Research on Monocular Depth Estimation for Autonomous Driving 


Vol. 48,  No. 12, pp. 1623-1632, Dec.  2023
10.7840/kics.2023.48.12.1623


PDF
  Abstract

To achieve autonomous driving, various sensors such as cameras, lidar, and radar are used to accurately perceive the surrounding environment. However, processing information from these multiple sensors for situational awareness requires significant costs, computational power, and introduces high latency. This poses practical challenges for real-time implementation in autonomous driving systems that require on-the-edge computing. Especially, research is actively underway to perform situation awareness using only cameras, without utilizing lidar or radar sensors that generate extensive 3D point cloud data. In this study, we explored ways to optimize the performance of Monocular Depth Estimation, a method that derives 3D information of the surrounding environment using only a single camera. We particularly focused on optimizing this approach by utilizing classical data augmentation techniques, proposing synthetic data augmentation methods, and employing appropriate loss functions to achieve the best results.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

J. Yoo, W. Jun, S. Lee, "Research on Monocular Depth Estimation for Autonomous Driving," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 12, pp. 1623-1632, 2023. DOI: 10.7840/kics.2023.48.12.1623.

[ACM Style]

Jisang Yoo, Woomin Jun, and Sungjin Lee. 2023. Research on Monocular Depth Estimation for Autonomous Driving. The Journal of Korean Institute of Communications and Information Sciences, 48, 12, (2023), 1623-1632. DOI: 10.7840/kics.2023.48.12.1623.

[KICS Style]

Jisang Yoo, Woomin Jun, Sungjin Lee, "Research on Monocular Depth Estimation for Autonomous Driving," The Journal of Korean Institute of Communications and Information Sciences, vol. 48, no. 12, pp. 1623-1632, 12. 2023. (https://doi.org/10.7840/kics.2023.48.12.1623)
Vol. 48, No. 12 Index

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880