A computer vision approach proved to be successful in animal tracking.
Helping wild animals conservation with machine learning.
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.
individual lions registered
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.
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.
Discover our approach
Develop a computer vision automated solution and pattern recognition software in 3 stages:
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.
The result of our partnership 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.
It has been a great working experience and our team looks forward to working with Tryolabs in the future on this unique conservation challenge.