Offline Object Extraction from Dynamic Occupancy Grid Map Sequences
This provides an automatic labeling solution for ground truth data in automated driving, reducing time and cost, though it is incremental as it builds on existing dynamic occupancy grid map representations.
The paper tackles the problem of automatically extracting object poses and shapes from dynamic occupancy grid map sequences to avoid manual annotation, achieving a well-performing algorithm that works with real sensor data in challenging scenarios.
A dynamic occupancy grid map (DOGMa) allows a fast, robust, and complete environment representation for automated vehicles. Dynamic objects in a DOGMa, however, are commonly represented as independent cells while modeled objects with shape and pose are favorable. The evaluation of algorithms for object extraction or the training and validation of learning algorithms rely on labeled ground truth data. Manually annotating objects in a DOGMa to obtain ground truth data is a time consuming and expensive process. Additionally the quality of labeled data depend strongly on the variation of filtered input data. The presented work introduces an automatic labeling process, where a full sequence is used to extract the best possible object pose and shape in terms of temporal consistency. A two direction temporal search is executed to trace single objects over a sequence, where the best estimate of its extent and pose is refined in every time step. Furthermore, the presented algorithm only uses statistical constraints of the cell clusters for the object extraction instead of fixed heuristic parameters. Experimental results show a well-performing automatic labeling algorithm with real sensor data even at challenging scenarios.