Applications of deep convolutional neural networks to predict length, circumference, and weight from mostly dewatered images of fish

Bravata, Nicholas; Kelly, Dylan; Eickholt, Jesse; Bryan, Janine; Miehls, Scott M.; Zielinski, Daniel

doi:10.1002/ece3.6618

Cited by 22 publications

(14 citation statements)

References 36 publications

(44 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another off-tank method is presented in Ref. [ 5 ], the dataset contains 694 images of fish from the 22 species of fish from 9 tributaries where images were captured. The fish’s weight is between 500 g and 1200 g. Six cameras were set at a fixed distance, with three being near-infrared cameras and three being general cameras.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…The performance of the weight estimation from Ref. [ 5 ] gains an MAE of 634 g. Secondly, underwater fish-weight estimation is presented in Ref. [ 7 ], where the fish weight-estimation methods are the weight prediction system for Nile Tilapia.…”

Section: Experimental Results and Analysismentioning

confidence: 99%

“…Firstly, in the case of off-water, fish weight-estimation-based CNNs are proposed in Refs. [5,41] by using ResNet-34 and LinkNet-34 for segmenting fish images, then the weight of the fish is computed from the surface area of the fish. The datasets from this research contain 2445 images of fish with weights in the The well-known weight estimation of fish can be categorized into two cases, in case of off-water and underwater scenarios.…”

Section: Maementioning

confidence: 99%

“…The strength of the regression principle is the simplicity of development and low computational complexity. Six cameras were set at a fixed distance—with three being near-infrared cameras and three being general cameras [ 5 ]—where a deep convolutional neural network (DCNN) estimated fish weight from the length, weight, and girth of the fish. The residual neural network (ResNet) and LinkNet for segmenting fish images then estimate the weight from the area of the detected fish [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models

Tengtrairat

Woo

Parathai

et al. 2022

Sensors

View full text Add to dashboard Cite

Underwater fish monitoring is the one of the most challenging problems for efficiently feeding and harvesting fish, while still being environmentally friendly. The proposed 2D computer vision method is aimed at non-intrusively estimating the weight of Tilapia fish in turbid water environments. Additionally, the proposed method avoids the issue of using high-cost stereo cameras and instead uses only a low-cost video camera to observe the underwater life through a single channel recording. An in-house curated Tilapia-image dataset and Tilapia-file dataset with various ages of Tilapia are used. The proposed method consists of a Tilapia detection step and Tilapia weight-estimation step. A Mask Recurrent-Convolutional Neural Network model is first trained for detecting and extracting the image dimensions (i.e., in terms of image pixels) of the fish. Secondly, is the Tilapia weight-estimation step, wherein the proposed method estimates the depth of the fish in the tanks and then converts the Tilapia’s extracted image dimensions from pixels to centimeters. Subsequently, the Tilapia’s weight is estimated by a trained model based on regression learning. Linear regression, random forest regression, and support vector regression have been developed to determine the best models for weight estimation. The achieved experimental results have demonstrated that the proposed method yields a Mean Absolute Error of 42.54 g, R2 of 0.70, and an average weight error of 30.30 (±23.09) grams in a turbid water environment, respectively, which show the practicality of the proposed framework.

show abstract

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: Experimental Results and Analysismentioning

confidence: 99%

Section: Maementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models

Tengtrairat

Woo

Parathai

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…Research has been carried out to automate the inspection and include counting the number of fish [22], detecting stocked fish [23], and classifying species [24]. Deep learning has been shown to be a promising method of estimating length, girth, and weight [25,26]. These are valuable tools for monitoring populations, and have been shown to provide good precision.…”

Section: Introductionmentioning

confidence: 99%

Photo Identification of Individual Salmo trutta Based on Deep Learning

Pedersen

Mohammed

2021

Applied Sciences

View full text Add to dashboard Cite

Individual fish identification and recognition is an important step in the conservation and management of fisheries. One of most frequently used methods involves capturing and tagging fish. However, these processes have been reported to cause tissue damage, premature tag loss, and decreased swimming capacity. More recently, marine video recordings have been extensively used for monitoring fish populations. However, these require visual inspection to identify individual fish. In this work, we proposed an automatic method for the identification of individual brown trouts, Salmo trutta. We developed a deep convolutional architecture for this purpose. Specifically, given two fish images, multi-scale convolutional features were extracted to capture low-level features and high-level semantic components for embedding space representation. The extracted features were compared at each scale for capturing representation for individual fish identification. The method was evaluated on a dataset called NINA204 based on 204 videos of brown trout and on a dataset TROUT39 containing 39 brown trouts in 288 frames. The identification method distinguished individual fish with 94.6% precision and 74.3% recall on a NINA204 video sequence with significant appearance and shape variation. The identification method takes individual fish and is able to distinguish them with precision and recall percentages of 94.6% and 74.3% on NINA204 for a video sequence with significant appearance and shape variation.

show abstract

Automated image analysis as a tool to measure individualised growth and population structure in Chinook salmon (Oncorhynchus tshawytscha)

Tuckey

Ashton

et al. 2022

Aquaculture Fish & Fisheries

View full text Add to dashboard Cite

Selective breeding programmes depend on high‐quality measurements of phenotype and genotype with repeated individualised phenotype measurements throughout the life cycle being optimal. Recent advances in electronics and computer vision technologies offer opportunities to improve both the quality, quantity and individualisation of repeated phenotypic measurements, but remain underutilised in aquaculture breeding programmes. In this study, we compare manual measurements of phenotypic traits of Chinook salmon (Oncorhynchus tshawytscha) with digital images and an automated software analysis pipeline written in the Python® programming language using the OpenCV machine vision library. Manual measurements of length, girth and weight of passive integrated transponder‐tagged individuals were compared with image‐based measures of 738 individuals over a time span from June–December 2019. Linear regressions showed strong correlations between manual and automated measurements for fork length, girth and weight (R2 = 0.989, R2 = 0.918, R2 = 0.987, respectively). Image‐based software measurements proved powerful for tracking general population changes in growth over the study period while retaining insights about subpopulations deviating from the average (e.g. losing weight). Taken together, our study demonstrates that image‐analysis can be used to estimate fish growth traits with a high degree of precision, requires reduced labour and demonstrates that additional knowledge can be gained through tracking individuals throughout production to harvest.

show abstract

Applications of deep convolutional neural networks to predict length, circumference, and weight from mostly dewatered images of fish

Cited by 22 publications

References 36 publications

Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models

Non-Intrusive Fish Weight Estimation in Turbid Water Using Deep Learning and Regression Models

Photo Identification of Individual Salmo trutta Based on Deep Learning

Automated image analysis as a tool to measure individualised growth and population structure in Chinook salmon (Oncorhynchus tshawytscha)

Contact Info

Product

Resources

About