Vision-Touch Fusion for Predicting Grasping Stability Using Self Attention and Past Visual Images.
Gang YanZhida QinSatoshi FunabashiAlexander SchmitzTito Pradhono TomoSophon SomlorLorenzo JamoneShigeki SuganoPublished in: ICDL (2023)
Keyphrases
- vision system
- visual appearance
- ground truth
- three dimensional
- image database
- visual environment
- input image
- image data
- visual input
- object recognition
- multiple images
- visual field
- visual perception
- web images
- image registration
- observed scene
- visual tasks
- image classification
- visual attention
- human observers
- fusion methods
- image collections
- image set
- image matching
- image regions
- segmentation algorithm
- edge detection
- low level
- image features
- test images
- visual information
- eye tracking
- data fusion
- single image
- selective attention
- image analysis
- real time