Aerial Semantic PErception ENgine
See anything from the air — just by asking.
ASPEEN is a re-promptable aerial-perception SDK that turns a live or recorded drone video feed into an operator-steerable, depth-aware decision stream — open-vocabulary detect, segment and track, plus plain-language situational interpretation. Re-target what it looks for by prompting: no retraining, no new labels.
- Zero-retrain adaptation
- Real-time on a single GPU
- SDK + plugin architecture
A perception layer you steer at runtime
Turn a drone RGB feed into continuous, actionable interpretation — not just raw boxes.
-
Open-vocabulary vision
Detect, segment, and track arbitrary classes from a text or exemplar prompt in a single multiplexed pass.
-
Depth-aware objects
A depth enrichment plugin adds distance-to-object, fused per detection for range-to-target downstream.
-
Situational interpretation
A vision-language model elevates detections into a plain-language "what is happening" stream.
-
Plugin architecture
Enrichment capabilities hot-attach to the core loop over one shared mask + ROI contract.
See it on real aerial footage
Open-vocabulary detection, segmentation, and plain-language interpretation applied to a live-style drone feed.
local real-time pipeline.Core thesis
Re-prompt, not retrain.
Conventional aerial computer vision is closed-set: every new geography, weather condition, or target class means a retraining loop with fresh labels before the system is usable. ASPEEN adapts to a new operating domain by re-prompting an open-vocabulary model at runtime — usable detection with zero retraining and near-real-time performance on aerial RGB video.
Closed-set CV
- Fixed, pre-trained label set
- Retrain per domain
- New labels for every new task
ASPEEN
- Open vocabulary, prompt-driven
- Re-target live, no retrain
- Adapts to geography, weather, targets
A tri-directional adaptive loop
Not a linear source → model → user chain. Three coupled poles, all adapting live.
-
Input
Dynamic sources
Live feeds can change or switch mid-run.
-
Compute
Adaptive model
Re-prompted at runtime — no retrain, no restart.
-
Human
Adaptive prompts
The operator re-steers intent live.
-
Output
Decision stream
Continuous, operator-actionable interpretation.
Built for first responders. Useful far beyond them.
Primary frame: UAS for first responders — rapid search, situational awareness, and incident mapping. A dual-use path runs from long-range inspection through automated agriculture to public-safety operations, with real-time aerial perception throughout.
- First response Rapid search, situational awareness, and incident mapping
- Inspection Long-range infrastructure survey
- Agriculture Automated crop and field monitoring
- Public safety Scene assessment and coordinated response
Deliverable & posture
- Form
- An SDK — a library/API you integrate into your own stack, not a turnkey app.
- Performance
- Real-time on commodity end-user GPUs (~RTX 4090 / 32 GB VRAM class).
- Adaptation
- Demonstrated by live re-prompting on the same feed — zero retraining, zero new labels.
- Edge
- Edge deployment is a viable future migration path.
Request access to ASPEEN
Building aerial autonomy, inspection, or first-responder operations? Get in touch for an SDK evaluation.
Contact Flyvercity