Vision Field Notes

Practical computer vision and edge AI, from someone who runs it in production.

Guides on training detectors, running them on small devices and keeping video analytics reliable. Written by a computer vision engineer, with no hype.

Latest articles

Tools and Workflow

Managing Per-Camera Configuration at Scale

Zones, thresholds, schedules and streams for hundreds of cameras: how to layer defaults and overrides, validate them and keep them versioned.

5 min read
Video Analytics

Main Stream or Substream: Choosing Resolution and Bitrate for Analytics

IP cameras offer a full-quality main stream and a lighter substream. Which to analyse depends on object size, model input and decode budget.

5 min read
Career and Freelancing

Turning Down a Computer Vision Project (and Offering Something Better)

Some vision projects should not be accepted as asked. How to spot them, say no without losing the client, and offer a version that works.

6 min read
YOLO and Detection Basics

Single-Class or Multi-Class: When to Merge or Split Detection Classes

Should car, van and truck be one class or three? How to decide a detector's classes, and why labelling fine and training coarse keeps options open.

5 min read
Edge Hardware and Deployment

Watchdogs and Self-Recovery for Unattended Edge Boxes

An edge box nobody can reach must recover on its own. Hardware watchdogs, systemd restarts, application health checks and remote alerts, layered.

5 min read
Datasets and Training

Deduplicating Video Frames Before Labelling

Most frames from a fixed camera are near-copies. How to pick frames worth labelling with difference checks, hashes and embeddings, keeping rare cases.

5 min read
Tools and Workflow

Profiling a Python Vision Pipeline: Finding the Real Bottleneck

Before optimising the model, find where the time actually goes. Stage timers, sampling profilers and the usual hidden costs in Python video pipelines.

5 min read
Video Analytics

How Many Frames per Second Does Your Analytics Need?

Analysing every frame is rarely necessary. How to pick an analysis frame rate from object speed, view size, filters and trackers, and test it.

5 min read
YOLO and Detection Basics

Why a Detector's Confidence Is Not a Probability

A box scored 0.8 is not right 80% of the time. What confidence scores are, why they shift between models and classes, and what that means for thresholds.

5 min read

YOLO and Detection Basics

All 17 articles in YOLO and Detection Basics

Datasets and Training

All 15 articles in Datasets and Training

Edge Hardware and Deployment

All 17 articles in Edge Hardware and Deployment

Video Analytics

All 17 articles in Video Analytics

Tools and Workflow

All 13 articles in Tools and Workflow

Career and Freelancing

All 10 articles in Career and Freelancing