Automatic detection of fish and tracking of movement for ecology. Issue 12 (18th May 2021)

• Record Type: Journal Article
• Authors: Lopez‐Marcano, Sebastian; L. Jinks, Eric; Buelow, Christina A.; Brown, Christopher J.; Wang, Dadong; Kusy, Branislav; M. Ditria, Ellen; Connolly, Rod M.
• Is Part Of: Ecology and evolution. Volume 11:Issue 12(2021)
• Page Start: 8254
• Page End: 8263
• Publication Date: 2021-05-18
• Subjects: computer vision -- connectivity -- deep learning -- dispersal -- machine learning -- object tracking -- underwater video; Ecology -- Periodicals; Evolution -- Periodicals; 577.05
• DOI: 10.1002/ece3.7656
• Languages: English
• ISSNs: 2045-7758

Abstract

Abstract: Animal movement studies are conducted to monitor ecosystem health, understand ecological dynamics, and address management and conservation questions. In marine environments, traditional sampling and monitoring methods to measure animal movement are invasive, labor intensive, costly, and limited in the number of individuals that can be feasibly tracked. Automated detection and tracking of small‐scale movements of many animals through cameras are possible but are largely untested in field conditions, hampering applications to ecological questions. Here, we aimed to test the ability of an automated object detection and object tracking pipeline to track small‐scale movement of many individuals in videos. We applied the pipeline to track fish movement in the field and characterize movement behavior. We automated the detection of a common fisheries species (yellowfin bream, Acanthopagrus australis) along a known movement passageway from underwater videos. We then tracked fish movement with three types of tracking algorithms (MOSSE, Seq‐NMS, and SiamMask) and evaluated their accuracy at characterizing movement. We successfully detected yellowfin bream in a multispecies assemblage (F1 score =91%). At least 120 of the 169 individual bream present in videos were correctly identified and tracked. The accuracies among the three tracking architectures varied, with MOSSE and SiamMask achieving an accuracy of 78% and Seq‐NMS 84%. By employing this integrated object detection and tracking pipeline, we demonstrated a noninvasive and reliable approach to studying fish behavior by tracking their movement under field conditions. These cost‐effective technologies provide a means for future studies to scale‐up the analysis of movement across many visual monitoring systems. Abstract : We applied automatic object detection and object tracking to track fish movement in the field and characterise movement behaviour.