Search

1. 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, labour intensive, costly, and measuring movement of many individuals is challenging. Automated detection and tracking of small-scale movements of many animals through cameras are possible. However, automated techniques are largely untested in field conditions, and this is hampering applications to ecological questions. 2. Here, we aimed to test the ability of computer vision algorithms to track small-scale movement of many individuals in videos. We apply the method to track fish movement in the field and characterize movement behaviour. First, we automated the detection of a common fisheries species (yellowfin bream, Acanthopagrus australis) from underwater videos of individuals swimming along a known movement corridor. We then tracked fish movement with three types of tracking algorithms (MOSSE, Seq-NMS and SiamMask), and evaluated their accuracy at characterizing movement. 3. We successfully detected yellowfin bream in a multi-species 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%. 4. By employing these emerging computer vision technologies, we demonstrated a non-invasive and reliable approach to studying fish behaviour by tracking their movement under field conditions. These cost-effective technologies potentially will allow future studies to scale-up analysis of movement across many underwater visual monitoring systems.

Source at http://hdl.handle.net/11250/2598650 A commercial scale sea-cage design, combining skirt and freshwater lens concepts with smart lighting and feeding for improved lice prevention and fish welfare, was trialed. Environment, lice levels and fish welfare were assessed. In addition, acoustic tags and echo sounders were used to track fish behaviour. An associated laboratory trial on brackish water salinity effects on host-attached salmon lice was also conducted. We found that within the interval standard skirt and freshwater lens skirt cages were fully-functioning, there was no significant effect on lice levels or fish welfare. Fish behaviour monitoring found variable use of the freshwater lens, though night lighting appeared to increase fish residence in the low salinity space provided. From this work an ultimate conclusion on the effectiveness of this technology cannot be drawn, but it is clear that a less saline brackish water is needed in combination with higher residence time of the fish to have a substantial reducing effect on lice levels on caged salmon. The lab scale trial suggested that to delay host-attached lice development < 12 ppt is required and to kill host-attached copepodids < 4 ppt is needed over durations of 3 hours or more. Prosjektet undersøkte om kombinasjon av brakkvannsbasseng, luseskjørt, målrettet belysning og dyp fôring i kommersielle merder var effektivt i å forebygge lusepåslag. Grunnleggende kunnskap om laksens valg av opphold i brakkvann ble studert med individmerket laks og dødelighet hos lakseluskopepoditter i kar med ulike brakkvann og oppholdstid. Ingen signifikant effekt på lusenivå eller fiskevelferd ble funnet av standardskjørt og brakkvannsbasseng i perioden da oppsettet fungerte optimalt. Laksen hadde variabel bruk av bassenget, og nattbelysning så ut til å øke fiskens oppholdstid i brakkvannet. En endelig konklusjon om effektiviteten mot lus av denne teknologien kan imidlertid ikke trekkes. En kan imidlertid konkludere at det er et klart behov for lavere saltholdighet i kombinasjon med høyere oppholdstid for at brakkvannet skal kunne ha en betydelig reduserende effekt på lusens påslag, dødelighet og utviklingstid. Karforsøkene viste at lusens utviklingstid ble forsinket ved saltholdigheter < 12 ppt, og for å ta livet av påslåtte kopepoditter er det nødvendig med saltholdighet < 4 ppt over 3 timer eller lengre.