← Back to the chapter · Previous detail

Technical detail · Sensor Fusion Architectures

Metadata at each fusion level

At data level, combine measurements before feature extraction, usually after calibration and time alignment. Feature-level outputs need their schema, window, and sensor coverage. State-level outputs carry estimates, tracks, covariance, and confidence from local filters or trackers. Decision-level outputs carry alarms, classes, votes, or abstentions when lower-level evidence is unavailable.

LevelExampleRequired MetadataFailure Mode
DataTwo temperature probes fused after calibration and time alignment.Units, calibration id, event time, freshness, raw value, and accepted/rejected flag.Combining measurements that describe different times or units.
FeatureIMU and magnetometer features fused for motion-state classification.Feature schema, window, normalisation, sensor coverage, and feature version.Comparing features from different windows or preprocessing versions.
StateTrack-to-track fusion from two local Kalman filters.State vector, covariance, process model, time step, and correlation assumptions.Overconfident fusion because shared evidence is counted twice.
DecisionGateway alarm and cloud classifier vote on the same incident.Label definition, confidence, abstain rule, detector version, and voting policy.Voting over incompatible labels or suppressing low-confidence disagreement.

← Back to the chapter · Previous detail