Projects / PennApps XXVI
Award winnerCATEGORY - Privacy / SecurityConfidence: low
Superhuman
A swarm of AI agents searches CCTV footage in parallel, restores damaged frames and matches suspects from text descriptions.
Project facts
- Team
- 2 people
- Build
- software only
- AI
- multi agent, computer vision, generative media
Problem
Investigators review surveillance footage clip by clip, too slowly for urgent cases.
Solution
Over twenty agents analyse feeds in parallel; video inpainting restores occluded frames; vision-language models and face re-identification match natural-language descriptions; a generative layer predicts trajectories.
Demo moment
Team-described: describe a person and see matching clips across cameras.
Why it stood out
- organizer statedWon “CATEGORY - Privacy / Security” among 85 submissions.Source ↗
- team statedStacks many techniques (inpainting, re-identification, VLM retrieval) in one pipeline.Source ↗
- curator inferenceWon the privacy and security category while being a surveillance tool; the civil-liberties trade-off is not addressed in its summary.
Lessons for your next hackathon
- Technical depth can win a security category, but expect hard questions on misuse.
Similar situations
Projects that share domains, mechanisms or judging lenses — often with a different problem and stack.Tune the comparison.
Award winner · 2026
Upload an executable and get readable code, its behaviours and a safety verdict before you run it.
Shared: domains security networking · mechanisms visible engineering depth · lenses technical depth · stack next.js, python
Award winner · 2025
Turns a video, even from a Raspberry Pi feed, into an interactive animated 3D scene in the browser.
Shared: mechanisms demo first wow, visible engineering depth · lenses technical depth · ai computer vision, generative media · stack next.js, python
Award winner · 2025
Turns packet captures into plain-English, evidence-backed security narratives.
Shared: domains security networking · lenses technical depth · stack python
Award winner · 2025
AI agents that align schemas and merge data when two financial institutions combine.
Shared: mechanisms visible engineering depth · lenses technical depth · ai multi agent · stack python
Award winner · 2026
Draw annotations on medical video and they stay attached to the anatomy as it moves.
Shared: mechanisms visible engineering depth · lenses technical depth · ai computer vision · stack python, opencv
Award winner · 2026
Detects market regimes from order-book microstructure and switches trading strategy before instability hits.
Shared: mechanisms visible engineering depth · lenses technical depth · stack python
Sources
- https://devpost.com/software/superhuman · devpost project · retrieved 2026-10-13
- https://pennapps-xxvi.devpost.com/project-gallery · devpost gallery · retrieved 2026-10-13