Development of Real-Time Traffic-Object Detection Models Applied for Autonomous Intelligent Vehicles
Main Article Content
Abstract
Technologies for detecting traffic objects are an essential requirement for any applications in autonomous intelligent vehicles. In this work, models for detecting traffic objects were developed. Based on the existing datasets and the pre-trained models, fine-tuning techniques were applied to achieve trained models with higher accuracies even for the very challenging test data. The traffic object detection was developed based on the pre-trained YOLOv5s model. Two approaches were introduced for the traffic sign detection task. The so-called tiling technique incorporated with the YOLOv5s model was exploited in the first approach. In the second approach, a combination of the RetinaFace model for the localization and the MobileNetV1-SSD for the classification was employed. The experimental results show that all developed models release a very high rate of accuracy with a maximum AP50 of 75.9% for object detection and mAP50 of 64.2% for sign detection. Models developed via the second approach have twofold advantages in terms of accuracy and computational efficiency, which allows to deploy practical applications.
Keywords
autonomous intelligent vehicles, deep learning, embedded hardware, object detection
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
[1] Taxonomy and Definitions for Terms Related to OnRoad Motor Vehicle Automated Driving Systems, SAE Standard J3016, 2014.
[2] T. Karasawa, K. Watanabe, Q. Ha, A. Tejero-DePablos, Y. Ushiku, and T. Harada, Multispectral object detection for autonomous vehicles, in Proc. Themat. Work. ACM Multimed. 2017, Mountain View, CA, USA, 2017, pp. 35–43.
[3] J. Varagula, P. A. N. Kulproma, and T. Itob, Object detection method in traffic by on-board computer vision with time delay neural network, in Proc. KES2017, Marseille, France, 2017, vol. 112, pp. 127–136. https://doi.org/10.1016/j.procs.2017.08.185
[4] H. Zhang, K. Wang, Y. Tian, C. Gou, and F. Y. Wang, MFR-CNN: Incorporating multi-scale features and global information for traffic object detection, IEEE Trans. Veh. Technol., vol. 67, no. 9, pp. 8019–8030, Sept. 2018, 10.1109/TVT.2018.2843394. https://doi.org/10.1109/TVT.2018.2843394
[5] Á. Arcos-García, J. A. Álvarez-García, and L. M. Soria-Morillo, Evaluation of deep neural networks for traffic sign detection systems, Neurocomputing, vol. 316, pp. 332–344, 2018, 10.1016/j.neucom.2018.08.009. https://doi.org/10.1016/j.neucom.2018.08.009
[6] M. Cordts et al., The cityscapes dataset for semantic urban scene understanding, in Proc. CVPR, Las Vegas, NV, USA, 2016, pp. 3213–3223. https://doi.org/10.1109/CVPR.2016.350
[7] G. Jocher, A. Stoken, J. Borovec, C. NanoCode012, L. Changyu, H. Laughing, ultralytics/yolov5: v4.0, Ultralytics, Jan. 5, 2021.
[8] F. Ö. Ünel, B. O. Özkalayci and C. Çiğla, The power of tiling for small object detection, in Proc. CVPRW, Long Beach, CA, USA, 2019, pp. 582-591. https://doi.org/10.1109/CVPRW.2019.00084
[9] J. Deng, J. Guo, Y. Zhou, J. Yu, I. Kotsia, S. Zafeiriou, RetinaFace: single-stage dense face localisation in the wild, arXiv: 1905.00641, 2019.
[10] Single Shot MultiBox Detector Implementation in Pytorch.
[11] Zalo AI Challenge.
[12] N. H. Dung, Application of convolution neural network in design and fabrication of robots for transporting goods in factories, J. Sci. Technol., vol. 147 (2020), pp. 51-58, Nov. 2020. https://doi.org/10.51316/30.8.9
[13] T. Y. Lin et al., Microsoft COCO: Common objects in context, Lect. Notes Comput. Sci., vol. 8693 LNCS, no. PART 5, pp. 740–755, 2014 https://doi.org/10.1007/978-3-319-10602-1_48
[14] Jetson Nano Developer.
[15] Jetson AGX Xavier Developer.
[2] T. Karasawa, K. Watanabe, Q. Ha, A. Tejero-DePablos, Y. Ushiku, and T. Harada, Multispectral object detection for autonomous vehicles, in Proc. Themat. Work. ACM Multimed. 2017, Mountain View, CA, USA, 2017, pp. 35–43.
[3] J. Varagula, P. A. N. Kulproma, and T. Itob, Object detection method in traffic by on-board computer vision with time delay neural network, in Proc. KES2017, Marseille, France, 2017, vol. 112, pp. 127–136. https://doi.org/10.1016/j.procs.2017.08.185
[4] H. Zhang, K. Wang, Y. Tian, C. Gou, and F. Y. Wang, MFR-CNN: Incorporating multi-scale features and global information for traffic object detection, IEEE Trans. Veh. Technol., vol. 67, no. 9, pp. 8019–8030, Sept. 2018, 10.1109/TVT.2018.2843394. https://doi.org/10.1109/TVT.2018.2843394
[5] Á. Arcos-García, J. A. Álvarez-García, and L. M. Soria-Morillo, Evaluation of deep neural networks for traffic sign detection systems, Neurocomputing, vol. 316, pp. 332–344, 2018, 10.1016/j.neucom.2018.08.009. https://doi.org/10.1016/j.neucom.2018.08.009
[6] M. Cordts et al., The cityscapes dataset for semantic urban scene understanding, in Proc. CVPR, Las Vegas, NV, USA, 2016, pp. 3213–3223. https://doi.org/10.1109/CVPR.2016.350
[7] G. Jocher, A. Stoken, J. Borovec, C. NanoCode012, L. Changyu, H. Laughing, ultralytics/yolov5: v4.0, Ultralytics, Jan. 5, 2021.
[8] F. Ö. Ünel, B. O. Özkalayci and C. Çiğla, The power of tiling for small object detection, in Proc. CVPRW, Long Beach, CA, USA, 2019, pp. 582-591. https://doi.org/10.1109/CVPRW.2019.00084
[9] J. Deng, J. Guo, Y. Zhou, J. Yu, I. Kotsia, S. Zafeiriou, RetinaFace: single-stage dense face localisation in the wild, arXiv: 1905.00641, 2019.
[10] Single Shot MultiBox Detector Implementation in Pytorch.
[11] Zalo AI Challenge.
[12] N. H. Dung, Application of convolution neural network in design and fabrication of robots for transporting goods in factories, J. Sci. Technol., vol. 147 (2020), pp. 51-58, Nov. 2020. https://doi.org/10.51316/30.8.9
[13] T. Y. Lin et al., Microsoft COCO: Common objects in context, Lect. Notes Comput. Sci., vol. 8693 LNCS, no. PART 5, pp. 740–755, 2014 https://doi.org/10.1007/978-3-319-10602-1_48
[14] Jetson Nano Developer.
[15] Jetson AGX Xavier Developer.