Video Analytics Suite

ATR Real-Time Detection & Tracking

Neuronic edge analytics detect, classify and track multiple targets in real time from EO and IR video, holding track identity through occlusion and platform motion.

Platform
EO/IR payload with Jetson class edge computer

What is demonstrated

This demonstration shows the Neuronic Video Analytics Suite performing automatic target recognition on live EO and IR video, with bounding boxes, target classes, persistent track IDs and a selected target held under precision tracking.

Capability

Automatic target recognition, multi-target tracking with persistent identity, re-identification after occlusion and EO/IR operation.

Why it is operationally useful

Operators cannot watch every frame of every feed. Turning video into classified, tracked targets at the edge shortens the detection-to-decision cycle and lets a single operator supervise several sensors.

Scenario

Mission sequence

  1. 01Live EO video is processed onboard the edge computer.
  2. 02Targets are detected and classified with confidence and class labels.
  3. 03Multiple tracks are maintained simultaneously with stable IDs.
  4. 04A target is selected for precision area-of-interest tracking.
  5. 05The target is occluded and re-identified when it reappears.
  6. 06The IR channel demonstrates the same performance at night.
  7. 07Target metadata is reported for downstream C2 and autonomy.

Transcript

Full narration transcript

Published in full so the demonstration is indexable and answerable by search and AI systems.

The feed shown is live EO video processed entirely onboard the platform's edge computer — no ground processing and no cloud.

Detections appear immediately with class labels for personnel and vehicles, each assigned a persistent track identifier.

As targets cross and separate, the tracker maintains identity rather than issuing new tracks.

The operator selects one target. Precision area-of-interest tracking locks onto it and drives the gimbal to keep it centred.

The target passes behind cover. When it re-emerges, re-identification restores the original track ID.

The same pipeline runs on the infrared channel, so the capability carries into night operations.

Throughout, target metadata is published to command and control and to the platform's autonomy layer.

Behind the demo

Video Analytics Suite

Edge-AI video analytics for automatic detection, classification and persistent tracking from EO and IR video.

  • Automatic Target Recognition (ATR)
  • Detection and classification of personnel, vehicles and aerial targets
  • Multi-target tracking with persistent track IDs
  • Re-identification after occlusion or field-of-view loss
  • Area-of-interest (AOI) precision tracking
  • EO and IR processing, day and night
View the product

Discuss your platform and mission

Tell us the platform, sensor and mission. We will walk you through integration options and arrange a technical demonstration.