Multilevel Cross-Aware RGBD Semantic Segmentation of Indoor Environments
- Resource Type
- Conference
- Authors
- Shi, Wenjun; Zhu, Dongchen; Zhang, Guanghui; Chen, Lili; Wang, Lei; Li, Jiamao; Zhang, Xiaolin
- Source
- 2019 IEEE International Conference on Cyborg and Bionic Systems (CBS) Cyborg and Bionic Systems (CBS), 2019 IEEE International Conference on. :346-351 Sep, 2019
- Subject
- Bioengineering
Components, Circuits, Devices and Systems
Computing and Processing
Engineered Materials, Dielectrics and Plasmas
Robotics and Control Systems
Signal Processing and Analysis
- Language
Semantic segmentation is the main step towards scene understanding which is one of the most important tasks of computer vision. As the depth and color information are independent, the combination of depth and RGB images can improve the quality of semantic labeling. In this paper, we proposed a multilevel cross-aware network (MCA-Net) for RGBD semantic segmentation to jointly reason about 2D appearance and depth geometric information. Our MCA-Net utilizes basic residual structure to encode texture information and depth geometric information respectively. Multilevel cross-aware fusion modules are designed to fuse multi-scale complementary features extracted from RGB and depth images. The proposed network produces high quality segmentation results of RGBD images particularly in indoor environments. The experiments conducted on Scannet dataset demonstrate the effectiveness of apperceiving and fusing multilevel features and that proposed MCA-Net outperforms state-of-the-art methods.