Tryolabs logoTryolabs logo compact
  • Services
  • Our work
  • Company
    • About us
    • Team
    • Careers
  • Blog
  • Hire us
  • Services
  • Our work
  • About us
  • Team
  • Careers
  • Blog
  • Contact
LINC logo

Lion preservation with computer vision

The Lion Identification Network of Collaborators - LINC - monitors lions to help with their preservation across African territory. This community of conservationists and researchers in conjunction with IEF R&D created an open-source platform to track Panthera Leo in order to maintain the genetic viability of the species and create better policy decisions to protect the last remaining lions.

Case hero imageCase hero image
Image description


Conservationists needed to automate the process of identification of over 400 lions. To accurately monitor the population and better understand the connectivity between them, researchers in the past used to manually track lion's movements by comparing hundreds of pictures or utilizing GPS collars.

They do so by manually identifying whisker patterns taken from photographs, and preset grids where each pattern corresponds to one specimen. Another solution was to place a short-term GPS-tracking collar on each lion.

Both of the options are time-consuming, and collaring the lions is especially invasive for the animal.

Read more
Image description


A computer vision system with a pattern recognition software now serves as an automated, non-invasive solution for identifying and monitoring lions. By recognizing face and whisker patterns in lion images conservationists can collectively locate the animals by sharing their images information in a system that classifies and identifies the population.

The tool consists of computer vision and pattern recognition algorithms that can automatically perform two different methods for lion identification: face and whisker id.

To achieve this, the community uploads the photographs into the system, which then performs a database match to identify each specific lion. This reduces the time spent and team size needed, allowing conservationists to use large data sets in their work viably.

Read more

About LINC

Location: Africa

Organization type: NGO

Founded: 2017

Image description

Helping wild animals conservation with machine learning.

A computer vision approach proved to be successful in animal tracking. Get inspired by other AI for social good applications.

Image description


Develop a computer vision automated solution and pattern recognition software in 3 stages:

Stage 1

Lion feature object detection

Using a dataset of lion images that are tagged with bounding boxes around features, such as head, eyes and nose, the algorithm identifies the feature classes in new photos.
Train a Fast R-CNN architecture to perform object detection on the lion images, using PyTorch and torchvision to grab the model architecture and build all the necessary pipelines.
Technical details

Stage 2

Face identification

The dataset consists of individual identified lion face images. Given a new image, the system returns the lion with the highest probability of being the one in the photo.

With a metric learning approach, the face images are mapped to a vectorial space, where two images from the same lion are very close, and pictures from different lions are distant.

A network is trained as an image classifier to achieve this mapping, where each class represents a different entity (in this case, a different lion). The classifier layers are removed, and the embeddings generated by an intermediate layer is used as our image representation.

Transfer learning over a pre-trained ResNet50 network is applied, and then the last three layers are removed, getting an output of size 512. All the experiments from this phase are carried out using FastAI, a library built on top of PyTorch.

Technical details

Stage 3

Whiskers identification

In this phase there are two image datasets available, one for right whisker images and one for the left ones.

All images are labeled with the lion's identifier, and given a photo of a specimen's whisker area, the system returns the lions from the database with the highest probability of being the one portrayed in the picture.

Phase one object detector is used for detecting single whisker spots, this generates a point cloud from each of the whisker images. Since very few images per lion are available at this dataset, experiments with point cloud algorithms were carried out.

A match between two of these point clouds is performed by applying Coherent Point Drift, and then a point cloud distance is used to determine how good is the pairing. Then the lions with the smallest matching distance are the ones with the highest probability of being the lion we are looking for.

Technical details


Tryolabs was a great partner in developing the new algorithms for this uniquely challenging problem set. The end result of this work has been a targeted solution that can run in a resource constrained environment with or without network connection.

This work shows the flexibility and an openness of Tryolabs to out of the box thinking essential to developing not just a powerful algorithm but one that can work on all levels of the conservationist work practice.

Overall it has been a great working experience and IEF R&D and the conservation team look forward to working in the future with Tryolabs on this unique and important conservation challenge.

Justin Downs
Justin Downs

Get in touch

Tell us a bit about your project, we'd love to see how we can help.
You can send us an email or just fill out the form below.

Email icon

Email us!

Paper sheet icon

Contact us!


Our work


  • Phone: (+598) 2716 8997
  • US: 44 Montgomery St,
    San Francisco, CA
  • Luxembourg: 9 rue du Laboratoire
  • Uruguay: Rambla Gandhi 655/701,
© 2021. All rights reserved.