Abstract
Abstract This paper presents and evaluates a method for detecting and counting demersal fish species in complex, cluttered, and occluded environments that can be installed on the conveyor belts of fishing vessels. Fishes on the conveyor belt were recorded using a colour camera and were detected using a deep neural network. To improve the detection, synthetic data were generated for rare fish species. The fishes were tracked over the consecutive images using a multi-object tracking algorithm, and based on multiple observations, the fish species was determined. The effect of the synthetic data, the amount of occlusion, and the observed dorsal or ventral fish side were investigated and a comparison with human electronic monitoring (EM) review was made. Using the presented method, a weighted counting error of 20% was achieved, compared to a counting error of 7% for human EM review on the same recordings.
Highlights
Fisheries management often relies on population models that integrate fisheries data, including catch estimates (Beverton and Holt, 1957; Rijnsdorp et al, 2007; Bradshaw et al, 2018)
Adding synthetic data had a limited effect on the precision, but substantially improved the macro recall and the F1-score. This makes sense since the frequency of the less frequent fish species is mainly increased in the training dataset
The model having 200 additional synthetic images has both the highest weighted and macro F1-score and is used in the rest of the experiments described in this paper
Summary
Fisheries management often relies on population models that integrate fisheries data, including catch estimates (Beverton and Holt, 1957; Rijnsdorp et al, 2007; Bradshaw et al, 2018). Discarding of fish occurs because of market conditions or fishery management regulations, such as minimum landing sizes or quotas (Catchpole et al, 2005; Rochet and Trenkel, 2005; Poos et al, 2009). Attempts to collect information on discarded catch are generally done at sea via on-board observer programmes (Fernandes et al, 2011; Snyder and Erbaugh, 2020). In these programmes, trained personnel collect numbers, weights, length, age, and species compositions of the discarded part of the catch (Uhlmann et al, 2013). At-sea observer programmes are expensive and time-consuming, often cover only a small fraction of the overall fishing effort of fishing fleets
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
