Multimodal Deep-Learning for Object Recognition Combining Camera and LIDAR Data.
Gledson MelottiCristiano PremebidaNuno M. M. da S. GonçalvesPublished in: ICARSC (2020)
Keyphrases
- deep learning
- lidar data
- object recognition
- unsupervised learning
- machine learning
- field of view
- point cloud
- high resolution
- urban environments
- computer vision
- urban areas
- d objects
- structure from motion
- hyperspectral imagery
- mental models
- video camera
- camera motion
- natural images
- weakly supervised
- image segmentation
- multiscale
- image sequences
- higher order
- multiple images
- object detection
- image features
- viewpoint
- image processing
- panoramic images