@article{fdi:010094268,
  title = {{A}utomatic coral morphotypes detection with {YOLO} : a deep learning approach for efficient and accurate coral reef monitoring},
  author = {{O}uassine, {Y}. and {Z}ahir, {J}. and {C}onruyt, {N}. and {K}ayal, {M}ohsen and {M}artin, {P}. {A}. and {C}henin, {E}ric and {B}igot, {L}. and {L}ebbe, {R}. {V}.},
  editor = {},
  language = {{ENG}},
  abstract = {{C}oral reefs harbor a large portion of marine biodiversity but are declining rapidly. {C}onservation efforts rely on monitoring coral abundance and composition as predominant indicators of ecosystem health and management success. {H}owever, manual monitoring of coral abundance proves arduous where artificial intelligence-based automatization can help improve efficiency and accuracy. {T}his paper presents a methodology using {YOLO}v5-based deep learning for automatic detection of corals and classification by morphotype, representing an important step toward streamlining machine-assisted coral reef monitoring. {T}he research addresses the escalating need for precise and timely ecosystem assessments amidst increasing ecological shifts of coral reefs. {U}sing state-of-the-art object detection techniques, the study strives to streamline the detection and classification of diverse coral morphotypes, which is essential for understanding reef dynamics and assessing conservation efforts. {T}o train and evaluate our system, we use a dataset consisting of 280 original underwater coral reef images. {W}e increased the number of annotated images to 388 by manipulating images using data augmentation techniques, which can improve model performance by providing more diverse examples for training. {O}ur system leverages the {YOLO}v5 algorithm's real-time object detection capabilities, enabling efficient and accurate coral detection. {W}e used {YOLO}v5 to extract discriminating features from the annotated dataset, enabling the system to generalize, including previously unseen underwater images. {T}he successful implementation of the automatic coral morphotypes detection system with {YOLO}v5 on our original image dataset highlights the potential of advanced computer vision techniques for coral reef research and conservation.},
  keywords = {{M}achine {L}earning ; {D}eep {L}earning ; {U}nderwater ecosystems ; {C}orals ; {O}bject ; {D}etection ; {YOLO}v5},
  booktitle = {},
  journal = {{A}rtificial {I}ntelligence for {K}nowledge {M}anagement, {E}nergy and {S}ustainability},
  volume = {693},
  numero = {},
  pages = {177--188},
  ISSN = {1868-4238},
  year = {2024},
  DOI = {10.1007/978-3-031-61069-1_13},
  URL = {https://www.documentation.ird.fr/hor/fdi:010094268},
}