Deep Learning Techniques for Beef Cattle Body Weight Prediction

Gjergji, Mikel; Weber, Vanessa; Silva, Luiz Otavio Campos; Gomes, Rodrigo da Costa; Araújo, Thiago Luís Alves Campos de; Pistori, Hemerson; Álvarez, Marco

doi:10.1109/ijcnn48605.2020.9207624

Cited by 27 publications

(22 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since feature selection in previous work has been typically done manually and is prone to human error during the image processing stage, Gjergji et al (2020) employed DL—a novel approach capable to automatically extract relevant features from digital images and known to outperform traditional ML models for both classification and regression problems for a large number of CV problems. The authors explored the prediction performance of CNN, RCNNs, RAMs, and RAMs with CNN to predict beef cattle weight using CV techniques.…”

Section: And CV Methods For Bw Predictionmentioning

confidence: 99%

“…While animal biometrics is an emerging field focused on quantification and detection of the phenotypic appearance of species, individuals, behaviors, and morphological traits ( Kühl and Burghardt, 2013 ), animal morphometrics ( Rohlf, 1990 ; Adams et al, 2004 ; Doyle et al, 2018 ) is almost exclusively focused on landmark-based methods (and less on outline-based methods) using quantitative analysis of form relying on measuring the size and shape of animals, and the relation between size and shape (allometry). Estimation of livestock BW using biometric and morphometric measurements has been studied in detail for various species, such as cattle ( Taşdemir et al, 2011a , b ; Miller et al, 2019 ; Tasdemir and Ozkan, 2019 ; Gjergji et al, 2020 ; de Moraes Weber et al, 2020 ; Rudenko, 2020 ), pigs ( Brandl and Jørgensen, 1996 ; O’Connell et al, 2007 ; Mutua et al, 2011 ; Sungirai et al, 2014 ; Al Ard Khanji et al, 2018 ), sheep ( Eyduran et al, 2015 ; Huma and Iqbal, 2019 ), goats ( Sebolai et al, 2012 ; Eyduran et al, 2017 ; Temoso et al, 2017 ), camels ( Fadlelmoula et al, 2020 ; de Moraes Weber et al, 2020 ), yaks ( Yan et al, 2019 ), poultry ( Mendeş and Akkartal, 2009 ), and fish ( Fernandes et al, 2020b ). This process is typically applied to avoid drawbacks associated with manually performed individual animal weighing such as: 1) the animal and manual laborer stress associated with animal relocation, 2) the costs associated with this labor-intensive process, and 3) the significant cost associated with acquiring and maintaining industrial scales.…”

Section: Biometric and Morphometric Measurements For Bw Predictionmentioning

confidence: 99%

“…Nevertheless, these low-level technologies are affected by animal breed, feeding method, animal satiety level, and the elasticity or plasticity of the measuring tapes or tubes ( Joo, 2010 ). A paradigm shift in morphometric estimations via advanced systems can be observed in recent years, when computer vision (CV) and deep learning (DL) techniques are increasingly applied to this problem and more abstract image features, such as body area and texture patterns ( Gjergji et al, 2020 ) that are not directly connected to previously applied morphometric measurements are used to predict BW with increasing success.…”

Section: Introductionmentioning

confidence: 99%

“…The DL modeling component typically includes image selection, morphometric feature extraction, and feature selection as part of complex neural network architectures such as convolutional neural networks—CNNs ( Fukushima, 1980 ), recurrent convolutional neural networks—RCNNs/RNNs ( Spoerer et al, 2017 ), recurrent attention models—RAMs ( Mnih et al, 2014 ), and RAMs with CNNs ( Ba et al, 2014 ). Preliminary livestock studies implementing this approach reported significant improvements for BW prediction when compared with more traditional approaches ( Fernandes et al, 2019 , 2020a ; Gjergji et al, 2020 ), nevertheless there is plenty of space for improvements particularly on the precise automatic segmentation of animals from images with complex backgrounds, confounding backgrounds (similar colour as the subjects) or multiple subjects. This task can be addressed using various approaches such as the active shape model proposed by ( Cootes et al, 1993 ) and successfully applied by ( Wirthgen et al, 2011 ) using infrared thermography or a texture-based segmentation approach using a semi-supervised learning method proposed by ( Shukla and Anand, 2016 ).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

ASAS-NANP SYMPOSIUM: Applications of machine learning for livestock body weight prediction from digital images

Wang

Shadpour

Chan

et al. 2021

Journal of Animal Science

View full text Add to dashboard Cite

Monitoring, recording, and predicting livestock body weight (BW) allows for timely intervention in diets and health, greater efficiency in genetic selection, and identification of optimal times to market animals because animals that have already reached the point of slaughter represent a burden for the feedlot. There are currently two main approaches (direct and indirect) to measure the BW in livestock. Direct approaches include partial-weight or full-weight industrial scales placed in designated locations on large farms that measure passively or dynamically the weight of livestock. While these devices are very accurate, their acquisition, intended purpose and operation size, repeated calibration and maintenance costs associated with their placement in high-temperature variability, and corrosive environments are significant and beyond the affordability and sustainability limits of small and medium size farms and even of commercial operators. As a more affordable alternative to direct weighing approaches, indirect approaches have been developed based on observed or inferred relationships between biometric and morphometric measurements of livestock and their BW. Initial indirect approaches involved manual measurements of animals using measuring tapes and tubes and the use of regression equations able to correlate such measurements with BW. While such approaches have good BW prediction accuracies, they are time consuming, require trained and skilled farm laborers, and can be stressful for both animals and handlers especially when repeated daily. With the concomitant advancement of contactless electro-optical sensors (e.g., 2D, 3D, infrared cameras), computer vision (CV) technologies, and artificial intelligence fields such as machine learning (ML) and deep learning (DL), 2D and 3D images have started to be used as biometric and morphometric proxies for BW estimations. This manuscript provides a review of CV-based and ML/DL-based BW prediction methods and discusses their strengths, weaknesses, and industry applicability potential.

show abstract

Section: And CV Methods For Bw Predictionmentioning

confidence: 99%

Section: Biometric and Morphometric Measurements For Bw Predictionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

ASAS-NANP SYMPOSIUM: Applications of machine learning for livestock body weight prediction from digital images

Wang

Shadpour

Chan

et al. 2021

Journal of Animal Science

View full text Add to dashboard Cite

show abstract

“…Furthermore, deep learning was used for predicting the weight of cattle in Ref. [ 21 ]. Deep learning extends to perform the regression task with automatic feature extraction given by 2-dimensional images.…”

Section: Introductionmentioning

confidence: 99%

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