Institutional Sponsorship for Liverpool John Moores
Lead Research Organisation:
Liverpool John Moores University
Department Name: Astrophysics Research Institute
Abstract
Abstracts are not currently available in GtR for all funded research. This is normally because the abstract was not required at the time of proposal submission, but may be because it included sensitive information such as personal details.
People |
ORCID iD |
| Ian McCarthy (Principal Investigator) |
Publications
Chalmers C
(2023)
Removing Human Bottlenecks in Bird Classification Using Camera Trap Images and Deep Learning
in Remote Sensing
Doull KE
(2021)
An Evaluation of the Factors Affecting 'Poacher' Detection with Drones and the Efficacy of Machine-Learning for Detection.
in Sensors (Basel, Switzerland)
Westworth SOA
(2022)
Understanding External Influences on Target Detection and Classification Using Camera Trap Images and Machine Learning.
in Sensors (Basel, Switzerland)
| Description | We have used the Institutional Award to build on our "Astro-Ecology" initiative at Astrophysics Research Institute in Liverpool, setting up a network of camera traps at Knowsley Safari Park which uses our machine learning setup to automatically detect and tag animals, humans, cars, etc., and then uses a mobile phone network to ping the images immediately back to a central location. We've used this as a proof of concept for long-term animal and poacher detection in the wild. Having shown this works well in a controlled setting, we are now setting up an array of camera traps in an area with mobile phone reach for a year and get images for a model that is specific for that area. This can then be used for real-time detection of animals and humans to monitor biodiversity and help reduce poaching. |
| Exploitation Route | We have demonstrated the efficiency of real-time machine learning-based analysis of imaging data to help tackle some of the largest challenges faced by humanity (climate change, biodiversity loss). |
| Sectors | Environment |
| Description | Context: The Astro-Ecology group within the Astrophysics Research Institute has demonstrated that astrophysically optimised thermal-drone systems are extremely efficient at finding and identifying animals and pinpointing the location of wildfires. The approach to impact has been to: (i) develop and implement an automated monitoring system that is very low cost, robust, simple to operate, that can automatically detect, identify and geo-tag animals and fires in thermal infrared footage over large and inhospitable areas, and (ii) begin systematically taking this to key global biodiversity and fire hotspots. We are now working with 14 leading conservation agencies on 5 continents around the world in real-life conservation and fire-fighting situations. The factor 100x improvement in survey efficiency our system offers over existing methods has had a direct impact on halting biodiversity loss and reducing the size and duration of fires which comprise a significant fraction of annual anthropogenic CO2 emissions - a main driver of climate change. Our interaction with government agencies is shaping conservation/land use policy, and legislation at a national level, e.g. working with the Madagascan Government's Civil Aviation Authority to help implement a National Drone Policy document. We have used the Institutional Award to build on our "Astro-Ecology" initiative, setting up a network of camera traps at Knowsley Safari Park which uses our machine learning setup to automatically detect and tag animals, humans, cars, etc., and then uses a mobile phone network to ping the images immediately back to a central location. We've used this as a proof of concept for long-term animal and poacher detection in the wild. Having shown this works well in a controlled setting, we are now setting up an array of camera traps in an area with mobile phone reach for a year and get images for a model that is specific for that area. This can then be used for real-time detection of animals and humans to monitor biodiversity and help reduce poaching. |
| First Year Of Impact | 2022 |
| Sector | Environment |
| Impact Types | Societal Economic |
| Description | Institute of Physics report |
| Geographic Reach | National |
| Policy Influence Type | Participation in a guidance/advisory committee |
| URL | https://www.iop.org/policy/physics-research-and-development-blueprint/initial-report/discovery |
| Description | Voice of America article |
| Form Of Engagement Activity | A broadcast e.g. TV/radio/film/podcast (other than news/press) |
| Part Of Official Scheme? | No |
| Geographic Reach | International |
| Primary Audience | Public/other audiences |
| Results and Impact | A Voice of America article on trafficking of pangolins |
| Year(s) Of Engagement Activity | 2023 |