Advancements and Challenges in Visual Perception for Autonomous Driving

Haotang Wang

doi:10.62051/wawtq028

Authors

Haotang Wang

DOI:

https://doi.org/10.62051/wawtq028

Keywords:

Visual perception; Autonomous driving; Transfer Learning Survey.

Abstract

As autonomous driving has become more popular, research on the technology has proliferated. There are many schemes to realize autonomous driving, including visual perception, lidar, and radar. Among them, visual perception implements advanced neural networks and transfer learning to achieve excellent performance. This article mainly discusses the advantages of visual perception, the challenges it faces, and possible solutions, while comparing it with other schemes from various aspects at the same time. The approaches to the study mainly involve literature review and comparative analysis. The article concludes that visual perception will thrive and dominate the autonomous driving industry in the future. The prospect of development is also investigated, and some potential solutions that can improve the performance of autonomous driving are provided in the passage. This comprehensive analysis underscores the pivotal role of the visual perception in advancing autonomous driving technology, highlighting its cost-effectiveness, scalability, and future potential in transforming transportation.

Downloads

Download data is not yet available.

References

[1] Jiageng Mao, Shaoshuai Shi, Xiaogang Wang, Hongsheng Li. 3D object detection for autonomous driving: a comprehensive survey. International Journal of Computer Vision, 2023, 131(8): 1909-1963.

[2] Juan Zhong, Zheng Liu, Xi Chen. Transformer-based Models and Hardware Acceleration Analysis in Autonomous Driving: A Survey. arXiv preprint arXiv:2304.10891, 2023.

[3] Si Liu, Chen Gao, Yuan Chen, Xingyu Peng, Xianghao Kong, Kun Wang, Runsheng Xu, Wentao Jiang, Hao Xiang, Jiaqi Ma, Miao Wang. Towards vehicle-to-everything autonomous driving: a survey on collaborative perception. arXiv preprint arXiv:2308.16714, 2023.

[4] Keli Huang, Botian Shi, Xiang Li, Xin Li, Siyuan Huang, Yikang Li. Multi-modal sensor fusion for auto driving perception: a survey. arXiv preprint arXiv:2202.02703, 2022.

[5] Hrag Harout Jebamikyous, Rasha Kashef, Autonomous vehicles perception (avp) using deep learning: modeling, assessment, and challenges. IEEE Access, 2022, 10: 10523-10535.

[6] Shifeng Zhang, Longyin Wen, Zhen Lei, Stan Z. Li. RefineDet++: Single-shot refinement neural network for object detection. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 31(2), 674-687.

[7] Karthik Allam. Big data analytics in robotics: unleashing the potential for intelligent automation. EPH-International Journal of Business & Management Science, 2022, 8(4), 5-9.

[8] Ibrahim Sobh, Ahmed Hamed, Varun Ravi Kumar, Senthil Yogamani. Adversarial attacks on multi-task visual perception for autonomous driving, 2021, Electronic Imaging, 34.

[9] Luigi Bonati, Yueyu Zhang, Michele Parrinello. Neural networks-based variationally enhanced sampling. Proceedings of the National Academy of Sciences, 2019, 116(36), 17641-17647.