Using automated video analysis to study fish escapement through escape panels in active fishing gears: Application to the effect of net colour. (June 2020)

• Record Type: Journal Article
• Authors: Simon, Julien; Kopp, Dorothée; Larnaud, Pascal; Vacherot, Jean-Philippe; Morandeau, Fabien; Lavialle, Gaël; Morfin, Marie
• Is Part Of: Marine policy. Volume 116(2020)
• Publication Date: 2020-06
• Subjects: Trawl selectivity -- Fish behaviour -- Underwater videos -- Computer vision -- Object detection -- Object tracking; Marine resources -- Economic aspects -- Periodicals; Fisheries -- Periodicals; Ressources marines -- Aspect économique -- Périodiques; Pêches -- Périodiques; Fisheries; Marine resources -- Economic aspects; Periodicals; 333.916405
• DOI: 10.1016/j.marpol.2019.103785
• Languages: English
• ISSNs: 0308-597X

Abstract

Abstract: Quantification of the escapement rate of unwanted fish through a selective device is usually based on catch comparison. This study proposes a new, time efficient method to automatically compare two selective devices by automated counting of fish escapements through each selective device based on video sequences. First, sea trials were conducted to record video sequences of fish escaping a white and black square mesh panel. Then, all of the underwater sequences were automatically analysed by a computer vision software for automated object detection and tracking. Finally, the algorithm was assessed using 150 min of video sequences analysed by humans. We observed that the variability in escapements rate between all the observers on reference video sequences could reach 5%. As the difference in escapements rate between the algorithm and the observers was lower than the variability between observers, the automated approach was validated. The software detected a significant difference in fish escapement rate according to the net colour in the camera field of view: 60% of all fish escaped through the white panel. Our results suggest that net colour influences the escape rates of fish. The colour of the selective device should therefore be investigated further with the aim of increasing their efficiency. Further development of the software could be done to identify species and size of the fish and assess the effectiveness of a selective device by species and size. Highlights: Computer vision was used to automatically compare the escapement rate from two selective devices based on video sequences. The detection ability of the software was compared with the one of human observers. Automated counts showed good reliability overall and followed the trends of manual counts. Results show that net colour may influences the effectiveness of the selective device. Automated image processing increase the ability to analyse data while reducing the time required to do so.