Improving generalization for 3D object categorization with Global Structure Histograms

We propose a new object descriptor for three dimensional data named the Global Structure Histogram (GSH). The GSH encodes the structure of a local feature response on a coarse global scale, providing a beneficial trade-off between generalization and discrimination. Encoding the structural characteristics of an object allows us to retain low local variations while keeping the benefit of global representativeness. In an extensive experimental evaluation, we applied the framework to category-based object classification in realistic scenarios. We show results obtained by combining the GSH with several different local shape representations, and we demonstrate significant improvements to other state-of-the-art global descriptors.

Authors

• Marianna Madry
• Carl Henrik Ek
• Renaud Detry
• Kaiyu Hang
• Danica Kragic

Keywords

• Histograms
• Robustness
• Encoding
• Databases
• Image color analysis
• Shape
• Data models
• Global Structure
• Global Histogram
• Local Features
• Real Scenarios
• Experimental Evaluation
• Object Features
• Global Descriptors
• Extensive Experimental Evaluation
• Real Applications
• Discriminatory Power
• Point Cloud
• Global Information
• Distance Distribution
• K-means Algorithm
• Amount Of Training Data
• Training Examples
• Objective Structured
• Bag-of-words
• Local Descriptors
• Object Pose
• Partial View
• Global Representation
• Object Instances
• Point In The Graph
• Description Of Surface
• Object Point Cloud
• Object Point
• Sensor Noise
• Incomplete Model