Fusion-Mask-RCNN: Visual robotic grasping in cluttered scenes.

Junyan Ge Lingbo Mao Jinlong Shi Yan Jiang

Published in: Multim. Tools Appl. (2024)

Keyphrases

cluttered scenes
partially occluded
shape matching
object models
object segmentation

multiple objects
low level
salient points
visual features

visual information
object class
object classes
static images

image segmentation
vision system
single image
multiscale