Predictive 3D Content Streaming Based on Decision Tree Classifier Approach

3D content streaming and rendering system has attracted a significant attention from both academia and industry. However, these systems struggle to provide comparable quality to that of locally stored and rendered 3D data. Since the rendered 3D content on to the client machine is controlled by the users, their interactions have a strong impact on the performance of 3D content streaming and rendering system. Thus, considering user behaviours in these systems could bring significant performance improvements. Towards the end, we propose a decision tree that captures all parameters making part of user interactions. The decision trees are built from the information found while interacting with various types of 3D content by different set of users. In this, the 3D content could be static or dynamic 3D object/scene. We validate our model through another set of interactions over the 3D contents by same set of users. The validation shows that our model can learn the user interactions and is able to predict several interactions helping thus in optimizing these systems for better performance. We also propose various approaches based on traces collected from the same/different users to accelerate the learning process of the decision tree.