection and classification on GTSRB. arXiv preprint. https://arxiv.org/abs/2403.08283
[15] Sruthy, S. (2024). Enhancing traffic sign recognition by classifying deep learning. Signal, Image and Video Processing. https://link.springer.com/article/10.1007/s11760-024-03108-1
[16] Mingwin, S., Shisu, Y., Wanwag, Y., & Huing, S. (2024). Revolutionizing traffic sign recognition: Unveiling the potential of vision transformers. arXiv preprint. https://arxiv.org/abs/2404.19066
[17] Pavlitska, S., Lambing, N., Bangaru, A. K., & Zöllner, J. M. (2023). Traffic light recognition using convolutional neural networks: A survey. arXiv preprint. https://arxiv.org/abs/2309.02158 DOI: https://doi.org/10.1109/ITSC57777.2023.10422041
[18] Xu, Y., et al. ( 2020). Traffic Sign Recognition Based on Deep Learning. IEEE Access, 8;74220-74229.
[19] Chen, L., et al. (2021). Convolutional Neural Networks for Real-Time Traffic Sign Recognition. IEEE Transactions on Intelligent Transportation Systems, 22(3);1561-1572.
[20] Sharma, R., et al. (2023). A Comprehensive Survey on Traffic Sign Detection and Recognition. International Journal of Research and Analytical Reviews (IJRAR), 10(2);120-130.
[21] Kumar, S., and Patel, R. (2022). Real-Time Traffic Sign Recognition System Using Machine Learning.. International Research Journal of Modernization in Engineering Technology and Science (IRJMETS), 4(2);89-96.
[22] Singh, A., and Gupta, N. (2023). Unified Framework for Traffic Sign Detection and Classification Using Deep Neural Networks. IEEE Access, 11;54230-54241.
[23] Lee, J., et al. (2023). A Survey on Traffic Light Recognition Using Convolutional Neural Networks. arXiv preprint arXiv:2309.02158,
[24] Patel, M., and Sharma, P. (2024). Optimized Traffic Sign Recognition Using CNN on GTRSB. arXiv preprint arXiv:2403.08283, 2024.
[25] Zhao, Y., et al. (2024). Efficient Edge Deployment of Depthwise Separable Convolutions for Real-Time Traffic Signal Recognition." arXiv preprint arXiv:2411.07544, .
[26] Chen, W., et al. (2024) Hybrid Attention Enhanced Depthwise Separable Convolutions for Traffic Signal Recognition." Sensors, 24(18);6075.
[27] Haase, P., and Amthor, M. (2020). Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved Performance. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4133-4142. CVPR. DOI: https://doi.org/10.1109/CVPR42600.2020.01461
[28] Zhang, L., et al. (2024). Energy-Efficient Depthwise Separable Convolution Architectures for Embedded Traffic Signal Recognition. Lecture Notes in Computer Science, Springer,pp. 156-170. DOI: https://doi.org/10.1007/978-981-97-5562-2_10
[29] Chollet, François. (2017). Xception: Deep Learning with Depthwise Separable Convolutions. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1251-1258. DOI: https://doi.org/10.1109/CVPR.2017.195
[30] Li, Wei, et al. (2023,). C2S-RoadNet: Road Extraction Model with Depth-Wise Separable Convolutions and Lightweight Asymmetric Self-Attention. Remote Sensing, 15(18);4531. DOI: https://doi.org/10.3390/rs15184531
[31] Lee, Der-Hau, and Jinn-Liang Liu. (2021). End-to-End Deep Learning of Lane Detection and Path Prediction for Real-Time Autonomous Driving. arXiv preprint arXiv:2102.04738, DOI: https://doi.org/10.1007/s11760-022-02222-2
[32] Thamilarasi V, Hema R, Dr.A.Noble Mary Juliet, Dr. Adlin Sheeba, Gauri Ghule, Raja A, (2025). AI-Powered Real-Time Runway Safety: UAV-Based Video Analysis with ICSO-Enhanced Deep Learning, Journal name: International Journal of Computational and Experimental Science and Engineering , 11(1);1314-1329. DOI: https://doi.org/10.22399/ijcesen.1184
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
