Probabilistic multi-class segmentation for the Amazon Picking Challenge

We present a method for multi-class segmentation from RGB-D data in a realistic warehouse picking setting. The method computes pixel-wise probabilities and combines them to find a coherent object segmentation. It reliably segments objects in cluttered scenarios, even when objects are translucent, reflective, highly deformable, have fuzzy surfaces, or consist of loosely coupled components. The robust performance results from the exploitation of problem structure inherent to the warehouse setting. The proposed method proved its capabilities as part of our winning entry to the 2015 Amazon Picking Challenge. We present a detailed experimental analysis of the contribution of different information sources, compare our method to standard segmentation techniques, and assess possible extensions that further enhance the algorithm's capabilities. We release our software and data sets as open source.

Authors

• Rico Jonschkowski
• Clemens Eppner
• Sebastian Höfer
• Roberto Martín-Martín
• Oliver Brock

Keywords

• Robots
• Image color analysis
• Image segmentation
• Histograms
• Three-dimensional displays
• Probabilistic logic
• Robustness
• Multi-class Segmentation
• Amazon Picking Challenge
• Source Of Information
• Object Segmentation
• Random Forest
• Object Detection
• Bounding Box
• Number Of Objects
• Target Object
• Color Features
• Gaussian Blur
• Post-processing Step
• Pose Estimation
• Distinct Color
• Object Parts
• Back Projection
• Segment Size
• Different Sources Of Information
• Label Of Pixel
• Iterative Closest Point
• RGB-D Images
• Perception Of The Robot
• Object Pose
• Nearby Pixels
• Color Histogram
• Perceptual System
• μM Values
• Random Forest Classifier
• Robot Manipulator
• Continuous Values