Automatic Weight Estimation of Harvested Fish from Images

Konovalov, Dmitry A.; Saleh, Alzayat; Efremova, Dina B.; Domingos, Jose A.; Jerry, Dean R.

doi:10.1109/dicta47822.2019.8945971

Cited by 56 publications

(32 citation statements)

References 28 publications

(67 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The goal of these annotations is to train and evaluate models to segment fish across images. As a result, the segmentation output can be used to estimate fish sizes, shapes, and their weight as shown in 18,20 . These are important statistics that can be useful in applications like commercial trawling 10 .…”

Section: Data Collectionmentioning

confidence: 99%

A realistic fish-habitat dataset to evaluate algorithms for underwater visual analysis

Saleh

Laradji

Коновалов

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

Visual analysis of complex fish habitats is an important step towards sustainable fisheries for human consumption and environmental protection. Deep Learning methods have shown great promise for scene analysis when trained on large-scale datasets. However, current datasets for fish analysis tend to focus on the classification task within constrained, plain environments which do not capture the complexity of underwater fish habitats. To address this limitation, we present DeepFish as a benchmark suite with a large-scale dataset to train and test methods for several computer vision tasks. The dataset consists of approximately 40 thousand images collected underwater from 20 habitats in the marine-environments of tropical Australia. The dataset originally contained only classification labels. Thus, we collected point-level and segmentation labels to have a more comprehensive fish analysis benchmark. These labels enable models to learn to automatically monitor fish count, identify their locations, and estimate their sizes. Our experiments provide an in-depth analysis of the dataset characteristics, and the performance evaluation of several state-of-the-art approaches based on our benchmark. Although models pre-trained on ImageNet have successfully performed on this benchmark, there is still room for improvement. Therefore, this benchmark serves as a testbed to motivate further development in this challenging domain of underwater computer vision. Monitoring fish in their natural habitat is an important step towards sustainable fisheries. In the New South Wales state of Australia, for example, fisheries is valued at more than 100 million Australian dollars in 2012-2013 14. Effective monitoring can provide information about which areas require protection and restoration to maintain healthy fish populations for both human consumption and environmental protection. Having a system that can automatically perform comprehensive monitoring can significantly reduce labour costs and increase efficiency. The system can lead to a large positive sustainability impact and improve our ability to maintain a healthy ecosystem. Deep learning methods have consistently achieved state-of-the-art results in image analysis. Many methods based on deep neural networks achieved top performance for a variety of applications, including, ecological monitoring with camera trap data. One reason behind this success is that these methods can leverage largescale, publicly available datasets such as ImageNet 6 and COCO 24 for training before being fine-tuned for a new application. A particularly challenging application involves automatic analysis of underwater fish habitats which demands a comprehensive, accurate computer vision system. Thus, considerable research efforts have been put towards developing systems for the task of understanding complex marine environments and distinguishing between a diverse set of fish species, which are based on publicly available fish datasets 1,3,8,15,35. However, these fish datasets are small and do not fully capture t...

show abstract

Section: Data Collectionmentioning

confidence: 99%

A realistic fish-habitat dataset to evaluate algorithms for underwater visual analysis

Saleh

Laradji

Коновалов

et al. 2020

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

“…Semantic Segmentation is an important computer vision task that can be applied to many real-life applications 11,25,41 Semantic Segmentation Methods for Fish Analysis have been used for efficient, automatic extraction of fish body measurements 16 , and prediction of their body weight 16,27,28 and shape for the purposes of preserving marine life. Garcia et al 18 used fully-supervised segmentation methods and the Mask R-CNN 22 architecture to localize and segment each individual fish in underwater images to obtain an estimate of the boundary of every fish in the image for estimating fish sizes to prevent catches of undersized fish.…”

Section: Related Workmentioning

confidence: 99%

Weakly Supervised Underwater Fish Segmentation Using Affinity LCFCN

Saleh

Laradji

Rodríguez

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Estimating fish body measurements like length, width, and mass has received considerable research due to its potential in boosting productivity in marine and aquaculture applications. Some methods are based on manual collection of these measurements using tools like a ruler which is time consuming and labour intensive. Others rely on fully-supervised segmentation models to automatically acquire these measurements but require collecting per-pixel labels which are also time consuming. It can take up to 2 minutes per fish to acquire accurate segmentation labels. To address this problem, we propose a segmentation model that can efficiently train on images labeled with point-level supervision, where each fish is annotated with a single click. This labeling scheme takes an average of only 1 second per fish. Our model uses a fully convolutional neural network with one branch that outputs per-pixel scores and another that outputs an affinity matrix. These two outputs are aggregated using a random walk to get the final, refined per-pixel output. The whole model is trained end-to-end using the LCFCN loss and thus we call our method Affinity-LCFCN (A-LCFCN). We conduct experiments on the DeepFish dataset, which contains several fish habitats from north-eastern Australia. The results show that A-LCFCN outperforms a fully-supervised segmentation model when the annotation budget is fixed. They also show that A-LCFCN achieves better segmentation results than LCFCN and a standard baseline.

show abstract

“…In particular, estimates are provided for the LWR parameters a and b in general as well as by body shape. Konovalov trained two instances of LinkNet‐34 segmented convolutional neural network (CNN) (Konovalov et al., 2019). Two instances include fish masks with excluded fins and tails and whole‐fish masks.…”

Section: Estimation Of the Weight And Length Of Fishmentioning

confidence: 99%