Skybird
Built on Kundi · Deployed in Government
Person detection, tracking, and trajectory analysis for video. Skybird identifies a target across frames, recovers from occlusions when subjects pass behind obstacles, identifies what caused each occlusion, and emits structured trajectory data for downstream analysis — designed to run inside government and security environments. The deploying agency owns the models, their weights, and any improvement derived from its data.
See Skybird work.
Click a window, or its green button, to read it full-screen.
Persistent identity across frames, even through occlusion.
Detection and tracking models run inside the Kundi deployment like any other model. Skybird combines a person tracker that keeps identity across frames, an open-vocabulary scene detector and an occlusion-aware track-merge layer — producing browser-ready annotated video plus per-frame structured output.
-
Person Tracking With Re-Identification
Re-identification for consistent tracking of a target person across frames, including across short disappearances.
-
Multi-Person Annotation
All detected persons get labeled bounding boxes with unique IDs in the output video — not just the target.
-
Occlusion Recovery
Merges broken track fragments when a person passes behind an obstacle (tree, pole, vehicle, structure), preserving identity continuity through gaps.
-
Obstacle Identification
Open-vocabulary detection identifies what caused each occlusion ("tree trunk", "parked vehicle", "wall"), enabling explainable track recoveries.
-
Open-Vocabulary Scene Detection
Periodic rescans catch scene objects entering the frame: vehicles, structures, street furniture, foreground items, traffic infrastructure.
-
Proximity Alerts
Configurable spatial alerts — e.g., the screen flashes when the target enters a defined proximity to a detected scene object.
-
Trajectory Output (JSON)
Per-frame bounding boxes, centers, timestamps, and confidence scores emitted as structured JSON for downstream analytics, dashboards, or replay.
-
Browser-Ready Video
H.264 + faststart encoding for direct browser playback of annotated output without external transcode steps.
Quantum-Resilient, aligned to the federal clock.
Skybird runs on Kundi inside government and security environments, with post-quantum cryptography as standard. Trajectory data, annotated video, and identity products are long-lived intelligence — protected against harvest-now, decrypt-later collection and aligned with the federal PQC mandates your mission already tracks.
-
Aligned With Federal PQC Deadlines
Post-quantum cryptography is standard. See Security & Compliance for algorithms and verification.
-
Protects Long-Lived Collection
Trajectory JSON and video evidence keep their sensitivity for years. Post-quantum cryptography protects them today against adversaries harvesting encrypted traffic to decrypt later.
-
Runs Where You Operate
Post-quantum protection travels with the deployment — on-premises or air-gapped, inside the government infrastructure Skybird already runs in. Crypto-agile, so algorithms rotate as NIST standards advance.
See it inside your environment.
Live Skybird walkthroughs in your environment are available under NDA. Request a briefing to see the live tracker, occlusion-recovery output, and structured trajectory data running against representative video sources.