TLCFuse: Temporal Multi-Modality Fusion Towards Occlusion-Aware Semantic Segmentation-Aided Motion Planning.
Gustavo Salazar-GomezWenqian LiuManuel Diaz-ZapataDavid Sierra GonzálezChristian LaugierPublished in: CoRR (2023)
Keyphrases
- multi modality
- motion planning
- semantic segmentation
- street scenes
- multi modal
- humanoid robot
- information theoretic
- medical images
- degrees of freedom
- superpixels
- image registration
- conditional random fields
- mobile robot
- path planning
- mutual information
- weakly supervised
- scene classification
- spatio temporal
- multi robot
- object categories
- object class
- object classes
- multiscale
- viewpoint
- biologically inspired
- image classification
- object detection
- deformation field
- image processing
- partial occlusion
- pose estimation
- pairwise
- dynamic environments
- higher order
- image sequences
- image segmentation