The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Download
Publications Copernicus
Download
Citation
Articles | Volume XLVI-4/W3-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVI-4/W3-2021, 191–198, 2022
https://doi.org/10.5194/isprs-archives-XLVI-4-W3-2021-191-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVI-4/W3-2021, 191–198, 2022
https://doi.org/10.5194/isprs-archives-XLVI-4-W3-2021-191-2022
 
10 Jan 2022
10 Jan 2022

AUTOMATIC FISH DETECTION FROM DIFFERENT MARINE ENVIRONMENTS VIDEO USING DEEP LEARNING

A. Loulidi1, R. Houssa2, L. Buhl-Mortensen3, H. Zidane2, and H. Rhinane1 A. Loulidi et al.
  • 1Laboratory of Geosciences, Department of Geology, Faculty of Sciences, University Hassan II, Casablanca, Morocco
  • 2National Institute of Fisheries Research (INRH), Casablanca, Morocco
  • 3Institute of Marine Research, Bergen, Norway

Keywords: Fish Detection, Marine Environment, Yolov3, Deep Learning, Computer Vision, Artificial Intelligence

Abstract. The marine environment provides many ecosystems that support habitats biodiversity. Benthic habitats and fish species associations are investigated using underwater gears to secure and manage these marine ecosystems in a sustainable manner. The current study evaluates the possibility of using deep learning methods in particular the You Only Look Once version 3 algorithm to detect fish in different environments such as; different shading, low light, and high noise within images and by each frame within an underwater video, recorded in the Atlantic Coast of Morocco. The training dataset was collected from Open Images Dataset V6, a total of 1295 Fish images were captured and split into a training set and a test set. An optimization approach was applied to the YOLOv3 algorithm which is data augmentation transformation to provide more learning samples. The mean average precision (mAP) metric was applied to measure the YOLOv3 model’s performance. Results of this study revealed with a mAP of 91,3% the proposed method is proved to have the capability of detecting fish species in different natural marine environments also it has the potential to be applied to detect other underwater species and substratum.