OpenCV AI Competition 2026, powered by AWS: Build vision systems that see, reason, and act with OpenCV 5 and Amazon Web Services (AWS). Win money and bragging rights! - Devpost

ScenePilot AI — ScenePilot AI

ScenePilot AI is an intelligent vision agent that uses OpenCV 5 and AWS to detect visual changes, investigate uncertain images, adapt its next action, and verify results through a webcam.

SketchForge — SketchForge

Autonomous hand-drawn sketch-to-full-stack app generator with OpenCV 5, AWS Graviton & closed-loop visual repair.

AI-Powered Inventory Management Using Computer Vision — AI-Powered Inventory Management Using Computer Vision

VisionStock AI is an intelligent inventory management system that uses computer vision and AI to identify household and store items from images, track inventory levels, and generate low-stock alerts.

Paryavaran: Agentic Vision Greenspace Engine — Paryavaran: Agentic Vision Greenspace Engine

Rapid urbanization drives toxic smog and heat crises in Delhi. We use OpenCV 5 aerial vision on AWS to autonomously identify bare land and deploy targeted micro-forests and green corridors.

Motion QA — Motion QA

MotionQA flags visual anomalies in PCB images for human review. Built with OpenCV 5 and AWS, it preserves evidence for each inspection

BorderShield AI — BorderShield AI

BorderShield AI helps border officers screen passports, visas and national IDs in seconds, using OpenCV to flag tampering and a hash-chained audit trail to keep every decision verifiable.

CrackWatch — CrackWatch

A crack gauge in your pocket: any bank card held next to a wall crack gives the scale, OpenCV 5 measures its width in mm at fixed points and tells you if it is growing.

Blabla — Blabla

Blabla

Lawata: Satellite Triage for Lake Pollution — Lawata: Satellite Triage for Lake Pollution

Lawata watches Laguna de Bay from orbit: OpenCV 5 spots suspicious plumes, an AWS agent takes a closer look and checks the rain, and only a person can send a field team to sample.

InspectLoop — InspectLoop

An inspection agent for PCBs: OpenCV 5 checks the capture, compares it with a golden board, scores a DNN patch memory, zooms where the heatmap points and asks a person when unsure. Runs on AWS.

Smoke Sentinel — Smoke Sentinel

Early wildfire smoke on fire-watch cameras, found by classical OpenCV 5 change detection. Held-out AUC 0.846 across 43 unseen cameras, against 0.440 for the naive baseline.

Near-miss intersection safety analyzer — Near-miss intersection safety analyzer

Finds the traffic conflicts that never became crashes in overhead junction video, in metres on the road surface, so a city can fix a junction before someone is hurt.

Autonomous Mine Countermeasure Robot via Webots & OpenCV — Autonomous Mine Countermeasure Robot via Webots & OpenCV

An autonomous AGV simulation utilizing OpenCV spatial moments and HSV masking for real-time target tracking and dynamic obstacle avoidance with a priority-based state machine in Webots.

GuardianCV: Privacy-First Gait & Fall-Risk Vision — GuardianCV: Privacy-First Gait & Fall-Risk Vision

Privacy-first gait and fall-risk screening from ordinary camera video. OpenCV 5 pixel math, Kalman tracking and an auditable perception agent, with honest measured limits. FastAPI, Docker, AWS tested.

PHANToM Grid :: Autonomous Agentic Vision Nexus — PHANToM Grid :: Autonomous Agentic Vision Nexus

Real-time edge perception combining OpenCV 5, FastMCP, and AWS Bedrock AgentCore to autonomously detect anomalies and actuate industrial robotics with microsecond determinism.

Spatially Aware Property Inspection — Spatially Aware Property Inspection

One phone video becomes a measured, photoreal 3D model of the room. OpenCV 5 finds and pins damage, shows what was never filmed, and an AI agent proposes accept, repair or refer.

StageSight: a river camera that checks its own gauge — StageSight: a river camera that checks its own gauge

OpenCV 5 reads flood stage off public USGS staff-plate cameras with no gauge data; a Claude agent on AWS decides whether the camera or the gauge is wrong, and a person approves.

RoadSense — RoadSense

RoadSense uses computer vision and machine learning to analyze road videos, detect potential hazards, assess road risks, and support safer travel decisions with AWS-powered reporting.

smoke-rescue — smoke-rescue

Quadruped robots search a burning house with no floor plan, joining their maps over a lossy radio with OpenCV 5 visual SLAM, so they can find survivors before firefighters go in.

HoldSight: One Eye-Signal Engine for Driver & Brain Health — HoldSight: One Eye-Signal Engine for Driver & Brain Health

One OpenCV 5 engine on AWS that screens driver impairment and cognitive decline from eye signals in 80 seconds, and holds with a reason code instead of guessing when it cannot measure.

ProofPack — ProofPack

ProofPack helps packing teams turn OpenCV 5 measurements into correction requests, verify fresh evidence, and withdraw stale results when a kit changes.

STRATA — Version Control for the Physical World — STRATA — Version Control for the Physical World

OpenCV 5 change detection between two visits of a place: typed events, calibrated confidence, coverage of what it did not see. Human-gated.

NDM Vision:Edge Anthropometric Node for Pediatric Telehealth — NDM Vision:Edge Anthropometric Node for Pediatric Telehealth

Manual infant length readings are error-prone. NDM Vision uses an OpenCV camera node to measure length at the edge, feeding WHO z-scores and a cloud telehealth dashboard for remote clinicians.

ErgoSight CV — Edge OpenCV & AWS IoT Ergonomic Safety Coach — ErgoSight CV — Edge OpenCV & AWS IoT Ergonomic Safety Coach

Privacy-first edge CV ergonomics (REBA/NIOSH) on AWS IoT.

241 – 264 of 520