Monocular vehicle perception and calibration based on U-Net and prior knowledge

Qiyuan Hu; Zhiheng Zhao; Sijie Luo; Yong Liu; Zhihao Gu

doi:10.1117/12.2647483

23 August 2022 Monocular vehicle perception and calibration based on U-Net and prior knowledge

Qiyuan Hu, Zhiheng Zhao, Sijie Luo, Yong Liu, Zhihao Gu

Proceedings Volume 12330, International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2022); 123300L (2022) https://doi.org/10.1117/12.2647483
Event: International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2022), 2022, Huzhou, China

Abstract

Monocular vehicle perception has been a vital problem in autonomous driving. Anchor-based detectors are always used to solve the problem but the used bounding box’s center to calibrate is actually not corresponded with vehicle’s 3D center. Therefore, we designed a perception network by point detector U-Net and propose a calibration method by using the 3D2D reprojection constraints and a prior plane in the imaging system. We evaluate our method on the ApolloCar3D dataset, and the experimental results prove that the proposed network is feasible and the calibration is effective. On the ApolloCar3D testing dataset, the mean average precision of the proposed network is 0.022, and can be well improved to 0.040 with our calibration method, which is competitive compared to other algorithms.

Citation Download Citation

Qiyuan Hu, Zhiheng Zhao, Sijie Luo, Yong Liu, and Zhihao Gu "Monocular vehicle perception and calibration based on U-Net and prior knowledge", Proc. SPIE 12330, International Conference on Cyber Security, Artificial Intelligence, and Digital Economy (CSAIDE 2022), 123300L (23 August 2022); https://doi.org/10.1117/12.2647483

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available