Table-Top Scene Analysis Using Knowledge-Supervised MCMC
This work addresses scene understanding for robotics or computer vision applications, but it appears incremental as it builds on existing probabilistic and knowledge-based methods.
The paper tackles the problem of generating abstract scene graphs for table-top scenes from uncertain 6D object pose estimates by using a probabilistic method that incorporates task-specific knowledge encoded in Markov logic networks, with results demonstrated in real-world experiments.
In this paper, we propose a probabilistic method to generate abstract scene graphs for table-top scenes from 6D object pose estimates. We explicitly make use of task-specfic context knowledge by encoding this knowledge as descriptive rules in Markov logic networks. Our approach to generate scene graphs is probabilistic: Uncertainty in the object poses is addressed by a probabilistic sensor model that is embedded in a data driven MCMC process. We apply Markov logic inference to reason about hidden objects and to detect false estimates of object poses. The effectiveness of our approach is demonstrated and evaluated in real world experiments.