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
Search this article
Abstract
<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>
Journal
-
- Journal of Robotics and Mechatronics
-
Journal of Robotics and Mechatronics 35 (6), 1450-1459, 2023-12-20
Fuji Technology Press Ltd.
- Tweet
Details 詳細情報について
-
- CRID
- 1390861471537539584
-
- NII Book ID
- AA10809998
-
- ISSN
- 18838049
- 09153942
-
- NDL BIB ID
- 033224231
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- NDL
- Crossref
-
- Abstract License Flag
- Disallowed