Fish Detection and Tracking in Pisciculture Environment using Deep Instance Segmentation

Arvind, C.; Prajwal, R; Bhat, Prithvi Narayana; Sreedevi, A.; Prabhudeva, K N

doi:10.1109/tencon.2019.8929613

Cited by 22 publications

(10 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DL has already been used for fish detection in the field, most of the time to automatically detect and classify fish from underwater cameras ( Alshdaifat, Talib & Osman, 2020 ; Huang et al, 2019 ; Jalal et al, 2020 ; Li et al, 2018 ; Rathi, Jain & Indu, 2018 ; Jones, Webster & Salvanes, 2021 ). CNNs have been used also in fish tanks, to monitor fish farms ( Arvind et al, 2019 ) and to study collective movements ( Heras et al, 2019 ; Romero-Ferrero et al, 2019 ). However, to our knowledge, no one has yet applied this technology to study fish behavioural types, a growing field with vast ecological implications ( Conrad et al, 2011 ; Mittelbach, Ballew & Kjelvik, 2014 ; Smith & Blumstein, 2008 ).…”

Section: Introductionmentioning

confidence: 99%

Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning

Signaroli

Lana

Martorell-Barceló

et al. 2022

PeerJ

View full text Add to dashboard Cite

Deep learning allows us to automatize the acquisition of large amounts of behavioural animal data with applications for fisheries and aquaculture. In this work, we have trained an image-based deep learning algorithm, the Faster R-CNN (Faster region-based convolutional neural network), to automatically detect and track the gilthead seabream, Sparus aurata, to search for individual differences in behaviour. We collected videos using a novel Raspberry Pi high throughput recording system attached to individual experimental behavioural arenas. From the continuous recording during behavioural assays, we acquired and labelled a total of 14,000 images and used them, along with data augmentation techniques, to train the network. Then, we evaluated the performance of our network at different training levels, increasing the number of images and applying data augmentation. For every validation step, we processed more than 52,000 images, with and without the presence of the gilthead seabream, in normal and altered (i.e., after the introduction of a non-familiar object to test for explorative behaviour) behavioural arenas. The final and best version of the neural network, trained with all the images and with data augmentation, reached an accuracy of 92,79% ± 6.78% [89.24–96.34] of correct classification and 10.25 ± 61.59 pixels [6.59-13.91] of fish positioning error. Our recording system based on a Raspberry Pi and a trained convolutional neural network provides a valuable non-invasive tool to automatically track fish movements in experimental arenas and, using the trajectories obtained during behavioural tests, to assay behavioural types.

show abstract

Section: Introductionmentioning

confidence: 99%

Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning

Signaroli

Lana

Martorell-Barceló

et al. 2022

PeerJ

View full text Add to dashboard Cite

show abstract

“…On the other hand, object tracking can locate and output the movement direction and speed of objects between video frames. In marine ecosystems, object tracking has been used to track on‐surface objects (see topios.org) and underwater objects such as fish, sea turtles, dolphins, and whales (Arvind et al., 2019; Chuang et al., 2017; Kezebou et al., 2019; Spampinato et al., 2008; Xu & Cheng, 2017).…”

Section: Introductionmentioning

confidence: 99%

Automatic detection of fish and tracking of movement for ecology

Lopez‐Marcano

Jinks

Buelow

et al. 2021

Ecology and Evolution

View full text Add to dashboard Cite

show abstract

“…Fully Connected Networks (FCN; Shi et al, 2018) can also classify any shaped image. More recently, object detectors such as YOLOv3 (Knausgård et al, 2021), masked regionbased CNN for segmentation (Arvind et al, 2019;Ditria et al, 2020), or hybrid object detection models (Mohamed et al, 2020) have been shown to outperform traditional computer vision techniques (L. . DL models make predictions based on learning from labelled datasets and require substantial volumes of accurately data compared with traditional "rule"-based computer vision models (Rawat and Wang, 2017) but can extract ecologically useful information from video footage only when adequately trained (Cutter et al, 2015;Ditria et al, 2021, Ditria et al, 2020.…”

Section: Deep Learning For Fish Classification and Object Detectionmentioning

confidence: 99%

Accelerating Species Recognition and Labelling of Fish From Underwater Video With Machine-Assisted Deep Learning

et al. 2022

View full text Add to dashboard Cite

Machine-assisted object detection and classification of fish species from Baited Remote Underwater Video Station (BRUVS) surveys using deep learning algorithms presents an opportunity for optimising analysis time and rapid reporting of marine ecosystem statuses. Training object detection algorithms for BRUVS analysis presents significant challenges: the model requires training datasets with bounding boxes already applied identifying the location of all fish individuals in a scene, and it requires training datasets identifying species with labels. In both cases, substantial volumes of data are required and this is currently a manual, labour-intensive process, resulting in a paucity of the labelled data currently required for training object detection models for species detection. Here, we present a “machine-assisted” approach for i) a generalised model to automate the application of bounding boxes to any underwater environment containing fish and ii) fish detection and classification to species identification level, up to 12 target species. A catch-all “fish” classification is applied to fish individuals that remain unidentified due to a lack of available training and validation data. Machine-assisted bounding box annotation was shown to detect and label fish on out-of-sample datasets with a recall between 0.70 and 0.89 and automated labelling of 12 targeted species with an F1 score of 0.79. On average, 12% of fish were given a bounding box with species labels and 88% of fish were located and given a fish label and identified for manual labelling. Taking a combined, machine-assisted approach presents a significant advancement towards the applied use of deep learning for fish species detection in fish analysis and workflows and has potential for future fish ecologist uptake if integrated into video analysis software. Manual labelling and classification effort is still required, and a community effort to address the limitation presented by a severe paucity of training data would improve automation accuracy and encourage increased uptake.

show abstract

Fish Detection and Tracking in Pisciculture Environment using Deep Instance Segmentation

Cited by 22 publications

References 6 publications

Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning

Measuring inter-individual differences in behavioural types of gilthead seabreams in the laboratory using deep learning

Automatic detection of fish and tracking of movement for ecology

Accelerating Species Recognition and Labelling of Fish From Underwater Video With Machine-Assisted Deep Learning

Contact Info

Product

Resources

About