Blog on earthtoolsmaker

Learning to Compare: A Visual Guide to Metric Learning for Wildlife Re-ID

Tue, 16 Jun 2026 00:00:00 +0000

Camera traps and field photos arrive by the thousand, and for conservation the first question is almost always the same: have we seen this animal before? Answering it — recognising an individual across time, cameras, and seasons — is called re-identification, and it underpins how researchers count populations, follow movements, and measure whether protection is working.

This is a visual, intuition-first tour of metric learning: the idea behind most modern re-identification systems. No heavy maths — just the shape of the problem and why this approach fits it so well.

Racing Models, Not Opinions: How We Ran Wildfire ML R&D for Pyronear

Fri, 12 Jun 2026 00:00:00 +0000

In 2024, we wrote about building an early forest fire detector with the NGO Pyronear: cameras on antenna towers, a YOLO object detector (a fast model that draws boxes around what it finds in a single image) running on a Raspberry Pi, and real fires detected from 35 kilometers away. This post is the next chapter — and it is less about a model than about a method.

Over the past months we helped Pyronear answer one question: can a model that watches smoke evolve over time cut false alarms without missing fires? The answer turned out to be yes — the winning model raises 4× fewer false alarms than the production baseline while catching slightly more fires. But the part worth writing about is how we got there: a literature survey distilled into a shortlist, a standardized experiment harness, and a leaderboard where five candidate models — including the current production system — raced on the same frozen test set.

Smoke Is a Behavior: Inside Pyronear's Temporal Wildfire Detection Model

Fri, 12 Jun 2026 00:00:00 +0000

In the previous post we told the story of how the new smoke verifier for Pyronear was selected: a literature survey, five candidate models, one leaderboard, one winner with 4× fewer false alarms. This post opens up the winner itself — the bbox-tube temporal model (bbox for the bounding boxes a detector draws around candidate smoke, tube for the way those boxes are linked across frames) now released as a versioned package — and walks through how it judges a sequence of camera frames, stage by stage, with figures computed from real wildfire sequences.

Volunteering at Wildlife Rescue Centers

Tue, 20 May 2025 00:00:00 +0000

In this post, we will share our experiences volunteering at various wildlife rescue centers.

Support wildlife rescue

WFFT and ARCAS both rely on donations to feed, treat, and rehabilitate the animals in their care. Every contribution goes directly to that work.

Introduction

A wildlife rescue center primarily focuses on the rehabilitation of injured, sick, or orphaned animals. The goal is to treat these animals and eventually release them back into their natural habitats.

Identify individuals with Local Feature Matching

Mon, 09 Dec 2024 00:00:00 +0000

In this post, we will explore a powerful technique widely used for identifying individuals across various species. This method leverages unique physical markings that remain relatively stable throughout an organism’s lifetime, making it effective for species with distinct patterns. For instance, whale sharks, trout, turtles, and seals all possess unique spot or scale patterns that lend themselves well to this computer vision approach.

By harnessing these identifiable features, researchers and conservationists can track and monitor individual animals, contributing to our understanding of biodiversity and aiding in conservation efforts. Join us as we delve into the intricacies of this technique and its applications in wildlife identification.

How to prepare data for identification?

Sun, 08 Dec 2024 00:00:00 +0000

In this post, we will explore essential preprocessing techniques for normalizing animal images, preparing them for individual identification.

We will focus on the initial stages of the machine learning pipelines developed for various projects, specifically bear and trout identification. In both cases, similar computer vision techniques and strategies were employed to successfully create robust identification systems.

Overview of the ML pipeline to identify bears using their facial markings with Metric Learning

Tracking the Journey: How to Monitor Wild Salmon Migrations

Fri, 30 Aug 2024 00:00:00 +0000

In this post, we will dive into the development of a wild salmon monitoring system, currently deployed at 8 sites in British Columbia.

We must take every step in our control now as climate-change related trends will make things more difficult for salmon populations in the years ahead. This demands urgency for Pacific salmon and for the 130+ species, including grizzlies, orcas and eagles, that depend on Pacific salmon.

– Pacific Salmon Foundation

Protecting the Forest: Building an early forest fire detector

Wed, 21 Aug 2024 00:00:00 +0000

In this post, we’ll walk through the development of an early forest fire detection system, built in collaboration with the NGO Pyronear.

Our detectors communicate fire alerts to a database that is connected to a supervision platform for the fire department.

– Pyronear

Pyronear takes a whole-system approach to fire risk. At its core is an early wildfire detection algorithm that runs on a compact microcomputer, fed by a network of high-resolution cameras mounted at high vantage points for panoramic coverage of the forest. Together they form a proactive line of defense against wildfires.

How to detect elephant rumbles at scale

Sat, 29 Jun 2024 00:00:00 +0000

This post walks through the development of an elephant rumble audio analyzer, built in partnership with The Elephant Listening Project.

Our vision is to conserve the tropical forests of Africa through acoustic monitoring, sound science, and education, focusing on forest elephants

– The Elephant Listening Project

For a comprehensive understanding of this project, one can read more on the detailed project page on passive acoustic monitoring for forest elephants.

What is sound?

Sound is produced by variations in air pressure. These pressure variations can be measured and plotted over time to create a visual representation of the sound.

A guide to designing a bear face recognition system

Fri, 12 Apr 2024 00:00:00 +0000

In this post we’ll walk through the technical development of a bear face recognition system — a critical component of the bear identification system built in close collaboration with the BearID Project NGO.

Our research and software tool will provide a replicable technique and general approach that can be applied to other species beyond bears, which could aid conservation efforts worldwide.

– BearID Project

For the full picture, here is the bear identification pipeline — tap through for the project:

A guide to designing a bear face segmentation system

Thu, 11 Apr 2024 00:00:00 +0000

In this post we’ll walk through the technical development of a bear face segmentation system — a critical component of the bear identification system built in close collaboration with the BearID Project NGO.

Our research and software tool will provide a replicable technique and general approach that can be applied to other species beyond bears, which could aid conservation efforts worldwide.

– BearID Project

For the full picture, here is the bear identification pipeline — tap through for the project:

How to build a benthic coral reefs analyser

Wed, 10 Apr 2024 00:00:00 +0000

In this post we explore the development of a benthic coral reef analyzer, built in partnership with ReefSupport to improve the tools for monitoring coral reefs and marine environments.

For the full picture, here is the coral analysis pipeline — tap through for the project:

Capture → segment → classify → measure coral cover over time

Leveraging computer vision for the segmentation of coral reefs in benthic imagery holds the potential to quantify the long-term growth or decline of coral cover within marine protected areas

How to build a real time bear detection system

Tue, 09 Apr 2024 00:00:00 +0000

In this post, we’ll walk through the development of a real-time bear detection system, built with the NGO HackThePlanet to safeguard Romanian farms by deterring bears.

Implementing non-invasive methods to deter bears from approaching farms and livestock holds promise in fostering harmonious relations between humans and bears.

For the full picture, here is the bear deterrence pipeline — tap through for the project:

Watch → detect the bear on-device → trigger → deter it from the farm