Abstract
Annually, deep learning algorithms have proven their effectiveness in many vision-based applications, such as autonomous driving, traffic, and congestion monitoring, and so on. In computer vision, accurate traffic sign recognition and semantic road detection are vital challenges for increased safety, which are becoming a major research topic for intelligent transport systems community. In this paper, a deep learning-based driving assistance system has been proposed. To this end, we present hybrid 2D-3D CNN models based on the transfer learning paradigm to achieve better performance on benchmark real-world datasets. The primary goal of transfer learning is to improve the learning process in the target domain while transferring relevant knowledge from the source domain. We combine a pre-trained deep 2D CNN and a shallow 3D CNN to significantly reduce complexity and speed-up the training algorithm. The first model, called Hybrid-TSR, is intended to effectively address the task of traffic sign recognition. Hybrid-SRD is the second architecture that allows the semantic detection of road space through a combination of up-sampling and deconvolutional operations. The experimental results show that the proposed methods have considerable relevance in terms of efficiency and accuracy.
Similar content being viewed by others
References
Arcos-García A, Álvarez-García J A, Soria-Morillo LM (2018) Deep neural network for traffic sign recognition systems: an analysis of spatial transformers and stochastic optimisation methods. Neural Netw 99:158–165
Arnab A, et al. (2018) Conditional random fields meet deep neural networks for semantic segmentation. IEEE Signal Process Mag 35(1):37–52
Ayachi R, Afif M, Said Y, Atri M (2019) Traffic signs detection for real-world application of an advanced driving assisting system using deep learning. Neural Process Lett 51:837–851
Badrinarayanan V, Kendall A, Cipolla R (2015) SegNet: a deep convolutional encoder-decoder architecture for image segmentation. arXiv:1511.00561
Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT’2010, pp 177–186
Chen Z, Chen Z (2017) RBNet: a deep neural network for unified road and road boundary detection. In: ICONIP, pp 677–687
Cireşan D, Meier U, Masci J, Schmidhuber J (2012) Multi-column deep neural network for traffic sign classification. Neural Netw 32:333–338
Gao P, Yuan R, Wang F, Xiao L, Fujita H, Zhang Y (2020) Siamese attentional keypoint network for high performance visual tracking. Knowl Based Syst 193:105448. https://doi.org/10.1016/j.knosys.2019.105448
Gao P, Zhang Q, Wang F, Xiao L, Fujita H, Zhang Y (2020) Learning reinforced attentional representation for end-to-end visual tracking. Inf Sci 517:52–67. https://doi.org/10.1016/j.ins.2019.12.084
Ge L, Liang H, Yuan J, Thalmann D (2017) 3D Convolutional neural networks for efficient and robust hand pose estimation from single depth images. In: CVPR, pp 5679–5688
Gecer B, Azzopardi G, Petkov N (2017) Color-blob-based COSFIRE filters for object recognition. Image Vis Comput 57:165–174
Greenhalgh J, Mirmehdi M (2012) Real-time detection and recognition of road traffic signs. IEEE Trans Intell Transp Syst 13(4):1498–1506
He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. arXiv:1512.03385
Hechri A, Hmida R, Mtibaa A (2015) Robust road lanes and traffic signs recognition for driver assistance system. Int J Comput Sci Eng 10(1/2):202–209
Hmida R, Ben Abdelali A, Mtibaa A (2018) Hardware implementation and validation of a traffic road sign detection and identification system. J Real-Time Image Proc 15(1):13–30
Howard AG, et al. (2017) MobileNets: efficient convolutional neural networks for mobile vision applications. arXiv:1704.04861
Hu K, Shen L, Albanie S, Sun G, Wu E (2017) Squeeze-and-excitation networks. arXiv:1709.01507
Ji S, Xu W, Yang M, Yu K (2013) 3D convolutional neural networks for human action recognition. IEEE Trans Pattern Anal Mach Intell 35(1):221–231. https://doi.org/10.1109/TPAMI.2012.59
John N, Anusha B, Kutty K (2015) A reliable method for detecting road regions from a single image based on color distribution and vanishing point location. Procedia Comput Sci 58:2–9
Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv:1412.6980
LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436–444
Lin C, Li L, Luo W, Wang KCP, Guo J (2019) Transfer learning based traffic sign recognition using inception-v3 model. Engineering 47(3):242–250
Liu Z, Li D, Ge SS, Tian F (2020) Small traffic sign detection from large image. Appl Intell 50:1–13
Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: CVPR, pp 3431–3440
Luo X, Zhu J, Yu Q (2019) Efficient convNets for fast traffic sign recognition. IET Intell Trans Syst 13(6):1011–1015. https://doi.org/10.1049/iet-its.2018.5489
Nam JH, Yang SH, Hu W, Kim BG (2015) A robust real-time road detection algorithm using color and edge information. In: ISVC, pp 532–541
Noh H, Hong S, Han B (2015) Learning deconvolution network for semantic segmentation. arXiv:1505.04366
Oliveira G, et al. (2018) Efficient and robust deep networks for semantic segmentation. Int J Robot Res 37:472–491
Onisr, 2019 French road safety observatory. ONISR. https://doi.org/http://www.onisr.securite-routiere.interieur.gouv.fr/contenus/en/road-safety-policy
Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22 (10):1345–1359
Peng X, Li Y, Wei X, Luo J, Murphey YL (2017) Traffic sign recognition with transfer learning. In: SSCI, pp 1–7
Ronneberger O, Fischer P, Brox T (2015) U-net: convolutional networks for biomedical image segmentation. arXiv:1505.04597
Saadna Y, Behloul A, Mezzoudj S (2019) Speed limit sign detection and recognition system using SVM and MNIST datasets. Neural Comput Appl 31:5005–5015. https://doi.org/10.1007/s00521-018-03994-w
Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC (2018) MobileNetV2: inverted residuals and linear bottlenecks. arXiv:1801.04381
Sermanet P, LeCun Y (2011) Traffic sign recognition with multi-scale convolutional networks. In: IJCNN, pp 2809–2813
Shustanov A, Yakimov P (2017) CNN design for real-time traffic sign recognition. Procedia Eng 201:718–725
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556
Stallkamp J, Schlipsing M, Salmen J, Igel C (2011) The German traffic sign recognition benchmark: a multi-class classification competition. In: IJCNN, pp 1453–1460
Stallkamp J, Schlipsing M, Salmen J, Igel C (2012) Man vs. computer: Benchmarking machine learning algorithms for traffic sign recognition. Neural Netw 32:323–332
Szegedy C, et al. (2014) Going deeper with convolutions. arXiv:1409.4842
Tabernik D, Skočaj D (2019) Deep learning for large-scale traffic-sign detection and recognition. arXiv:1904.00649
Tan M, Le QV (2019) EfficientNet: rethinking model scaling for convolutional neural networks. arXiv:1905.11946
Teichmann M, Weber M, Zöllner M, Cipolla R, Urtasun R (2018) MultiNet: real-time joint semantic reasoning for autonomous driving. In: IV, pp 1013–1020
Tran D et al (2015) Learning spatiotemporal features with 3D convolutional networks. In: ICCV, pp 4489–4497
Wen L, Jo K (2017) Traffic sign recognition and classification with modified residual networks. In: SII, pp 835–840
Who (2019) Global status report on road safety 2018. WHO. http://www.who.int/violence_injury_prevention/road_safety_status/2018/en. Accessed 19 Aug 2019
Wong A, Shafiee MJ, St. Jules M (2018) MicronNet: a highly compact deep convolutional neural network architecture for real-time embedded traffic sign classification. IEEE Access 6:59803–59810. https://doi.org/10.1109/ACCESS.2018.2873948
Xiao L, et al. (2018) Hybrid conditional random field based camera-LIDAR fusion for road detection. Inf Sci 432:543–558
Yao G, Lei T, Zhong J, Jiang P (2019) Learning multi-temporal-scale deep information for action recognition. Appl Intell 49(6):2017–2029. https://doi.org/10.1007/s10489-018-1347-3
Yu L, Jin M, Zhou K (2019) Multi-channel biomimetic visual transformation for object feature extraction and recognition of complex scenes. Appl Intell 50:792–811. https://doi.org/10.1007/s10489-019-01550-0
Zaklouta F, Stanciulescu B, Hamdoun O (2011) Traffic sign classification using K-d trees and random forests. In: IJCNN, pp 2151–2155
Zang D, et al. (2018) Deep learning–based traffic sign recognition for unmanned autonomous vehicles. Proc Inst Mech Eng Part I: J Syst Control Eng 232(5):497–505
Zhang S, Zhang Z, Sun L, Qin W (2019) One for all: a mutual enhancement method for object detection and semantic segmentation. Appl Sci 10(1):13
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Bayoudh, K., Hamdaoui, F. & Mtibaa, A. Transfer learning based hybrid 2D-3D CNN for traffic sign recognition and semantic road detection applied in advanced driver assistance systems. Appl Intell 51, 124–142 (2021). https://doi.org/10.1007/s10489-020-01801-5
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-020-01801-5