FASTCAT-Cloud: upload and analyse all your nature videos and pictures on the FASTCAT-Cloud website: receive only information on relevant images and recordings of wildlife activity and quickly identify the species names with Artificial Intelligence (AI).
Service description
FASTCAT (Flexible Ai System for CAmera Traps)-Cloud is an open website service able to:
(1) Automatically filter out most unwanted pictures and video streams, keeping images of animals. This saves you time as empty recordings or photos can be removed automatically.
(2) Integrate machine learning technology (a subset of AI – Artificial Intelligence) to automatically identify species, which means that you will see the suggested species names for each image.
(3) Provide you with the ability to obtain counts (number of species recorded or photographed), i.e. how many different species have been sighted this week, or how many times you have photographed a fox in the last 30 days.
(4) Eventually, this website service will connect with biodiversity citizen observatories. So, if you are a citizen scientist that uses a camera trap, you will be able to easily upload the picture to some platforms such as iSpot or SensorThingsAPI plus. The idea is to create a Graphical User Interface (GUI) that allows you to view the proposed species name. If you accept the suggested classification from the system, the picture is uploaded to any of the chosen biodiversity citizen observatories with the proposed identification name.
Development & how it works
The website service integrates an AI model to decide which frames, both from images and videos, contain an animal. This means that it will remove most images that are not useful (e.g. no animals present, near duplicates, false positives due to wind movement, etc.). The camera trap uses bespoke AI to automatically identify species and allows the user to automatically update the number of species, both from videos and pictures.
- Drastically cut the data analysed, archived or transmitted from any camera trap. This will be achieved by:
- Removing most images that are not useful (e.g. no animals present, near duplicates, false positives due to wind movement, etc.).
- Provide access to robust state-of-the-art processing methods and algorithms: recent deep-learning methods to automatically find animals (detection) and identify the species names. This will be achieved by:
- Providing automatic bounding boxes for objects of interest, which typically are various animals (the service provides such bounding boxes around animals.).
-
Provide a minimum of automatic analysis of data and make the entire processing of images much easier. This mainly involves three steps:
- (i) Filtering: remove most frames that are not useful; (ii) Providing bounding boxes around animals in images: in this step is where the counting is done; (iii) Implementing automatic species identification in each bounding box: animal species ID (when robust).
Innovation for the camera trap community
- Save time in selecting the images and videos: the website server greatly reduces the amount of unwanted data to store or filter.
- More easily identify the species names.
- Design your own observation pipeline around this camera trap.
- Provides you with a way to automatically generate statistics, e.g. the number of species recorded or photographed.
- Share the wildlife images with citizen science projects.
EOSC Marketplace:
Test the FASTCAT-Cloud demo:
Watch the video!
Related news:
Coordinator:
Questions & answers
- Will the FASTCAT-Cloud website be able to filter both images and videos?
Yes.
- Can I select which species subsets I want to download? For example, if I’m interested only in receiving the images/videos with foxes?
- In which formats can I upload photos and videos to the FASTCAT-Cloud website?
- Can the system detect humans?
Yes, the system can detect humans (as an animal class) and they can be removed or counted as such. However, we do not provide recognition of any other features (gender, etc.), just the label ‘human.’
Co-design highlights
Most of the attendees who answered the post-event survey would recommend the co-design session to a friend.
Want to join the co-design community?
Interact and meet other professionals working in your field
You will be able to network with other professionals and projects.
Help boost the functionalities of citizen observatories
For example, improve species identification with artificial intelligence, data integration from various citizen science platforms, etc.
Be an active part of the open science movement
Cos4Cloud's technical services are open source and are intended to be adapted and improved by the community involved.
Learn about citizen science, technology, and co-design
Also, we will tell you how we have applied co-design feedback in developing the service at the end of the project.
