Next Article in Journal
Assessing the Potential of Remotely-Sensed Drone Spectroscopy to Determine Live Coral Cover on Heron Reef
Previous Article in Journal
UAVs Trajectory Optimization for Data Pick Up and Delivery with Time Window
Article

SeeCucumbers: Using Deep Learning and Drone Imagery to Detect Sea Cucumbers on Coral Reef Flats

1
College of Science and Engineering, James Cook University Townsville, Bebegu Yumba Campus, 1 James Cook Drive Douglas, Townsville, QLD 4811, Australia
2
TropWATER, College of Science and Engineering, James Cook University Townsville, Bebegu Yumba Campus, 1 James Cook Drive Douglas, Townsville, QLD 4811, Australia
3
TropWATER, College of Science and Engineering, James Cook University Cairns, Nguma-bada Campus, 14-88 McGregor Road Smithfield, Cairns, QLD 4878, Australia
4
School of Engineering and Mathematics Science, La Trobe University, Melbourne, VIC 3086, Australia
*
Author to whom correspondence should be addressed.
Academic Editor: David R. Green
Drones 2021, 5(2), 28; https://doi.org/10.3390/drones5020028
Received: 25 March 2021 / Revised: 11 April 2021 / Accepted: 13 April 2021 / Published: 16 April 2021
Sea cucumbers (Holothuroidea or holothurians) are a valuable fishery and are also crucial nutrient recyclers, bioturbation agents, and hosts for many biotic associates. Their ecological impacts could be substantial given their high abundance in some reef locations and thus monitoring their populations and spatial distribution is of research interest. Traditional in situ surveys are laborious and only cover small areas but drones offer an opportunity to scale observations more broadly, especially if the holothurians can be automatically detected in drone imagery using deep learning algorithms. We adapted the object detection algorithm YOLOv3 to detect holothurians from drone imagery at Hideaway Bay, Queensland, Australia. We successfully detected 11,462 of 12,956 individuals over 2.7ha with an average density of 0.5 individual/m2. We tested a range of hyperparameters to determine the optimal detector performance and achieved 0.855 mAP, 0.82 precision, 0.83 recall, and 0.82 F1 score. We found as few as ten labelled drone images was sufficient to train an acceptable detection model (0.799 mAP). Our results illustrate the potential of using small, affordable drones with direct implementation of open-source object detection models to survey holothurians and other shallow water sessile species. View Full-Text
Keywords: holothurian; remote sensing; UAV; machine learning; object detection; YOLOv3; Great Barrier Reef; marine ecology; ecological monitoring; FAIR data holothurian; remote sensing; UAV; machine learning; object detection; YOLOv3; Great Barrier Reef; marine ecology; ecological monitoring; FAIR data
Show Figures

Figure 1

MDPI and ACS Style

Li, J.Y.Q.; Duce, S.; Joyce, K.E.; Xiang, W. SeeCucumbers: Using Deep Learning and Drone Imagery to Detect Sea Cucumbers on Coral Reef Flats. Drones 2021, 5, 28. https://doi.org/10.3390/drones5020028

AMA Style

Li JYQ, Duce S, Joyce KE, Xiang W. SeeCucumbers: Using Deep Learning and Drone Imagery to Detect Sea Cucumbers on Coral Reef Flats. Drones. 2021; 5(2):28. https://doi.org/10.3390/drones5020028

Chicago/Turabian Style

Li, Joan Y.Q.; Duce, Stephanie; Joyce, Karen E.; Xiang, Wei. 2021. "SeeCucumbers: Using Deep Learning and Drone Imagery to Detect Sea Cucumbers on Coral Reef Flats" Drones 5, no. 2: 28. https://doi.org/10.3390/drones5020028

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop