Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection
During the past decades, the composition and distribution of marine species have changed due to multiple anthropogenic pressures. Monitoring these changes in a cost-effective manner is of high relevance to assess the environmental status and evaluate the effectiveness of management measures. In part...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/6/1708 |
| _version_ | 1828153091752460288 |
|---|---|
| author | Miguel Martin-Abadal Ana Ruiz-Frau Hilmar Hinz Yolanda Gonzalez-Cid |
| author_facet | Miguel Martin-Abadal Ana Ruiz-Frau Hilmar Hinz Yolanda Gonzalez-Cid |
| author_sort | Miguel Martin-Abadal |
| collection | DOAJ |
| description | During the past decades, the composition and distribution of marine species have changed due to multiple anthropogenic pressures. Monitoring these changes in a cost-effective manner is of high relevance to assess the environmental status and evaluate the effectiveness of management measures. In particular, recent studies point to a rise of jellyfish populations on a global scale, negatively affecting diverse marine sectors like commercial fishing or the tourism industry. Past monitoring efforts using underwater video observations tended to be time-consuming and costly due to human-based data processing. In this paper, we present Jellytoring, a system to automatically detect and quantify different species of jellyfish based on a deep object detection neural network, allowing us to automatically record jellyfish presence during long periods of time. Jellytoring demonstrates outstanding performance on the jellyfish detection task, reaching an <i>F</i>1 <i>score</i> of 95.2%; and also on the jellyfish quantification task, as it correctly quantifies the number and class of jellyfish on a real-time processed video sequence up to a 93.8% of its duration. The results of this study are encouraging and provide the means towards a efficient way to monitor jellyfish, which can be used for the development of a jellyfish early-warning system, providing highly valuable information for marine biologists and contributing to the reduction of jellyfish impacts on humans. |
| first_indexed | 2024-04-11T22:20:31Z |
| format | Article |
| id | doaj.art-e14e5f53e49646e8a9471e20ee6e50ea |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T22:20:31Z |
| publishDate | 2020-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e14e5f53e49646e8a9471e20ee6e50ea2022-12-22T04:00:10ZengMDPI AGSensors1424-82202020-03-01206170810.3390/s20061708s20061708Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object DetectionMiguel Martin-Abadal0Ana Ruiz-Frau1Hilmar Hinz2Yolanda Gonzalez-Cid3Department of Mathematics and Computer Science, Systems Robotics and Vision Group (SRV), Universitat de les Illes Balears, 07122 Palma, SpainDepartment of Marine Ecosystem Dynamics, IMEDEA (CSIC-UIB), Institut Mediterrani d’Estudis Avançats, 07190 Esporles, SpainDepartment of Marine Ecosystem Dynamics, IMEDEA (CSIC-UIB), Institut Mediterrani d’Estudis Avançats, 07190 Esporles, SpainDepartment of Mathematics and Computer Science, Systems Robotics and Vision Group (SRV), Universitat de les Illes Balears, 07122 Palma, SpainDuring the past decades, the composition and distribution of marine species have changed due to multiple anthropogenic pressures. Monitoring these changes in a cost-effective manner is of high relevance to assess the environmental status and evaluate the effectiveness of management measures. In particular, recent studies point to a rise of jellyfish populations on a global scale, negatively affecting diverse marine sectors like commercial fishing or the tourism industry. Past monitoring efforts using underwater video observations tended to be time-consuming and costly due to human-based data processing. In this paper, we present Jellytoring, a system to automatically detect and quantify different species of jellyfish based on a deep object detection neural network, allowing us to automatically record jellyfish presence during long periods of time. Jellytoring demonstrates outstanding performance on the jellyfish detection task, reaching an <i>F</i>1 <i>score</i> of 95.2%; and also on the jellyfish quantification task, as it correctly quantifies the number and class of jellyfish on a real-time processed video sequence up to a 93.8% of its duration. The results of this study are encouraging and provide the means towards a efficient way to monitor jellyfish, which can be used for the development of a jellyfish early-warning system, providing highly valuable information for marine biologists and contributing to the reduction of jellyfish impacts on humans.https://www.mdpi.com/1424-8220/20/6/1708deep learningobject detectionjellyfish quantificationjellyfish monitoring |
| spellingShingle | Miguel Martin-Abadal Ana Ruiz-Frau Hilmar Hinz Yolanda Gonzalez-Cid Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection Sensors deep learning object detection jellyfish quantification jellyfish monitoring |
| title | Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection |
| title_full | Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection |
| title_fullStr | Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection |
| title_full_unstemmed | Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection |
| title_short | Jellytoring: Real-Time Jellyfish Monitoring Based on Deep Learning Object Detection |
| title_sort | jellytoring real time jellyfish monitoring based on deep learning object detection |
| topic | deep learning object detection jellyfish quantification jellyfish monitoring |
| url | https://www.mdpi.com/1424-8220/20/6/1708 |
| work_keys_str_mv | AT miguelmartinabadal jellytoringrealtimejellyfishmonitoringbasedondeeplearningobjectdetection AT anaruizfrau jellytoringrealtimejellyfishmonitoringbasedondeeplearningobjectdetection AT hilmarhinz jellytoringrealtimejellyfishmonitoringbasedondeeplearningobjectdetection AT yolandagonzalezcid jellytoringrealtimejellyfishmonitoringbasedondeeplearningobjectdetection |