A Study on Trade-off Evaluation by Simplifying Propagation Process of Vehicle Trajectory Prediction Model Based on Deep Learning 


Vol. 46,  No. 5, pp. 914-922, May  2021
10.7840/kics.2021.46.5.914


PDF Full-Text
  Abstract

In this paper, a method of simplifying the propagation process to improve the performance in the trade-off relationship between prediction accuracy and prediction time of vehicle trajectory prediction model based on deep learning is proposed. In vehicle trajectory prediction tasks, it is possible to predict increasingly high accuracy by using deep learning technology, but on the other hand, a trade-off problem occurred because of the increasing the prediction time of the model according to increased complexity. To solve this problem, various simplifying methods of propagation process were applied to the existing deep learning based state-of-the-art vehicle trajectory prediction model and the prediction accuracy and prediction time were measured through the experiments. In case of simplifying from the process to extract the Dynamic Motion features of neighboring vehicles, the predicted time was reduced by 15.7% in the PC environment and 2.1% in the embedded environment without any loss of the predicted accuracy.

  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.


  Cite this article

[IEEE Style]

G. Oh, H. Kim, S. Lim, "A Study on Trade-off Evaluation by Simplifying Propagation Process of Vehicle Trajectory Prediction Model Based on Deep Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 5, pp. 914-922, 2021. DOI: 10.7840/kics.2021.46.5.914.

[ACM Style]

Geesung Oh, Heejung Kim, and Sejoon Lim. 2021. A Study on Trade-off Evaluation by Simplifying Propagation Process of Vehicle Trajectory Prediction Model Based on Deep Learning. The Journal of Korean Institute of Communications and Information Sciences, 46, 5, (2021), 914-922. DOI: 10.7840/kics.2021.46.5.914.

[KICS Style]

Geesung Oh, Heejung Kim, Sejoon Lim, "A Study on Trade-off Evaluation by Simplifying Propagation Process of Vehicle Trajectory Prediction Model Based on Deep Learning," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 5, pp. 914-922, 5. 2021. (https://doi.org/10.7840/kics.2021.46.5.914)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880