A review of point cloud and image cross-modal fusion for self-driving.
Nan MaChuansheng XiaoMohan WangGenbao XuPublished in: CIS (2022)
Keyphrases
- point cloud
- cross modal
- image retrieval
- image data
- input image
- image features
- multi modal
- image content
- image collections
- image representation
- laser scanner
- image classification
- visual similarity
- visual data
- computer vision
- image segmentation
- image regions
- low level
- visual recognition
- distance measure
- image matching
- d objects
- high resolution
- multimedia databases
- high dimensional
- keywords
- multimedia