Real‐time alerts from AI‐enabled camera traps using the Iridium satellite network: A case‐study in Gabon, Central Africa
Abstract Efforts to preserve, protect and restore ecosystems are hindered by long delays between data collection and analysis. Threats to ecosystems can go undetected for years or decades as a result. Real‐time data can help solve this issue but significant technical barriers exist. For example, aut...
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-03-01
|
| Series: | Methods in Ecology and Evolution |
| Online Access: | https://doi.org/10.1111/2041-210X.14036 |
| _version_ | 1797767019345477632 |
|---|---|
| author | Robin C. Whytock Thijs Suijten Tim vanDeursen Jędrzej Świeżewski Hervé Mermiaghe Nazaire Madamba Narcisse Mouckoumou Joeri A. Zwerts Aurélie Flore Koumba Pambo Laila Bahaa‐el‐din Stephanie Brittain Anabelle W. Cardoso Philipp Henschel David Lehmann Brice Roxan Momboua Loïc Makaga Christopher Orbell Lee J. T. White Donald Midoko Iponga Katharine A. Abernethy |
| author_facet | Robin C. Whytock Thijs Suijten Tim vanDeursen Jędrzej Świeżewski Hervé Mermiaghe Nazaire Madamba Narcisse Mouckoumou Joeri A. Zwerts Aurélie Flore Koumba Pambo Laila Bahaa‐el‐din Stephanie Brittain Anabelle W. Cardoso Philipp Henschel David Lehmann Brice Roxan Momboua Loïc Makaga Christopher Orbell Lee J. T. White Donald Midoko Iponga Katharine A. Abernethy |
| author_sort | Robin C. Whytock |
| collection | DOAJ |
| description | Abstract Efforts to preserve, protect and restore ecosystems are hindered by long delays between data collection and analysis. Threats to ecosystems can go undetected for years or decades as a result. Real‐time data can help solve this issue but significant technical barriers exist. For example, automated camera traps are widely used for ecosystem monitoring but it is challenging to transmit images for real‐time analysis where there is no reliable cellular or WiFi connectivity. We modified an off‐the‐shelf camera trap (Bushnell™) and customised existing open‐source hardware to create a ‘smart’ camera trap system. Images captured by the camera trap are instantly labelled by an artificial intelligence model and an ‘alert’ containing the image label and other metadata is then delivered to the end‐user within minutes over the Iridium satellite network. We present results from testing in the Netherlands, Europe, and from a pilot test in a closed‐canopy forest in Gabon, Central Africa. All reference materials required to build the system are provided in open‐source repositories. Results show the system can operate for a minimum of 3 months without intervention when capturing a median of 17.23 images per day. The median time‐difference between image capture and receiving an alert was 7.35 min, though some outliers showed delays of 5‐days or more when the system was incorrectly positioned and unable to connect to the Iridium network. We anticipate significant developments in this field and hope that the solutions presented here, and the lessons learned, can be used to inform future advances. New artificial intelligence models and the addition of other sensors such as microphones will expand the system's potential for other, real‐time use cases including real‐time biodiversity monitoring, wild resource management and detecting illegal human activities in protected areas. |
| first_indexed | 2024-03-12T20:32:43Z |
| format | Article |
| id | doaj.art-df314c86a1ad45c7907d601bed8a60cd |
| institution | Directory Open Access Journal |
| issn | 2041-210X |
| language | English |
| last_indexed | 2024-03-12T20:32:43Z |
| publishDate | 2023-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Methods in Ecology and Evolution |
| spelling | doaj.art-df314c86a1ad45c7907d601bed8a60cd2023-08-01T18:55:49ZengWileyMethods in Ecology and Evolution2041-210X2023-03-0114386787410.1111/2041-210X.14036Real‐time alerts from AI‐enabled camera traps using the Iridium satellite network: A case‐study in Gabon, Central AfricaRobin C. Whytock0Thijs Suijten1Tim vanDeursen2Jędrzej Świeżewski3Hervé Mermiaghe4Nazaire Madamba5Narcisse Mouckoumou6Joeri A. Zwerts7Aurélie Flore Koumba Pambo8Laila Bahaa‐el‐din9Stephanie Brittain10Anabelle W. Cardoso11Philipp Henschel12David Lehmann13Brice Roxan Momboua14Loïc Makaga15Christopher Orbell16Lee J. T. White17Donald Midoko Iponga18Katharine A. Abernethy19Faculty of Natural Sciences University of Stirling Stirling UKHack the Planet, Q42 The Hague Zuid Holland The NetherlandsHack the Planet, Q42 The Hague Zuid Holland The NetherlandsAppsilon AI for Good Warsaw PolandSchool of Architecture and Environment, Department of Landscape Architecture, University of Oregon Oregon Eugene USAAgence Nationale des Parcs Nationaux Libreville GabonAgence Nationale des Parcs Nationaux Libreville GabonUtrecht University Utrecht The NetherlandsAgence Nationale des Parcs Nationaux Libreville GabonSchool of Life Sciences University of KwaZulu‐Natal Durban South AfricaUniversity of Oxford Department of Zoology Oxford UKDepartment of Ecology and Evolutionary Biology Yale University Connecticut New Haven USAPanthera New York New York USAAgence Nationale des Parcs Nationaux Libreville GabonAgence Nationale des Parcs Nationaux Libreville GabonAgence Nationale des Parcs Nationaux Libreville GabonFaculty of Natural Sciences University of Stirling Stirling UKFaculty of Natural Sciences University of Stirling Stirling UKInstitut de Recherche en Ecologie Tropicale, CENAREST Libreville GabonFaculty of Natural Sciences University of Stirling Stirling UKAbstract Efforts to preserve, protect and restore ecosystems are hindered by long delays between data collection and analysis. Threats to ecosystems can go undetected for years or decades as a result. Real‐time data can help solve this issue but significant technical barriers exist. For example, automated camera traps are widely used for ecosystem monitoring but it is challenging to transmit images for real‐time analysis where there is no reliable cellular or WiFi connectivity. We modified an off‐the‐shelf camera trap (Bushnell™) and customised existing open‐source hardware to create a ‘smart’ camera trap system. Images captured by the camera trap are instantly labelled by an artificial intelligence model and an ‘alert’ containing the image label and other metadata is then delivered to the end‐user within minutes over the Iridium satellite network. We present results from testing in the Netherlands, Europe, and from a pilot test in a closed‐canopy forest in Gabon, Central Africa. All reference materials required to build the system are provided in open‐source repositories. Results show the system can operate for a minimum of 3 months without intervention when capturing a median of 17.23 images per day. The median time‐difference between image capture and receiving an alert was 7.35 min, though some outliers showed delays of 5‐days or more when the system was incorrectly positioned and unable to connect to the Iridium network. We anticipate significant developments in this field and hope that the solutions presented here, and the lessons learned, can be used to inform future advances. New artificial intelligence models and the addition of other sensors such as microphones will expand the system's potential for other, real‐time use cases including real‐time biodiversity monitoring, wild resource management and detecting illegal human activities in protected areas.https://doi.org/10.1111/2041-210X.14036 |
| spellingShingle | Robin C. Whytock Thijs Suijten Tim vanDeursen Jędrzej Świeżewski Hervé Mermiaghe Nazaire Madamba Narcisse Mouckoumou Joeri A. Zwerts Aurélie Flore Koumba Pambo Laila Bahaa‐el‐din Stephanie Brittain Anabelle W. Cardoso Philipp Henschel David Lehmann Brice Roxan Momboua Loïc Makaga Christopher Orbell Lee J. T. White Donald Midoko Iponga Katharine A. Abernethy Real‐time alerts from AI‐enabled camera traps using the Iridium satellite network: A case‐study in Gabon, Central Africa Methods in Ecology and Evolution |
| title | Real‐time alerts from AI‐enabled camera traps using the Iridium satellite network: A case‐study in Gabon, Central Africa |
| title_full | Real‐time alerts from AI‐enabled camera traps using the Iridium satellite network: A case‐study in Gabon, Central Africa |
| title_fullStr | Real‐time alerts from AI‐enabled camera traps using the Iridium satellite network: A case‐study in Gabon, Central Africa |
| title_full_unstemmed | Real‐time alerts from AI‐enabled camera traps using the Iridium satellite network: A case‐study in Gabon, Central Africa |
| title_short | Real‐time alerts from AI‐enabled camera traps using the Iridium satellite network: A case‐study in Gabon, Central Africa |
| title_sort | real time alerts from ai enabled camera traps using the iridium satellite network a case study in gabon central africa |
| url | https://doi.org/10.1111/2041-210X.14036 |
| work_keys_str_mv | AT robincwhytock realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT thijssuijten realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT timvandeursen realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT jedrzejswiezewski realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT hervemermiaghe realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT nazairemadamba realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT narcissemouckoumou realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT joeriazwerts realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT aurelieflorekoumbapambo realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT lailabahaaeldin realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT stephaniebrittain realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT anabellewcardoso realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT philipphenschel realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT davidlehmann realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT briceroxanmomboua realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT loicmakaga realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT christopherorbell realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT leejtwhite realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT donaldmidokoiponga realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica AT katharineaabernethy realtimealertsfromaienabledcameratrapsusingtheiridiumsatellitenetworkacasestudyingaboncentralafrica |