Abstract
In this article, we present the scientific outcomes of the 2019 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee of the IEEE Geoscience and Remote Sensing Society. The 2019 Contest addressed the problem of 3-D reconstruction and 3-D semantic understanding on a large scale. Several competitions were organized to assess specific issues, such as elevation estimation and semantic mapping from a single view, two views, or multiple views. In Part A, we report the results of the best-performing approaches for semantic 3-D reconstruction according to these various setups, whereas 3-D point cloud semantic mapping is discussed in Part B.
Original language | English (US) |
---|---|
Article number | 9229514 |
Pages (from-to) | 922-935 |
Number of pages | 14 |
Journal | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
Volume | 14 |
DOIs | |
State | Published - 2021 |
Keywords
- 3-D reconstruction
- Classification
- Data Fusion Contest (DFC)
- convolutional neural network (CNN)
- deep learning
- elevation model
- height estimation
- image analysis and data fusion (IADF)
- light detection and ranging (LiDAR)
- multiview
- point cloud
- semantic labeling
- semantic mapping
- stereo
ASJC Scopus subject areas
- Computers in Earth Sciences
- Atmospheric Science