Practical writing on computer vision, edge deployment and the unglamorous details that decide whether a vision system works outside the lab.
Featured
From Bounding Boxes to Business Events: Designing an Analytics Layer
A detector tells you where things are. An operations team needs to know what happened. The analytics layer in between is where most of the real product decisions live.
Counting People in Public Spaces Without Identifying Them
Cities need occupancy and movement data. Residents need assurance that the cameras are not tracking them. Both requirements can be met if privacy is designed into the pipeline rather than promised afterward.
All articles
- Industrial AI
Why Most Defect Detection Projects Fail Before Training Starts
The model is rarely the problem. Decisions made about capture, lighting, labeling and acceptance criteria determine whether an inspection system can succeed long before anyone opens a training script.
7 min read - AI Engineering
Validating Vision Models on Footage From the Real Site
A model that scores well on a public benchmark can still fail on the cameras it will actually run on. Validation has to happen on real footage, with ground truth and failure analysis that reflect how the system will be used.
8 min read - Edge AI
What Actually Runs on an Edge Device: Anatomy of a Jetson Inference Pipeline
An edge AI device is more than a model file. Here is what a production inference pipeline on NVIDIA Jetson looks like, stage by stage, and where the engineering effort actually goes.
9 min read - Computer Vision
Choosing Between Detection and Segmentation for Visual Inspection
Bounding boxes and pixel masks answer different questions. Choosing the wrong one for an inspection task costs accuracy, compute and labeling effort. Here is how we decide.
6 min read
Occasional notes, straight from the engineers.
New articles and the occasional deployment lesson. No marketing sequence.