Automatic Training Data Generation Method for Pixel-Level Road Lane Segmentation

Xun Pan, Yutian Wu, Harutoshi Ogai

研究成果: Conference contribution

抄録

Lane detection or road detection is one of the key features of autonomous driving. By using deep convolutional neural network based semantic segmentation, we can build models with high accuracy and robustness. However, training a pixel-level semantic segmentation needs very fine-labeled training data, which requires large amount of labor. In this paper, we propose an automatic training data generating method, which can significantly reduce the effort of the training phase. Experiments prove that our method can generate high-quality training data for lane segmentation task.

本文言語English
ホスト出版物のタイトルGenetic and Evolutionary Computing - Proceedings of the 12th International Conference on Genetic and Evolutionary Computing, 2018
編集者Shih-Pang Tseng, Bixia Sui, Jeng-Shyang Pan, Jerry Chun-Wei Lin
出版社Springer-Verlag
ページ473-481
ページ数9
ISBN(印刷版)9789811358401
DOI
出版ステータスPublished - 2019 1 1
イベント12th International Conference on Genetic and Evolutionary Computing, ICGEC 2018 - Changzhou, China
継続期間: 2018 12 142018 12 17

出版物シリーズ

名前Advances in Intelligent Systems and Computing
834
ISSN(印刷版)2194-5357

Conference

Conference12th International Conference on Genetic and Evolutionary Computing, ICGEC 2018
CountryChina
CityChangzhou
Period18/12/1418/12/17

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science(all)

フィンガープリント 「Automatic Training Data Generation Method for Pixel-Level Road Lane Segmentation」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル