Building the “Automatic Body Condition Assessment System” (ABiCA), an Automatic Body Condition Scoring System using Active Shape Models and Machine Learning

Tedin, Rafael; Becerra, J. A.; Duro, Richard J.

doi:10.1007/978-3-319-01649-8_10

Cited by 6 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several attempts have been made to automate the BCS process, mainly by including an analysis of the cow's contour and shape (Sharony, 2003;Peacock et al, 2006;Halachmi et al, 2008;Bercovich et al, 2013;Salau et al, 2014;Tedín et al, 2014;Weber et al, 2014;Caccamo et al, 2015). However, these systems still require some level of human interference.…”

Section: Introductionmentioning

confidence: 98%

Development of automatic body condition scoring using a low-cost 3-dimensional Kinect camera

Spoliansky

Edan

Parmet

et al. 2016

Journal of Dairy Science

139

View full text Add to dashboard Cite

Body condition scoring (BCS) is a farm-management tool for estimating dairy cows' energy reserves. Today, BCS is performed manually by experts. This paper presents a 3-dimensional algorithm that provides a topographical understanding of the cow's body to estimate BCS. An automatic BCS system consisting of a Kinect camera (Microsoft Corp., Redmond, WA) triggered by a passive infrared motion detector was designed and implemented. Image processing and regression algorithms were developed and included the following steps: (1) image restoration, the removal of noise; (2) object recognition and separation, identification and separation of the cows; (3) movie and image selection, selection of movies and frames that include the relevant data; (4) image rotation, alignment of the cow parallel to the x-axis; and (5) image cropping and normalization, removal of irrelevant data, setting the image size to 150×200 pixels, and normalizing image values. All steps were performed automatically, including image selection and classification. Fourteen individual features per cow, derived from the cows' topography, were automatically extracted from the movies and from the farm's herd-management records. These features appear to be measurable in a commercial farm. Manual BCS was performed by a trained expert and compared with the output of the training set. A regression model was developed, correlating the features with the manual BCS references. Data were acquired for 4 d, resulting in a database of 422 movies of 101 cows. Movies containing cows' back ends were automatically selected (389 movies). The data were divided into a training set of 81 cows and a test set of 20 cows; both sets included the identical full range of BCS classes. Accuracy tests gave a mean absolute error of 0.26, median absolute error of 0.19, and coefficient of determination of 0.75, with 100% correct classification within 1 step and 91% correct classification within a half step for BCS classes. Results indicated good repeatability, with all standard deviations under 0.33. The algorithm is independent of the background and requires 10 cows for training with approximately 30 movies of 4 s each.

show abstract

Section: Introductionmentioning

confidence: 98%

Development of automatic body condition scoring using a low-cost 3-dimensional Kinect camera

Spoliansky

Edan

Parmet

et al. 2016

Journal of Dairy Science

139

View full text Add to dashboard Cite

show abstract

“…Thus, there is potential in technology such as digital images [26] to increase accuracy and objectivity in BCS compared to the traditional methodology of time consuming and subjective observer dependent manual scoring [27]. Recently, a variety of solutions for improved body condition scoring have been developed and tested, such as thermal imaging [28], the utilization of Fourier descriptors using still photos [29], machine learning [30], and 3D technology [31,32]. However, the above-mentioned systems are yet to be fully automated.…”

Section: Introductionmentioning

confidence: 99%

Validation of a Commercial Automated Body Condition Scoring System on a Commercial Dairy Farm

Mullins

Truman

Campler

et al. 2019

Animals

View full text Add to dashboard Cite

Body condition scoring (BCS) is the management practice of assessing body reserves of individual animals by visual or tactile estimation of subcutaneous fat and muscle. Both high and low BCS can negatively impact milk production, disease, and reproduction. Visual or tactile estimation of subcutaneous fat reserves in dairy cattle relies on their body shape or thickness of fat layers and muscle on key areas of the body. Although manual BCS has proven beneficial, consistent qualitative scoring can be difficult to implement. The desirable BCS range for dairy cows varies within lactation and should be monitored at multiple time points throughout lactation for the most impact, a practice that can be hard to implement. However, a commercial automatic BCS camera is currently available for dairy cattle (DeLaval Body Condition Scoring, BCS DeLaval International AB, Tumba, Sweden). The objective of this study was to validate the implementation of an automated BCS system in a commercial setting and compare agreement of the automated body condition scores with conventional manual scoring. The study was conducted on a commercial farm in Indiana, USA, in April 2017. Three trained staff members scored 343 cows manually using a 1 to 5 BCS scale, with 0.25 increments. Pearson’s correlations (0.85, scorer 1 vs. 2; 0.87, scorer 2 vs. 3; and 0.86, scorer 1 vs. 3) and Cohen’s Kappa coefficients (0.62, scorer 1 vs. 2; 0.66, scorer 2 vs. 3; and 0.66, scorer 1 vs. 3) were calculated to assess interobserver reliability, with the correlations being 0.85, 0.87, and 0.86. The automated camera BCS scores were compared with the averaged manual scores. The mean BCS were 3.39 ± 0.32 and 3.27 ± 0.27 (mean ± SD) for manual and automatic camera scores, respectively. We found that the automated body condition scoring technology was strongly correlated with the manual scores, with a correlation of 0.78. The automated BCS camera system accuracy was equivalent to manual scoring, with a mean error of −0.1 BCS and within the acceptable manual error threshold of 0.25 BCS between BCS (3.00 to 3.75) but was less accurate for cows with high (>3.75) or low (<3.00) BCS scores compared to manual scorers. A Bland–Altman plot was constructed which demonstrated a bias in the high and low automated BCS scoring. The initial findings show that the BCS camera system provides accurate BCS between 3.00 to 3.75 but tends to be inaccurate at determining the magnitude of low and high BCS scores. However, the results are promising, as an automated system may encourage more producers to adopt BCS into their practices to detect early signs of BCS change for individual cattle. Future algorithm and software development is likely to increase the accuracy in automated BCS scoring.

show abstract

“…Recently, a variety of vision-based solutions for BSC monitoring have been developed and tested, such as thermal imaging [ 121 ], 2D imaging [ 123 ], and 3D imaging technology [ 124 , 125 ]. Data analysis approaches have been applied to monitor the development of sensors, which increase the developed systems’ capacity, with examples such as Fourier transformation [ 123 ] and machine learning [ 126 ]. However, despite the advances already made, there are still limitations to fully automated solutions.…”

Section: Welfare Of Dairy Cows and Precision Livestock Farmingmentioning

confidence: 99%

Precision Technologies to Address Dairy Cattle Welfare: Focus on Lameness, Mastitis and Body Condition

Silva

Araújo

Guedes

et al. 2021

Animals

View full text Add to dashboard Cite

Specific animal-based indicators that can be used to predict animal welfare have been the core of protocols for assessing the welfare of farm animals, such as those produced by the Welfare Quality project. At the same time, the contribution of technological tools for the accurate and real-time assessment of farm animal welfare is also evident. The solutions based on technological tools fit into the precision livestock farming (PLF) concept, which has improved productivity, economic sustainability, and animal welfare in dairy farms. PLF has been adopted recently; nevertheless, the need for technological support on farms is getting more and more attention and has translated into significant scientific contributions in various fields of the dairy industry, but with an emphasis on the health and welfare of the cows. This review aims to present the recent advances of PLF in dairy cow welfare, particularly in the assessment of lameness, mastitis, and body condition, which are among the most relevant animal-based indications for the welfare of cows. Finally, a discussion is presented on the possibility of integrating the information obtained by PLF into a welfare assessment framework.

show abstract

Building the “Automatic Body Condition Assessment System” (ABiCA), an Automatic Body Condition Scoring System using Active Shape Models and Machine Learning

Cited by 6 publications

References 14 publications

Development of automatic body condition scoring using a low-cost 3-dimensional Kinect camera

Development of automatic body condition scoring using a low-cost 3-dimensional Kinect camera

Validation of a Commercial Automated Body Condition Scoring System on a Commercial Dairy Farm

Precision Technologies to Address Dairy Cattle Welfare: Focus on Lameness, Mastitis and Body Condition

Contact Info

Product

Resources

About