Seabird surveillance: combining CCTV and artificial intelligence for monitoring and research
Abstract Ecological research and monitoring need to be able to rapidly convey information that can form the basis of scientifically sound management. Automated sensor systems, especially if combined with artificial intelligence, can contribute to such rapid high‐resolution data retrieval. Here, we e...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-08-01
|
| Series: | Remote Sensing in Ecology and Conservation |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/rse2.329 |
| _version_ | 1797736705259732992 |
|---|---|
| author | Jonas Hentati‐Sundberg Agnes B. Olin Sheetal Reddy Per‐Arvid Berglund Erik Svensson Mareddy Reddy Siddharta Kasarareni Astrid A. Carlsen Matilda Hanes Shreyash Kad Olof Olsson |
| author_facet | Jonas Hentati‐Sundberg Agnes B. Olin Sheetal Reddy Per‐Arvid Berglund Erik Svensson Mareddy Reddy Siddharta Kasarareni Astrid A. Carlsen Matilda Hanes Shreyash Kad Olof Olsson |
| author_sort | Jonas Hentati‐Sundberg |
| collection | DOAJ |
| description | Abstract Ecological research and monitoring need to be able to rapidly convey information that can form the basis of scientifically sound management. Automated sensor systems, especially if combined with artificial intelligence, can contribute to such rapid high‐resolution data retrieval. Here, we explore the prospects of automated methods to generate insights for seabirds, which are often monitored for their high conservation value and for being sentinels for marine ecosystem changes. We have developed a system of video surveillance combined with automated image processing, which we apply to common murres Uria aalge. The system uses a deep learning algorithm for object detection (YOLOv5) that has been trained on annotated images of adult birds, chicks and eggs, and outputs time, location, size and confidence level of all detections, frame‐by‐frame, in the supplied video material. A total of 144 million bird detections were generated from a breeding cliff over three complete breeding seasons (2019–2021). We demonstrate how object detection can be used to accurately monitor breeding phenology and chick growth. Our automated monitoring approach can also identify and quantify rare events that are easily missed in traditional monitoring, such as disturbances from predators. Further, combining automated video analysis with continuous measurements from a temperature logger allows us to study impacts of heat waves on nest attendance in high detail. Our automated system thus produces comparable, and in several cases significantly more detailed, data than those generated from observational field studies. By running in real time on the camera streams, it has the potential to supply researchers and managers with high‐resolution up‐to‐date information on seabird population status. We describe how the system can be modified to fit various types of ecological research and monitoring goals and thereby provide up‐to‐date support for conservation and ecosystem management. |
| first_indexed | 2024-03-12T13:17:45Z |
| format | Article |
| id | doaj.art-aea561be33084f1683e8dffdb8efc620 |
| institution | Directory Open Access Journal |
| issn | 2056-3485 |
| language | English |
| last_indexed | 2024-03-12T13:17:45Z |
| publishDate | 2023-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | Remote Sensing in Ecology and Conservation |
| spelling | doaj.art-aea561be33084f1683e8dffdb8efc6202023-08-26T15:26:49ZengWileyRemote Sensing in Ecology and Conservation2056-34852023-08-019456858110.1002/rse2.329Seabird surveillance: combining CCTV and artificial intelligence for monitoring and researchJonas Hentati‐Sundberg0Agnes B. Olin1Sheetal Reddy2Per‐Arvid Berglund3Erik Svensson4Mareddy Reddy5Siddharta Kasarareni6Astrid A. Carlsen7Matilda Hanes8Shreyash Kad9Olof Olsson10Department of Aquatic Resources Swedish University of Agricultural Sciences Box 7018 75007 Uppsala SwedenDepartment of Aquatic Resources Swedish University of Agricultural Sciences Box 7018 75007 Uppsala SwedenAI Sweden Lindholmspiren 11 41756 Gothenburg SwedenBaltic Seabird Project Sanda Västerby 568 62379 Klintehamn SwedenBeräkning och Framsteg AB Göteborg SwedenEnergy and Materials Chalmers University of Technology Kemivägen 10 41296 Gothenburg SwedenChalmers Industriteknik Gothenburg SwedenDepartment of Aquatic Resources Swedish University of Agricultural Sciences Box 7018 75007 Uppsala SwedenDepartment of Electric Engineering Chalmers University of Technology Gothenburg SwedenDepartment of Electric Engineering Chalmers University of Technology Gothenburg SwedenStockholm Resilience Centre Stockholm University Stockholm SwedenAbstract Ecological research and monitoring need to be able to rapidly convey information that can form the basis of scientifically sound management. Automated sensor systems, especially if combined with artificial intelligence, can contribute to such rapid high‐resolution data retrieval. Here, we explore the prospects of automated methods to generate insights for seabirds, which are often monitored for their high conservation value and for being sentinels for marine ecosystem changes. We have developed a system of video surveillance combined with automated image processing, which we apply to common murres Uria aalge. The system uses a deep learning algorithm for object detection (YOLOv5) that has been trained on annotated images of adult birds, chicks and eggs, and outputs time, location, size and confidence level of all detections, frame‐by‐frame, in the supplied video material. A total of 144 million bird detections were generated from a breeding cliff over three complete breeding seasons (2019–2021). We demonstrate how object detection can be used to accurately monitor breeding phenology and chick growth. Our automated monitoring approach can also identify and quantify rare events that are easily missed in traditional monitoring, such as disturbances from predators. Further, combining automated video analysis with continuous measurements from a temperature logger allows us to study impacts of heat waves on nest attendance in high detail. Our automated system thus produces comparable, and in several cases significantly more detailed, data than those generated from observational field studies. By running in real time on the camera streams, it has the potential to supply researchers and managers with high‐resolution up‐to‐date information on seabird population status. We describe how the system can be modified to fit various types of ecological research and monitoring goals and thereby provide up‐to‐date support for conservation and ecosystem management.https://doi.org/10.1002/rse2.329Artificial intelligencemachine learningmonitoringobject detectionseabirds |
| spellingShingle | Jonas Hentati‐Sundberg Agnes B. Olin Sheetal Reddy Per‐Arvid Berglund Erik Svensson Mareddy Reddy Siddharta Kasarareni Astrid A. Carlsen Matilda Hanes Shreyash Kad Olof Olsson Seabird surveillance: combining CCTV and artificial intelligence for monitoring and research Remote Sensing in Ecology and Conservation Artificial intelligence machine learning monitoring object detection seabirds |
| title | Seabird surveillance: combining CCTV and artificial intelligence for monitoring and research |
| title_full | Seabird surveillance: combining CCTV and artificial intelligence for monitoring and research |
| title_fullStr | Seabird surveillance: combining CCTV and artificial intelligence for monitoring and research |
| title_full_unstemmed | Seabird surveillance: combining CCTV and artificial intelligence for monitoring and research |
| title_short | Seabird surveillance: combining CCTV and artificial intelligence for monitoring and research |
| title_sort | seabird surveillance combining cctv and artificial intelligence for monitoring and research |
| topic | Artificial intelligence machine learning monitoring object detection seabirds |
| url | https://doi.org/10.1002/rse2.329 |
| work_keys_str_mv | AT jonashentatisundberg seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch AT agnesbolin seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch AT sheetalreddy seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch AT perarvidberglund seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch AT eriksvensson seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch AT mareddyreddy seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch AT siddhartakasarareni seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch AT astridacarlsen seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch AT matildahanes seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch AT shreyashkad seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch AT olofolsson seabirdsurveillancecombiningcctvandartificialintelligenceformonitoringandresearch |