Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images
Human activities in the sea, such as intensive fishing and exploitation of offshore wind farms, may impact negatively on the marine mega fauna. As an attempt to control such impacts, surveying, and tracking of marine animals are often performed on the sites where those activities take place. Nowaday...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/2/339 |
| _version_ | 1827662988635537408 |
|---|---|
| author | Paul Berg Deise Santana Maia Minh-Tan Pham Sébastien Lefèvre |
| author_facet | Paul Berg Deise Santana Maia Minh-Tan Pham Sébastien Lefèvre |
| author_sort | Paul Berg |
| collection | DOAJ |
| description | Human activities in the sea, such as intensive fishing and exploitation of offshore wind farms, may impact negatively on the marine mega fauna. As an attempt to control such impacts, surveying, and tracking of marine animals are often performed on the sites where those activities take place. Nowadays, thank to high resolution cameras and to the development of machine learning techniques, tracking of wild animals can be performed remotely and the analysis of the acquired images can be automatized using state-of-the-art object detection models. However, most state-of-the-art detection methods require lots of annotated data to provide satisfactory results. Since analyzing thousands of images acquired during a flight survey can be a cumbersome and time consuming task, we focus in this article on the weakly supervised detection of marine animals. We propose a modification of the patch distribution modeling method (PaDiM), which is currently one of the state-of-the-art approaches for anomaly detection and localization for visual industrial inspection. In order to show its effectiveness and suitability for marine animal detection, we conduct a comparative evaluation of the proposed method against the original version, as well as other state-of-the-art approaches on two high-resolution marine animal image datasets. On both tested datasets, the proposed method yielded better F1 and recall scores (75% recall/41% precision, and 57% recall/60% precision, respectively) when trained on images known to contain no object of interest. This shows a great potential of the proposed approach to speed up the marine animal discovery in new flight surveys. Additionally, such a method could be adopted for bounding box proposals to perform faster and cheaper annotation within a fully-supervised detection framework. |
| first_indexed | 2024-03-10T00:36:37Z |
| format | Article |
| id | doaj.art-9eca7e21b6d9490fb1db3ef70a1b2c3b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T00:36:37Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-9eca7e21b6d9490fb1db3ef70a1b2c3b2023-11-23T15:16:06ZengMDPI AGRemote Sensing2072-42922022-01-0114233910.3390/rs14020339Weakly Supervised Detection of Marine Animals in High Resolution Aerial ImagesPaul Berg0Deise Santana Maia1Minh-Tan Pham2Sébastien Lefèvre3Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), UMR 6074, Université Bretagne Sud, F-56000 Vannes, FranceCentre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL), UMR 9189, Université de Lille, F-59000 Lille, FranceInstitut de Recherche en Informatique et Systèmes Aléatoires (IRISA), UMR 6074, Université Bretagne Sud, F-56000 Vannes, FranceInstitut de Recherche en Informatique et Systèmes Aléatoires (IRISA), UMR 6074, Université Bretagne Sud, F-56000 Vannes, FranceHuman activities in the sea, such as intensive fishing and exploitation of offshore wind farms, may impact negatively on the marine mega fauna. As an attempt to control such impacts, surveying, and tracking of marine animals are often performed on the sites where those activities take place. Nowadays, thank to high resolution cameras and to the development of machine learning techniques, tracking of wild animals can be performed remotely and the analysis of the acquired images can be automatized using state-of-the-art object detection models. However, most state-of-the-art detection methods require lots of annotated data to provide satisfactory results. Since analyzing thousands of images acquired during a flight survey can be a cumbersome and time consuming task, we focus in this article on the weakly supervised detection of marine animals. We propose a modification of the patch distribution modeling method (PaDiM), which is currently one of the state-of-the-art approaches for anomaly detection and localization for visual industrial inspection. In order to show its effectiveness and suitability for marine animal detection, we conduct a comparative evaluation of the proposed method against the original version, as well as other state-of-the-art approaches on two high-resolution marine animal image datasets. On both tested datasets, the proposed method yielded better F1 and recall scores (75% recall/41% precision, and 57% recall/60% precision, respectively) when trained on images known to contain no object of interest. This shows a great potential of the proposed approach to speed up the marine animal discovery in new flight surveys. Additionally, such a method could be adopted for bounding box proposals to perform faster and cheaper annotation within a fully-supervised detection framework.https://www.mdpi.com/2072-4292/14/2/339marine animal monitoringanomaly detectiondeep learningweakly supervised learningconvolutional neural networks |
| spellingShingle | Paul Berg Deise Santana Maia Minh-Tan Pham Sébastien Lefèvre Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images Remote Sensing marine animal monitoring anomaly detection deep learning weakly supervised learning convolutional neural networks |
| title | Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images |
| title_full | Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images |
| title_fullStr | Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images |
| title_full_unstemmed | Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images |
| title_short | Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images |
| title_sort | weakly supervised detection of marine animals in high resolution aerial images |
| topic | marine animal monitoring anomaly detection deep learning weakly supervised learning convolutional neural networks |
| url | https://www.mdpi.com/2072-4292/14/2/339 |
| work_keys_str_mv | AT paulberg weaklysuperviseddetectionofmarineanimalsinhighresolutionaerialimages AT deisesantanamaia weaklysuperviseddetectionofmarineanimalsinhighresolutionaerialimages AT minhtanpham weaklysuperviseddetectionofmarineanimalsinhighresolutionaerialimages AT sebastienlefevre weaklysuperviseddetectionofmarineanimalsinhighresolutionaerialimages |