Unsupervised object individuation from RGB-D image sequences

In this paper, we propose a novel unified framework for unsupervised object individuation from RGB-D image sequences. The proposed framework integrates existing location-based and feature-based object segmentation methods to achieve both computational efficiency and robustness in unstructured and dynamic situations. Based on the infant's object indexing theory, the newly proposed ambiguity graph plays as a key component of the framework to detect falsely segmented objects and rectify them by using both location and feature information. In order to evaluate the proposed method, three table-top multiple object manipulation scenarios were performed: stacking, unstacking, and occluding tasks. The results showed that the proposed method is more robust than the location-only method and more efficient than the feature-only method.

Authors

• Seong-Yong Koo
• Dongheui Lee
• Dong-Soo Kwon

Keywords

• Indexing
• Robustness
• Gaussian distribution
• Shape
• Robot sensing systems
• Image color analysis
• RGB-D Image Sequences
• Computational Efficiency
• Local Information
• Feature Information
• Multiple Objects
• Objective Indicators
• Object Segmentation
• Dynamic Situations
• Object Location
• Directed Graph
• Objective Information
• Target Object
• Gaussian Mixture Model
• Situation Changes
• Correction Process
• Depth Camera
• Individual Objects
• Object Parts
• Human Hand
• Point Cloud Data
• Multiple Object Tracking
• Unknown Objects
• Kullback-Leibler Distance
• Robot Operating System
• Unstructured Environments
• Separate Individuals
• Occluded Objects
• Robust Problem
• Weight Function