Context-Aware Sensor Modeling for Asynchronous Multi-Sensor Tracking in Stone Soup
This work addresses a domain-specific problem for multi-sensor tracking systems, offering an incremental improvement by integrating context-aware modeling into existing frameworks.
The paper tackled the problem of multi-sensor tracking with asynchronous sensors, where uniform observability assumptions degrade fusion performance, and introduced DetectorContext in Stone Soup to enable state-dependent detection modeling, resulting in restored stable fusion and significant improvements in HOTA and GOSPA metrics without increasing false tracks.
Multi-sensor tracking in the real world involves asynchronous sensors with partial coverage and heterogeneous detection performance. Although probabilistic tracking methods permit detection probability and clutter intensity to depend on state and sensing context, many practical frameworks enforce globally uniform observability assumptions. Under multi-rate and partially overlapping sensing, this simplification causes repeated non-detections from high-rate sensors to erode tracks visible only to low-rate sensors, potentially degrading fusion performance. We introduce DetectorContext, an abstraction for the open-source multi-target tracking framework Stone Soup. DetectorContext exposes detection probability and clutter intensity as state-dependent functions evaluated during hypothesis formation. The abstraction integrates with existing probabilistic trackers without modifying their update equations. Experiments on asynchronous radar-lidar data demonstrate that context-aware modeling restores stable fusion and significantly improves HOTA and GOSPA performance without increasing false tracks.