Operator-Truth Mission Management for Drone-Assisted Search & Rescue — integrating real-time AI detection, multi-object tracking, geospatial evidence fusion, and autonomous mission orchestration.
Timely detection and localisation of survivors in disaster-affected areas remains a critical challenge. GuardianEye bridges the gap between fragmented UAV tools and integrated, mission-aware SAR platforms.
Traditional ground-based search operations are constrained by terrain accessibility, visibility conditions, and physical endurance. Existing UAV-based SAR systems address individual components — such as detection or path planning — in isolation, leaving integration, evidence management, and operator coordination as afterthoughts.
This fragmentation increases cognitive load for operators and delays the critical detection-to-decision timeline, when every second counts in saving lives.
Raw frames processed through detection, tracking, geolocation, and fusion — each independently testable.
Frame-level detections are fused into geo-referenced clusters that persist across the mission timeline.
Five-panel real-time console with live telemetry, detection overlays, map view, alert triage, and mission replay.
A three-stage architecture that spans the entire pipeline from frame ingestion to operator alerting, with modular, independently testable components.
Frame ingestion from UAV camera or mobile edge nodes via REST API. Real-time video stream processing with GPS-synchronized telemetry capture.
Four-stage perception pipeline: YOLOv8 detection → Hungarian tracking → Pinhole geolocation → DBSCAN evidence fusion. Each module independently testable.
Prioritised evidence clusters surfaced via WebSocket, FSM-governed mission state transitions, coverage engine tracking, and operator console alerting.
YOLOv8n inference with configurable confidence threshold
Hungarian assignment + Kalman prediction tracking
Pinhole-camera pixel-to-GPS projection
DBSCAN clustering with haversine distance
Multi-factor weighted scoring engine
Async FSM-based mission lifecycle
Grid-based area tracking per sector
Timeline-indexed event playback & seek
Six core algorithms power GuardianEye's perception and decision pipeline, from frame-level detection to mission-level orchestration.
The perception pipeline uses an Ultralytics YOLOv8n model as the primary detection engine. Given a video frame, the detector produces bounding boxes, class labels, and confidence scores.
Detections below a configurable confidence threshold τ are discarded. The model runs at real-time speeds on commodity hardware.
Multi-object tracking associates detections across frames using optimal Hungarian assignment with Kalman prediction for persistent target identities.
Matches with IoU below θIoU (default 0.3) are rejected. A soft re-identification fallback uses centroid distance for occluded targets.
Projects pixel-space bounding-box centroids to GPS coordinates using a pinhole camera model with UAV pose data.
The centroid offset from frame centre is rotated by the heading angle and converted to geographic displacement using the GSD and local latitude. Achieves sub-3m accuracy.
Individual geo-estimates are fused into persistent evidence clusters using DBSCAN with a haversine-distance metric, eliminating parametric assumptions about target count.
Each cluster maintains a running centroid (weighted average), uncertainty radius, and cumulative metadata. This reduces false positives by 39.7% and improves cluster RMSE to 1.75 m.
Evidence clusters are ranked by a composite weighted score to surface the most critical targets to operators.
Person targets receive class weight 1.0; vehicles 0.6; unknown classes default to 0.3. Persistence is capped at 5 observations, and recency uses exponential decay.
The orchestrator enforces strict state transitions through a finite-state machine, ensuring safe and deterministic mission execution.
An Abort state is reachable from any airborne state. Precheck validates GPS lock, battery margin, geofence integrity, and service health. The revisit policy evaluates 5 criteria including battery margin ≥ 30%, uncertainty > 25m, and cooldown ≥ 60s.
Production-grade tools chosen for reliability, performance, and real-time operation on commodity hardware.
High-performance REST/WebSocket API with async support
Ultralytics real-time object detection inference
Pure-Python Hungarian tracker with no external dependencies
Density-based clustering with haversine distance metric
PX4-compatible UAV flight controller interface
Real-time 5-panel operator console with Canvas overlays
One-command reproducible evaluation environment
50-iteration OTMC evaluation with ground-truth comparison — 40 completed iterations exercising the real mission-management path under repeatable perturbations.
| Metric | DBSCAN On | DBSCAN Off | Delta | Improvement |
|---|---|---|---|---|
| Mean F1 Score | 0.421 | 0.318 | +0.103 | +32.4% |
| Cluster RMSE (m) | 1.75 | 2.30 | −0.55 | −23.9% |
| Mean Localization Error (m) | 1.79 | — | — | — |
| False Positive Reduction | 39.7% | vs non-clustering ablation | ||
| Metric | Blockers On | Blockers Off |
|---|---|---|
| Missions Completed | 17 | 23 |
| Missions Blocked | 10 | 0 |
| Block Rate | 37.0% | 0.0% |
| Total Iterations | 27 | 23 |
Five-panel surveillance-grade layout designed for maximum situational awareness during active SAR missions.
Persistent system health indicators — connection status, GPS lock, battery level, mission mode, and clock.
Ten-section sidebar: live feed, mission control, detections, coverage, evidence, alerts, replay, devices, logs, and settings.
Live video feed with real-time AI bounding-box overlays rendered on HTML5 Canvas at 30 FPS.
Tabbed display for interactive map, telemetry graphs, priority alerts, and target tracking status.
One-click controls: connect, camera toggle, record, AI toggle, patrol mode, RTL, and emergency stop.
Comparing GuardianEye against recent UAV SAR systems across detection, tracking, fusion, evaluation, and safety dimensions.
| System | Detection | Tracking | Geolocation | Evidence Fusion | Mission Mgmt. | Safety | Evaluation |
|---|---|---|---|---|---|---|---|
| Lygouras et al. | CNN | None | GPS only | None | Manual | No | Field test |
| Mishra et al. | YOLOv5 | None | None | None | None | No | Offline batch |
| Bejiga et al. | CNN | None | None | None | None | No | Offline batch |
| SORT | Any | Kalman+IoU | None | None | None | No | MOT bench |
| DeepSORT | Any | Kalman+Deep | None | None | None | No | MOT bench |
| GuardianEye | YOLOv8n | Hungarian+Kalman | Pinhole+Raycast | DBSCAN+Haversine | FSM+OTMC | 6-condition | 50-iter MC |