Research and Analysis of Deep Learning in Environmental Perception for Autonomous Driving
DOI:
https://doi.org/10.61173/h73vsr83Keywords:
Autonomous Driving, Environmental Perception, Deep Learning, Computer VisionAbstract
Autonomous driving technology, as a revolutionary development in the transportation field, relies on efficient and reliable environmental perception systems. Deep learning plays a key role in the environmental perception of autonomous driving, with its capabilities widely applied in areas such as signal and sign recognition, semantic segmentation, instance segmentation, and SLAM (Simultaneous Localization and Mapping). This study conducts research and analysis on the aforementioned key technologies. It concludes that while deep learning technology has shown excellent performance in the perceptual systems of autonomous driving, it still faces challenges that require further research and resolution, such as generalization performance, eal-time requirements, and safety issues.
References
[1] Zheng, C., Guo, M., Zhou, C. (2024). Review of SLAM Algorithms Based on LiDAR. Digital Manufacturing Science, (02), 100-105.
[2] Guo, C. (2024, July 22). Behind the Popularity of “Luobo Kuai Pao” [News Article]. China Automotive News, p. 033. doi:10.28116/n.cnki.ncqcb.2024.000115.
[3] Zhao, L. (2024). Study on the Responsibility of Autonomous Vehicle in Traffic Accidents. China-Arab States Science and Dean&Francis Technology Forum (Bilingual Edition), 7, 152-156.
[4] Zhang, X., Chen, H., Li, Y. (2024). Application Practices of Automotive Data Processing Security Requirements National Standards in the Automotive Industry. Information Technology and Standardization (Supplement 1), 130-135.
[5] Zhu, X., Wang, B., & Lin, Y. (2023). Risks and countermeasures of artificial intelligence data security and privacy protection. Cybersecurity (03), 30-34.
[6] Wang, S., Dai, X., Xu, N. (2017). Overview on Environment Perception Technology for Unmanned Ground Vehicle. Journal of Changchun University of Science and Technology (Natural Science Edition), 1, 1-6.
[7] Wang, H., Luo, T., & Lu, P. (2018). Development of the lidar applications in unmanned vehicles and its key technology analysis. Laser & Infrared, 12, 1458-1467.
[8] Han, B., & Wang, Z. (2019). Overview of Development of Vehicle-mounted Millimeter-wave Radar at Home and Abroad. Digital Communication World, (09), 15-16.
[9] Liu, K., Dong, M., Wang, P. (2022). A traffic light recognition method based on image enhancement. Electronic Measurement Technology, (07), 137-145. doi:10.19651/j.cnki.emt.2108559.
[10] Li, X., Guo, X., & Guo, J. (2013). HOG-Feature and SVM Based Method for Forward Vehicle Recognition. Computer Science, S2, 329-332.
[11] Gao, X., Liao, Y., & Liu, L. (2024). Road condition detection based on adaptive random forest migration learning. Journal of Ningde Normal University (Natural Science Edition), (02), 143-151. doi:10.15911/j.cnki.35-1311/n.2024.02.003.
[12] Qin, Y., Cai, Y., Huang, P. (2023). Detection Method of Railway Signal Lights and Parking Carriages Based on Improved Faster R-CNN. Journal of Xihua University (Natural Science Edition), (02), 62-69.
[13] Kim, H.-K., Park, J. H., & Jung, H.-Y. (2018). An Efficient Color Space for Deep-Learning Based Traffic Light Recognition [Article]. Journal of Advanced Transportation, Article 2365414. https://doi.org/10.1155/2018/2365414
[14] Jensen, M. B., Philipsen, M. P., Mogelmose, A., Moeslund, T. B., & Trivedi, M. M. (2016). Vision for Looking at Traffic Lights: Issues, Survey, and Perspectives [Article]. Ieee Transactions on Intelligent Transportation Systems, 17(7), 1800- 1815. https://doi.org/10.1109/tits.2015.2509509
[15] Zhang, F., Yang, F., & Li, C. (2019). Fast Vehicle Detection Method Based on Improved YOLOv3. Computer Engineering and Applications, (02), 12-20.
[16] Huang, J., Liu, P., & Tang, W. (Year not specified). MMD- YOLOv7: Vehicle detection method under dark conditions. Computer Engineering, 1-12.
[17] Liang, X. (2023). Research on Traffic Sign Recognition for Autonomous Driving Scenarios [Master’s Thesis, Guangzhou University]. https://link.cnki.net/doi/10.27040/d.cnki. ggzdu.2023.001153
[18] Huang, Z., Sun, G., & Li, F. (2004). Traffic Sign Segment Based on RGB Vision Model. Microelectronics & Computer, 10, 147-148+152. doi:10.19304/j.cnki.issn1000-7180.2004.10.040.
[19] Barnes, N., Loy, G., & Shaw, D. (2010). The regular polygon detector [Article]. Pattern Recognition, 43(3), 592-602. https://doi.org/10.1016/j.patcog.2009.09.008
[20] Cireşan, D., Meier, U., Masci, J., & Schmidhuber, J. (2012). Multi-column deep neural network for traffic sign classification. Neural Networks, 32, 333-338. https://doi.org/https://doi. org/10.1016/j.neunet.2012.02.023
[21] Masci, J., Meier, U., Cireşan, D., & Schmidhuber, J. (2011). Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction. In T. Honkela, W. Duch, M. Girolami, & S. Kaski, Artificial Neural Networks and Machine Learning – ICANN 2011 Berlin, Heidelberg.
[22] Sermanet, P., & LeCun, Y. (2011, 31 July-5 Aug. 2011). Traffic sign recognition with multi-scale Convolutional Networks. The 2011 International Joint Conference on Neural Networks,
[23] Zeng, Y., Xu, X., Fang, Y., & Zhao, K. (2015). Traffic Sign Recognition Using Extreme Learning Classifier with Deep Convolutional Features.
[24] Tian, X., Wang, L., & Ding, Q. (2019). Review of Image Semantic Segmentation Based on Deep Learning. Journal of Software, (02), 440-468. doi:10.13328/j.cnki.jos.005659.
[25] Su, L., Sun, Y., & Yuan, S. (2022). A survey of instance segmentation research based on deep learning. Journal of Intelligent Systems, (01), 16-31.
[26] Yao, M., Deng, H., Fu, W. (2021). An Improved Mask R-CNN Image Instance Segmentation Algorithm. Software, (09), 78-82.
[27] Yuan, C., Lai, J., Zhang, J., & Lyu, P. (2018, 9-13 Jan. 2018). Research on an autonomously tightly integrated positioning method for UAV in sparse-feature indoor environment. 2018 15th International Bhurban Conference on Applied Sciences and Technology (IBCAST),
[28] LIU Peng, REN Gongchang, HE Zhou. Method for extracting corner feature from 2D laser SLAM[J]. Journal of Nanjing University of Aeronautics & Astronautics, 2021, 53(3): 366-372.
[29] Engel, J., Schöps, T., & Cremers, D. (2014). LSD-SLAM: Large-Scale Direct Monocular SLAM. In D. Fleet, T. Pajdla, B. Schiele, & T. Tuytelaars, Computer Vision – ECCV 2014 Cham.
[30] Bescos, B., Facil, J. M., Civera, J., & Neira, J. (2018). DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes [Article]. Ieee Robotics and Automation Letters, 3(4), 4076-4083. https://doi.org/10.1109/lra.2018.2860039
Downloads
Published
Issue
Section
License
Copyright (c) 2024 by the authors.
This work is licensed under a Creative Commons Attribution 4.0 International License.
