04 / VISION SYSTEMS
Computer vision systems I've built.
Detection, tracking, and inspection that run on real cameras in real places, plus the datasets, dashboards, and pipelines around them. Computer vision is where I started.
LIVE DEMOS
Watch them work, or press a key and try.
Computer vision
Cameras that detect, count, and flag defects on real production lines, in real time. It's where I started.
HOW THEY'RE BUILT
From pixels to decisions.
- 01CaptureCameras, streams, calibration
- 02DetectOptimized models on GPU or edge
- 03TrackIdentities across frames
- 04ReasonZones, rules, events
- 05DeliverDashboards, alerts, APIs
WHAT I'VE BUILT
Platforms, systems, and pipelines.
Mask0
A private computer vision data platform for importing, annotating, validating, versioning, and exporting datasets without platform lock-in.
React · Python · PostgreSQL · Cloud deploymentNNCODE Vision System
An end-to-end computer vision application with frontend, backend, database, detection, tracking, and operational analytics.
Computer vision · Full stack · YOLOReal-time video analytics
GPU-accelerated detection, segmentation, tracking, and event pipelines for live cameras and operational environments.
DeepStream · TensorRT · OpenCVOPEN SOURCE
Vision code used by engineers around the world.
ComputerVision
A broad library of practical computer vision implementations.
GitHub ↗YOLO-3D
3D object detection using YOLO and depth estimation.
GitHub ↗opencv-python-tutorials
Scripts and documentation for practical OpenCV development.
GitHub ↗VisualSLAM
Visual simultaneous localization and mapping experiments.
GitHub ↗WRITING
What I've learned building these.
SAY HI
Got something you want to build?
Send me a message and tell me about it. It's just me on the other end, from the first chat to everything we build after that.
Send me a message ↗nicolainielsen@nicolai-nielsen.com