Smartphone indoor localization requires low-cost, robust positioning across scene transitions and phone-use variations. Pedestrian dead reckoning (PDR) enables infrastructure-free deployment but accumulates errors from heading drift, structural transitions, and carrying-mode changes. Existing methods often treat contextual cues as a single event stream or local correction signal, limiting their ability to address distinct localization errors. This paper presents a framework enhanced by hierarchical multi-sensor context recognition.
Scene-event segment processing
- A jointly data- and model-driven recognition model predicts environment, scene, and activity probabilities, which are converted into scene-event and action-context segments.
- Scene-event segments guide scene-constrained PDR correction through corridor heading constraints.
- They also enable landmark attraction.
- They incorporate fixed-lag backtracking.
- They handle vertical-transition handling.
Action-context segment processing
- Action-context segments drive action-aware RoNIN-based position compensation.
- This compensation targets carrying-mode-dependent drift.
Experiments on cross-floor and multi-action trajectories against LiDAR-SLAM references show that the proposed framework outperforms PDR and representative learned inertial odometry baselines. They demonstrate that hierarchical semantics provide reliable, localization-specific correction cues.