TSDF++: A Multi-Object Formulation for Dynamic Object Tracking and Reconstruction
This work addresses scalability and occlusion handling issues in dynamic object tracking and reconstruction for robotics, such as autonomous navigation, though it is incremental as it builds on existing TSDF frameworks.
The paper tackles the problem of simultaneously tracking and reconstructing multiple dynamic objects in robotic scenes by proposing TSDF++, a multi-object formulation that uses a single volume to encode all objects, preserving accurate reconstructions even during occlusions. It demonstrates this ability on a public synthetic dataset, showing improved performance over standard TSDF methods.
The ability to simultaneously track and reconstruct multiple objects moving in the scene is of the utmost importance for robotic tasks such as autonomous navigation and interaction. Virtually all of the previous attempts to map multiple dynamic objects have evolved to store individual objects in separate reconstruction volumes and track the relative pose between them. While simple and intuitive, such formulation does not scale well with respect to the number of objects in the scene and introduces the need for an explicit occlusion handling strategy. In contrast, we propose a map representation that allows maintaining a single volume for the entire scene and all the objects therein. To this end, we introduce a novel multi-object TSDF formulation that can encode multiple object surfaces at any given location in the map. In a multiple dynamic object tracking and reconstruction scenario, our representation allows maintaining accurate reconstruction of surfaces even while they become temporarily occluded by other objects moving in their proximity. We evaluate the proposed TSDF++ formulation on a public synthetic dataset and demonstrate its ability to preserve reconstructions of occluded surfaces when compared to the standard TSDF map representation.