Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images

被引:10
|
作者
Berg, Paul [1 ]
Maia, Deise Santana [2 ]
Pham, Minh-Tan [1 ]
Lefevre, Sebastien [1 ]
机构
[1] Univ Bretagne Sud, UMR 6074, Inst Rech Informat & Syst Aleatoires IRISA, F-56000 Vannes, France
[2] Univ Lille, UMR 9189, Ctr Rech Informat Signal & Automat Lille CRIStAL, F-59000 Lille, France
关键词
marine animal monitoring; anomaly detection; deep learning; weakly supervised learning; convolutional neural networks; ENERGY;
D O I
10.3390/rs14020339
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
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.
引用
收藏
页数:17
相关论文
共 50 条
  • [31] Deep Learning Approaches on Defect Detection in High Resolution Aerial Images of Insulators
    Wen, Qiaodi
    Luo, Ziqi
    Chen, Ruitao
    Yang, Yifan
    Li, Guofa
    [J]. SENSORS, 2021, 21 (04) : 1 - 26
  • [32] Robust Vehicle Detection in High-Resolution Aerial Images With Imbalanced Data
    Li X.
    Li X.
    Li Z.
    Xiong X.
    Khyam M.O.
    Sun C.
    [J]. IEEE Transactions on Artificial Intelligence, 2021, 2 (03): : 238 - 250
  • [33] Detection of mine-like objects in high-resolution aerial images
    Zhuravlev, Andrey V.
    Bugaev, Alexander S.
    Ivashov, Sergey I.
    Razevig, Vladimir V.
    [J]. ELECTRO-OPTICAL REMOTE SENSING, DETECTION, AND PHOTONIC TECHNOLOGIES AND THEIR APPLICATIONS, 2007, 6739
  • [34] Detection of Cars in High-Resolution Aerial Images of Complex Urban Environments
    ElMikaty, Mohamed
    Stathaki, Tania
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2017, 55 (10): : 5913 - 5924
  • [35] An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
    Shen, Yiqiu
    Wu, Nan
    Phang, Jason
    Park, Jungkyu
    Liu, Kangning
    Tyagi, Sudarshini
    Heacock, Laura
    Kim, S. Gene
    Moy, Linda
    Cho, Kyunghyun
    Geras, Krzysztof J.
    [J]. MEDICAL IMAGE ANALYSIS, 2021, 68
  • [36] Target Discrimination Based on Weakly Supervised Learning for High-Resolution SAR Images in Complex Scenes
    Du, Lan
    Dai, Hui
    Wang, Yan
    Xie, Weitong
    Wang, Zhaocheng
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2020, 58 (01): : 461 - 472
  • [37] HAMIL: High-Resolution Activation Maps and Interleaved Learning for Weakly Supervised Segmentation of Histopathological Images
    Zhong, Lanfeng
    Wang, Guotai
    Liao, Xin
    Zhang, Shaoting
    [J]. IEEE TRANSACTIONS ON MEDICAL IMAGING, 2023, 42 (10) : 2912 - 2923
  • [38] Weakly Supervised Road Segmentation in High-Resolution Remote Sensing Images Using Point Annotations
    Lian, Renbao
    Huang, Liqin
    [J]. IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2022, 60
  • [39] The possibility of using high resolution satellite images for detection of marine mammals
    Platonov, N. G.
    Mordvintsev, I. N.
    Rozhnov, V. V.
    [J]. BIOLOGY BULLETIN, 2013, 40 (02) : 197 - 205
  • [40] The possibility of using high resolution satellite images for detection of marine mammals
    N. G. Platonov
    I. N. Mordvintsev
    V. V. Rozhnov
    [J]. Biology Bulletin, 2013, 40 : 197 - 205