Data Augmentation for Semantic Segmentation Using a Real Image Dataset Captured Around the Tsukuba City Hall

  • Ueda Yuriko
    Department of Computer Science, Graduate School of Science and Technology, Meiji University
  • Adachi Miho
    Department of Computer Science, Graduate School of Science and Technology, Meiji University
  • Morioka Junya
    Department of Computer Science, Graduate School of Science and Technology, Meiji University
  • Wada Marin
    Department of Computer Science, Graduate School of Science and Technology, Meiji University
  • Miyamoto Ryusuke
    Department of Computer Science, School of Science and Technology, Meiji University

この論文をさがす

抄録

<p>We are exploring the use of semantic scene understanding in autonomous navigation for the Tsukuba Challenge. However, manually creating a comprehensive dataset that covers various outdoor scenes with time and weather variations to ensure high accuracy in semantic segmentation is onerous. Therefore, we propose modifications to the model and backbone of semantic segmentation, along with data augmentation techniques. The data augmentation techniques, including the addition of virtual shadows, histogram matching, and style transformations, aim to improve the representation of variations in shadow presence and color tones. In our evaluation using images from the Tsukuba Challenge course, we achieved the highest accuracy by switching the model to PSPNet and changing the backbone to ResNeXt. Furthermore, the adaptation of shadow and histogram proved effective for critical classes in robot navigation, such as road, sidewalk, and terrain. In particular, the combination of histogram matching and shadow application demonstrated effectiveness for data not included in the base training dataset.</p>

収録刊行物

被引用文献 (1)*注記

もっと見る

参考文献 (23)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ