Deep Learning Methods for Semantic Segmentation of Dense 3D SLAM Maps
-
- Yingjian Pei
- MIST, Kyushu Institute of Technology
-
- Chumkamon Sakmongkon
- MIST, Kyushu Institute of Technology
-
- Hayashi Eiji
- MIST, Hayashi Lab
説明
Most real-time SLAM systems can only achieve semi-dense mapping, and the robot lacks specific knowledge of the mapping results, so it can only achieve simple positioning and obstacle avoidance, which may be used as an obstacle in the face of the target object to be grasped, thus affecting the realization of motion planning. The use of semantic segmentation in dense SLAM maps allows the robot to better understand the map information, distinguish the meaning of different blocks in the map by semantic labels, and achieve fast feature matching and Loop Closure Detection based on the relationship between semantic labels in the scene. There are many semantic segmentation datasets based on street scenes and indoor scenes available for use, and these datasets have some common tags. Based on these training data, we can derive a semantic segmentation model based on RGB images by using the Pytorch platform for training.
収録刊行物
-
- 人工生命とロボットに関する国際会議予稿集
-
人工生命とロボットに関する国際会議予稿集 26 764-767, 2021-01-21
株式会社ALife Robotics
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390288225748889728
-
- NII論文ID
- 120007038827
-
- ISSN
- 21887829
- 24359157
-
- HANDLE
- 10228/00008271
-
- 本文言語コード
- en
-
- 資料種別
- conference paper
-
- データソース種別
-
- JaLC
- IRDB
- Crossref
- CiNii Articles
- OpenAIRE
-
- 抄録ライセンスフラグ
- 使用不可