Dynamic Semantic Occupancy Mapping using 3D Scene Flow and Closed-Form Bayesian Inference
This work addresses mapping inconsistencies for robotics and autonomous systems by integrating dynamic object handling, though it appears incremental as it builds on existing methods with flow and Bayesian inference.
The paper tackles the problem of dynamic objects causing artifacts in mapping algorithms by developing a framework that incorporates 3D scene flow into a closed-form Bayesian inference model, resulting in a 3D continuous semantic occupancy map that outperforms static counterparts and improves over predecessors and input measurements consistently in experiments.
This paper reports on a dynamic semantic mapping framework that incorporates 3D scene flow measurements into a closed-form Bayesian inference model. Existence of dynamic objects in the environment can cause artifacts and traces in current mapping algorithms, leading to an inconsistent map posterior. We leverage state-of-the-art semantic segmentation and 3D flow estimation using deep learning to provide measurements for map inference. We develop a Bayesian model that propagates the scene with flow and infers a 3D continuous (i.e., can be queried at arbitrary resolution) semantic occupancy map outperforming its static counterpart. Extensive experiments using publicly available data sets show that the proposed framework improves over its predecessors and input measurements from deep neural networks consistently.