Explain What You See: Open-Ended Segmentation and Recognition of Occluded 3D Objects

TL;DR

This paper introduces a novel semantic 3D object-parts segmentation method suitable for open-ended scenarios, and integrates it with online learning to improve recognition robustness under occlusion in robotic applications.

Contribution

It presents a flexible segmentation approach for open-ended 3D object recognition and combines it with argumentation-based online learning to handle occlusion effectively.

Findings

Higher mean intersection over union with fewer learning instances

Enhanced robustness to occlusion in 3D object recognition

Provides explicit explanations for recognition decisions

Abstract

Local-HDP (for Local Hierarchical Dirichlet Process) is a hierarchical Bayesian method that has recently been used for open-ended 3D object category recognition. This method has been proven to be efficient in real-time robotic applications. However, the method is not robust to a high degree of occlusion. We address this limitation in two steps. First, we propose a novel semantic 3D object-parts segmentation method that has the flexibility of Local-HDP. This method is shown to be suitable for open-ended scenarios where the number of 3D objects or object parts is not fixed and can grow over time. We show that the proposed method has a higher percentage of mean intersection over union, using a smaller number of learning instances. Second, we integrate this technique with a recently introduced argumentation-based online incremental learning method, thereby enabling the model to handle a high degree of occlusion. We show that the resulting model produces an explicit set of explanations for the 3D object category recognition task.