دانشگاه تربیت دبیر شهید رجائی
انتشارات دانشگاه تربیت دبیر شهید رجائی

  اخبار و اعلانات

 آمار

تعداد نشریات11
تعداد شماره‌ها217
تعداد مقالات2,179
تعداد مشاهده مقاله3,140,552
تعداد دریافت فایل اصل مقاله2,283,381
Safavi, S. H., Sadeghi, M., Ebadpour, M.. (1402). DPRSMR: Deep Learning-based Persian Road Surface Marking Recognition. فناوری آموزش, 11(2), 409-418. doi: 10.22061/jecei.2023.9496.627
S. H. Safavi; M. Sadeghi; M. Ebadpour. "DPRSMR: Deep Learning-based Persian Road Surface Marking Recognition". فناوری آموزش, 11, 2, 1402, 409-418. doi: 10.22061/jecei.2023.9496.627
Safavi, S. H., Sadeghi, M., Ebadpour, M.. (1402). 'DPRSMR: Deep Learning-based Persian Road Surface Marking Recognition', فناوری آموزش, 11(2), pp. 409-418. doi: 10.22061/jecei.2023.9496.627
Safavi, S. H., Sadeghi, M., Ebadpour, M.. DPRSMR: Deep Learning-based Persian Road Surface Marking Recognition. فناوری آموزش, 1402; 11(2): 409-418. doi: 10.22061/jecei.2023.9496.627

DPRSMR: Deep Learning-based Persian Road Surface Marking Recognition

Journal of Electrical and Computer Engineering Innovations (JECEI)
دوره 11، شماره 2، مهر 2023، صفحه 409-418    اصل مقاله (1.18 M)
نوع مقاله: Original Research Paper
شناسه دیجیتال (DOI): 10.22061/jecei.2023.9496.627
نویسندگان
S. H. Safavi* 1؛ M. Sadeghi2؛ M. Ebadpour2
1Faculty of Advanced Technologies, University of Mohaghegh Ardabili, Namin, Iran.
2Faculty of Engineering, University of Mohaghegh Ardabili, Ardabil, Iran.
تاریخ دریافت: 25 آذر 1401،  تاریخ بازنگری: 10 اسفند 1401،  تاریخ پذیرش: 20 اسفند 1401 
چکیده
Background and Objectives: Persian Road Surface Markings (PRSMs) recognition is a prerequisite for future intelligent vehicles in Iran. First, the existence of Persian texts on the Road Surface Markings (RSMs) makes it challenging. Second, the RSM could appear on the road with different qualities, such as poor, fair, and excellent quality. Since the type of poor-quality RSM is variable from one province to another (i.e., varying road structure and scene complexity), it is a very essential and challenging task to recognize unforeseen poor-quality RSMs. Third, almost all existed datasets have imbalanced classes that affect the accuracy of the recognition problem.
Methods: To address the first challenge, the proposed Persian Road Surface Recognizer (PRSR) approach hierarchically separates the texts and symbols before recognition. To this end, the Symbol Text Separator Network (STS-Net) is proposed. Consequently, the proposed Text Recognizer Network (TR-Net) and Symbol Recognizer Network (SR-Net) respectively recognize the text and symbol. To investigate the second challenge, we introduce two different scenario. Scenario A: Conventional random splitting training and testing data. Scenario B: Since the PRSM dataset include few images of different distance from each scene of RSM, it is highly probable that at least one of these images appear in the training set, making the recognition process easy. Since in any province of Iran, we may see a new type of poor quality RSM, which is unforeseen before (in training set), we design a realistic and challengeable scenario B in which the network is trained using excellent and fair quality RSMs and tested on poor quality ones. Besides, we propose to use the data augmentation technique to overcome the class imbalanced data challenge.
Results: The proposed approach achieves reliable performance (precision of 73.37% for scenario B) on the PRSM dataset . It significantly improves the recognition accuracy up to 15% in different scenarios.
Conclusion: Since the PRSMs include both Persian texts (with different styles) and symbols, prior to recognition process, separating the text and symbol by a proposed STS-Net could increase the recognition rate. Deploying new powerful networks and investigating new techniques to deal with class imbalanced data in the recognition problem of the PRSM dataset as well as data augmentation would be an interesting future work.
کلیدواژه‌ها
Self-driving Technology؛ Scene Understanding؛ Deep Learning؛ Alex-Net؛ VGG
مراجع
[1] T. Veit, J. P. Tarel, P. Nicolle, and P. Charbonnier, "Evaluation of road marking feature extraction," in Proc. 11th International IEEE Conference on Intelligent Transportation Systems: 174–181, 2008.

[2] T. Wu, A. Ranganathan, "A practical system for road marking detection and recognition," in Proc. IEEE Intelligent Vehicles Symposium: 25–30, 2012.

[3] B. Mathibela, P. Newman, I. Posner, "Reading the road: Road marking classification and interpretation," IEEE Trans. Intell. Transp. Syst., 16(4): 2072–2081, 2015.

[4] X. Liu, Z. Deng, H. Lu, L. Cao, "Benchmark for road marking detection: Dataset specification and performance baseline," in Proc. IEEE 20th International Conference on Intelligent Transportation Systems (ITSC), 2017.

[5] F. Yu et al., "BDD100K: A diverse driving video database with scalable annotation tooling," arXiv preprint arXiv:1805.04687, 2018.

[6] S. H. Safavi et al., "Image dataset for persian road surface markings," in Proc. IEEE 10th Iranian Conference on Machine Vision and Image Processing (MVIP): 258–264, 2017.

[7] A. Geiger, P. Lenz, C. Stiller, R. Urtasun, "Vision meets Robotics: The KITTI Dataset," Int. J. Rob. Res., 32(11): 1231–1237, 2013.

[8] J. L. Blanco, F. A. Moreno, J. Gonzalez-Jimenez, "The málaga urban dataset: High-rate stereo and lidars in a realistic urban scenario," Int. J. Rob. Res., 33(2): 207–214, 2014.

[9] W. Maddern, G. Pascoe, C. Linegar, P. Newman, "1 Year, 1000km: The Oxford RobotCar Dataset," Int. J. Rob. Res. (IJRR), 36(1): 3–15, 2017.

[10] W. Maddern, G. Pascoe, M. Gadd, D. Barnes, B. Yeomans, P. Newman, "Real-time kinematic ground truth for the oxford robotcar dataset", in arXiv preprint arXiv: 2002.10152, 2020.

[11] A. Gupta, A. Choudhary, “A framework for camera-based real-time lane and road surface marking detection and recognition,” IEEE Trans. Intell. Veh., 3(4): 476–485, 2018.

[12] T. Bruls, W. Maddern, A. A. Morye, P. Newman, “Mark yourself: Road marking segmentation via weakly-supervised annotations from multimodal data,” in Proc. IEEE International Conference on Robotics and Automation (ICRA): 1863-1870, 2018.

[13] A. Fallah, A. Soliemani, H. Khosravi, “Real-time lane detection based on image edge feature and hough transform,” J. Electr. Comput. Eng. Innovations (JECEI), 9(2): 193-202, 2021.

[14] N. S. Danishevskiy, I. A. Ershov, D. O. Budanov, “Computer vision system for road surface marking recognition,” in Proc. IEEE International Conference on Electrical Engineering and Photonics (EExPolytech): 130-133, 2022.

[15] B. A. Maxwell et al., “Real-time physics-based removal of shadows and shading from road surfaces”, in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW): 1277–1285, 2019.

[16] E. S. Dawam, X. Feng, “Smart city lane detection for autonomous vehicle” in Proc. IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech): 334-338, 2020.

[17] M. R. Bachute, J. M. Subhedar, “Autonomous driving architectures: insights of machine learning and deep learning algorithms,” Elsevier, Machine Learning with Applications, 6(100164): 1-25 2021.

[18] D. K. Dewangan, S. P. Sahu, “RCNet: road classification convolutional neural networks for intelligent vehicle system,” Intell. Serv. Rob., 14(2): 199-214, 2021.

[19] R. D. Brehar, M. P. Muresan, T. Mariţa, C. C. Vancea, M. Negru, S. Nedevschi, “Pedestrian street-cross action recognition in monocular far infrared sequences,” IEEE Access, (9): 74302-74324, 2021.

[20] J. Redmon, A. Farhadi, “Yolov3: An incremental improvement”, arXiv preprint arXiv:1804.02767, 2018.

[21] Z. Feng, M. Li, M. Stolz, M. Kunert, W. Wiesbeck, “Lane detection with a high-resolution automotive radar by introducing a new type of road marking,” IEEE Trans. Intell. Trans. Syst., 20(7): 2430-2447, 2018.

[22] S. Chen, Z. Zhang, H. Ma, L. Zhang, R. Zhong, “A content-adaptive hierarchical deep learning model for detecting arbitrary-oriented road surface elements using MLS point clouds,” IEEE Trans. Geosc. Remote Sens., 61(5700516): 1-16, 2023.

[23] A. Krizhevsky, I. Sutskever, G. E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Advances in neural information processing systems (NIPS 2012): 1097–1105, 2012.

[24] K. Simonyan. A. Zisserman, “Very deep convolutional networks for largescale image recognition,” arXiv preprint arXiv:1409.1556, 2014.

[25] R. Girshick, “Fast r-cnn,” in Proc. IEEE International Conference on Computer Vision and Pattern Recognition (CVPR): 1440-1448, 2015.

[26] S. Ren, K. He, R. Girshick, J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” Advances in neural information processing systems (NIPS), (28):1-9, 2015.

[27] S. Ren, K. He, R. Girshick, J. Sun, “Faster r-cnn: Towards real-time object detection with region proposal networks,” IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 39(6):1137-1149, 2017.

[28] X. Ding, X. Zhang, N. Ma, J. Han, G. Ding, J. Sun, “RepVGG: Making VGG-style ConvNets great again,” in Proc. IEEE/CVF conference on computer vision and pattern recognition (CVPR): 13733-13742, 2021.

[29] L. Chen et. al., “Deep integration: A multi-label architecture for road scene recognition,” IEEE Trans. Image Proc., 28(10): 4883–4898, 2019.

[30] K. Lis et. al., “Detecting the unexpected via image resynthesis” in Proc. IEEE/CVF International Conference on Computer Vision (ICCV): 2152-2161, 2019.

 

آمار
تعداد مشاهده مقاله: 456
تعداد دریافت فایل اصل مقاله: 254


سامانه مدیریت نشریات علمی. طراحی و پیاده سازی از سیناوب