22 Posts
Vision
Learning to Compare: A Visual Guide to Metric Learning for Wildlife Re-ID
An intuition-first, visual guide to metric learning — how machines learn to tell individual animals apart for conservation re-identification.
Racing Models, Not Opinions: How We Ran Wildfire ML R&D for Pyronear
How a literature survey, self-contained experiments, and a shared leaderboard turned 28 research papers into a production smoke verifier with 4x fewer false alarms.
Smoke Is a Behavior: Inside Pyronear's Temporal Wildfire Detection Model
How the temporal smoke verifier works, step by step — detection boxes become tubes, stabilized crops make motion legible, and a vision transformer plus a tiny temporal head learn that smoke grows and drifts.
Identify individuals with Local Feature Matching
A comprehensive examination of using local feature matching for individual identification.
How to prepare data for identification?
An in-depth look at the common preprocessing stages required to perform identification using computer vision.
Tracking the Journey: How to Monitor Wild Salmon Migrations
An in-depth look at the systems developed and deployed to track the journey of wild salmon as they return to their natal streams.
Protecting the Forest: Building an early forest fire detector
Detecting early forest fires in real time using low powered technology
A guide to designing a bear face recognition system
Identify bears with Metric Learning.
A guide to designing a bear face segmentation system
Detecting bears in real time using low-power technology.
How to build a benthic coral reefs analyser
Learn how to successfully train a computer vision model to accurately analyse underwater benthic imagery.
How to build a real time bear detection system
Detecting bears in real time using low-power technology.
