Explain What You See: Open-Ended Segmentation and Recognition of Occluded 3D Objects
This addresses the limitation of existing methods in robotics for robust 3D object recognition under occlusion, though it appears incremental as it builds on prior Local-HDP and argumentation-based techniques.
The paper tackles the problem of recognizing occluded 3D objects in open-ended scenarios by proposing a semantic 3D object-parts segmentation method that improves mean intersection over union with fewer learning instances and integrates it with an argumentation-based learning method to handle high occlusion, producing explicit explanations for recognition.
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.