Search

Simple Summary: Technological advancements have revolutionized dairy cattle management through digital and precision approaches. This study conducts a bibliometric analysis of these technologies, identifying emerging patterns, research themes, and author collaborations. It reveals top journals of interest and emerging technologies such as machine learning and computer vision. These tools are crucial for decisions enhancing health and efficiency in milk production, promoting more sustainable practices. It highlights the evolution of precision livestock farming and introduces digital livestock farming, demonstrating how advanced digital tools transform dairy herd management. This shift not only boosts productivity but also redefines cattle management, emphasizing its impact on the sustainability and efficiency of milk production. The advancement of technology has significantly transformed the livestock landscape, particularly in the management of dairy cattle, through the incorporation of digital and precision approaches. This study presents a bibliometric analysis focused on these technologies involving dairy farming to explore and map the extent of research in the scientific literature. Through this review, it was possible to investigate academic production related to digital and precision livestock farming and identify emerging patterns, main research themes, and author collaborations. To carry out this investigation in the literature, the entire timeline was considered, finding works from 2008 to November 2023 in the scientific databases Scopus and Web of Science. Next, the Bibliometrix (version 4.1.3) package in R (version 4.3.1) and its Biblioshiny software extension (version 4.1.3) were used as a graphical interface, in addition to the VOSviewer (version 1.6.19) software, focusing on filtering and creating graphs and thematic maps to analyze the temporal evolution of 198 works identified and classified for this research. The results indicate that the main journals of interest for publications with identified affiliations are "Computers and Electronics in Agriculture" and "Journal of Dairy Science". It has been observed that the authors focus on emerging technologies such as machine learning, deep learning, and computer vision for behavioral monitoring, dairy cattle identification, and management of thermal stress in these animals. These technologies are crucial for making decisions that enhance health and efficiency in milk production, contributing to more sustainable practices. This work highlights the evolution of precision livestock farming and introduces the concept of digital livestock farming, demonstrating how the adoption of advanced digital tools can transform dairy herd management. Digital livestock farming not only boosts productivity but also redefines cattle management through technological innovations, emphasizing the significant impact of these trends on the sustainability and efficiency of dairy production. [ABSTRACT FROM AUTHOR]

Broiler activity and occupation patterns are of special interest to farmers during visual inspection. However, this is time consuming and precision livestock farming (PLF) technologies can enable the monitoring of such key flock behavioural indicators in a continuous and automated way in the house. The aim is to show how the welfare status of the poultry flock can be evaluated by real-time monitoring of activity and occupation patterns. Four top view cameras were installed in a commercial broiler house for 9 complete growing cycles. The cameras recorded images continuously and they were translated into numerical values of activity and occupation indices each minute. Three welfare assessments were performed in weeks 3, 4 and 5 of each growing cycle according to the standardised Welfare Quality® assessment protocol for broiler chickens. A real-time dynamic model was developed to monitor and forecast the time evolution of these indices and the confidence intervals for normal behaviour over each growing cycle. Statistically relevant correlations (p < 0.05) between the time birds spent in an alert situation during the growing cycle and the percentage of birds showing worse welfare scores were found for occupation deviations and foot pad lesions (R 2 = 0.60) and activity deviations and hock burns (R 2 = 0.70). Furthermore, these deviations can be located inside the poultry house through the relation between activity and occupation indices in specific areas associated with particular broiler behaviours, such as feeding, drinking and resting. Evaluating this relation, regular activity and occupation patterns for each behaviour were defined. This work shows that it is possible to link deviations in activity and occupation patterns of broiler flocks in commercial farms with the welfare assessment scores by human experts. This tool allows the farmer to evaluate the risk of welfare issues in the flock and to get early warnings about which bird behaviours are affected and the location in the house where these alerts are being triggered. Highlights • Real-time monitoring of broiler's behaviour. • Deviations in broiler activity patterns are correlated to hock burns. • Deviations in broiler occupation patterns are correlated to foot pad lesions. [ABSTRACT FROM AUTHOR]

The assessment of animal welfare on-farm is important to ensure that current welfare standards are followed. The current manual assessment proposed by Welfare Quality® (WQ), although being an essential tool, is only a point-estimate in time, is very time consuming to perform, only evaluates a subset of the animals, and is performed by the subjective human. Automation of the assessment through information technologies (ITs) could provide a continuous objective assessment in real-time on all animals. The aim of the current systematic review was to identify ITs developed for welfare monitoring within the pig production chain, evaluate the ITs developmental stage and evaluate how these ITs can be related to the WQ assessment protocol. The systematic literature search identified 101 publications investigating the development of ITs for welfare monitoring within the pig production chain. The systematic literature analysis revealed that the research field is still young with 97% being published within the last 20 years, and still growing with 63% being published between 2016 and mid-2020. In addition, most focus is still on the development of ITs (sensors) for the extraction and analysis of variables related to pig welfare; this being the first step in the development of a precision livestock farming system for welfare monitoring. The majority of the studies have used sensor technologies detached from the animals such as cameras and microphones, and most investigated animal biomarkers over environmental biomarkers with a clear focus on behavioural biomarkers over physiological biomarkers. ITs intended for many different welfare issues have been studied, although a high number of publications did not specify a welfare issue and instead studied a general biomarker such as activity, feeding behaviour and drinking behaviour. The 'good feeding' principle of the WQ assessment protocol was the best represented with ITs for real-time on-farm welfare assessment, while for the other principles only few of the included WQ measures are so far covered. No ITs have yet been developed for the 'Comfort around resting' and the 'Good human-animal relationship' criteria. Thus, the potential to develop ITs for welfare assessment within the pig production is high and much work is still needed to end up with a remote solution for welfare assessment on-farm and in real-time. [ABSTRACT FROM AUTHOR]

This systematic review aims to explore how information technologies (ITs) are currently used to monitor the welfare of broiler chickens. The question posed for the review was "which ITs are related to welfare and how do they monitor this for broilers?". The Welfare Quality® (WQ) protocol for broiler assessment was utilized as a framework to analyse suitable articles. A total of 57 studies were reviewed wherein all principles of broiler welfare were addressed. The "good health" principle was the main criteria found to be addressed by ITs and IT-based studies (45.6% and 46.1%, respectively), whereas the least observed principle was "good feeding" (8.8%). This review also classified ITs and IT-based studies by their utilization (location, production system, variable measured, aspect of production, and experimental/practical use). The results show that the current focus of ITs is on problems with conventional production systems and that less attention has been given to free-range systems, slaughterhouses, and supply chain issues. Given the valuable results evidenced by the exploitation of ITs, their use in broiler production should continue to be encouraged with more attention given to farmer adoption strategies. [ABSTRACT FROM AUTHOR]

Body condition scoring (BCS) gives a relative measure of subcutaneous body fat available as energy reserves in the dairy cow. It is an important management tool for maximising milk production and reproduction efficiency while reducing the incidence of metabolic and peripartum diseases. The feasibility of estimating the BCS by computer vision has been demonstrated in recent research. However, the techniques explored to date may be limited in dynamic backgrounds or in applications for an imbalanced dataset of cows' BCS, which is likely to be encountered in dairy farming. In this study, a dynamic background model (Gaussian Mixture Model, GMM) was used to separate the cow from the background. Then, a series of image processing algorithms were proposed for quantifying the indicators used in manual scoring, including global features and local features. Finally, an ensemble learning approach was used to model the imbalanced dataset. The results demonstrate that applying GMM on depth images can eliminate the difficulty of object detection caused by background changes. The image processing algorithms can automatically acquire valid images, locate regions of interest and extract image features without any manual intervention. In 5-fold cross-validation, the ensemble model achieved an average accuracy of 56% within 0.125-point deviation, 76% within 0.25-point deviations and 94% within 0.5-point deviations. Especially, the proposed method has a better predictive performance for cows with extreme body condition than is possible with the current state of the art. • A computer vision method was proposed to evaluate the BCS of cows automatically. • The GMM was used to extract individual cows from the dynamic background. • Global features and local features were extracted to quantify manual scoring criteria. • The ensemble model was used to model on the imbalanced dataset. [ABSTRACT FROM AUTHOR]

Aquaculture production of finfish has seen rapid growth in production volume and economic yield over the last decades, and is today a key provider of seafood. As the scale of production increases, so does the likelihood that the industry will face emerging biological, economic and social challenges that may influence the ability to maintain ethically sound, productive and environmentally friendly production of fish. It is therefore important that the industry aspires to monitor and control the effects of these challenges to avoid also upscaling potential problems when upscaling production. We introduce the Precision Fish Farming (PFF) concept whose aim is to apply control-engineering principles to fish production, thereby improving the farmer's ability to monitor, control and document biological processes in fish farms. By adapting several core principles from Precision Livestock Farming (PLF), and accounting for the boundary conditions and possibilities that are particular to farming operations in the aquatic environment, PFF will contribute to moving commercial aquaculture from the traditional experience-based to a knowledge-based production regime. This can only be achieved through increased use of emerging technologies and automated systems. We have also reviewed existing technological solutions that could represent important components in future PFF applications. To illustrate the potential of such applications, we have defined four case studies aimed at solving specific challenges related to biomass monitoring, control of feed delivery, parasite monitoring and management of crowding operations. Highlights • Precision Fish Farming (PFF) concept developed. • Goal is to stimulate transition from experience-to knowledge-based production. • Review of technology usage in finfish aquaculture industry and research. • Concrete future application possibilities for PFF. • Guidelines suggested for future research in aquaculture technology in PFF framework. [ABSTRACT FROM AUTHOR]

Play behaviour is considered an indicator of animal welfare in young pigs. However, as play behaviour events are short-lasting and occur sporadically, continuous monitoring is necessary. This study presents a first attempt at automatic detection of locomotor play behaviour in young pigs from video by classifying locomotor play from other solitary behaviours including standing, walking, and running. Two methods were developed, compared, and sequentially combined: (1) a less computational heavy method utilising the Gaussian Mixture Model for quantification of movement combined with the calculation of contour features and standard machine learning classifiers (FEATURES); (2) a computational heavy method utilising a deep learning classifier taking both spatial and temporal features into account (DEEP). The DEEP classifier outperformed the FEATURES classifier and obtained values of internal validation recall, precision, and specificity of 94%, 88% and 96%, respectively. When combining the two classification methods, almost similar performance was retained, whilst 44% of the other behaviours were correctly classified without the need for deep learning methods. The combination thereby decreased the computational power needed to run the algorithm. Thus, locomotor play can be automatically detected in young pigs and the combination of a less computational heavy method with a deep learning method can reduce the computational requirements for the classification and detection of complex behaviours. Future work should focus on the segmentation of single pigs during high-speed activity in order to enable the play detection algorithm to work in real-life settings. • Locomotor play in young pig can be classified from other solitary behaviour. • Both spatial and temporal features needed to detect the complex behaviour. • Recall, precision, and specificity of 94%, 88% and 96%, respectively. • Combining methods have potential to decrease computational footprint. • Remote tracking may be needed to segment playing pigs. [ABSTRACT FROM AUTHOR]

As a typical harmful social behaviour, tail biting is considered to be a welfare-reducing problem with economic consequences for pig production. Taking a computer-vision based approach, in this study, we have developed a novel method to automatically identify and locate tail-biting interactions in group-housed pigs. The method employs a tracking-by-detection algorithm to simplify the group-level behaviour to pairwise interactions. Then, a convolution neural network (CNN) and a recurrent neural network (RNN) are combined to extract the spatial-temporal features and classify behaviour categories. The performance of the proposed method was evaluated by quantifying the localisation accuracy and behaviour classification accuracy. The results demonstrate that the tracking-by-detection approach is capable of obtaining the trajectories of biters and victims with a localisation accuracy of 92.71%. The spatial-temporal features trained by CNN and RNN are robust and effective with a category accuracy of 96.25%. In total, our proposed method is capable to identify and locate 89.23% of tail-biting behaviour in group-housed pigs. • A novel method was proposed to recognise and locate pig tail-biting behaviour. • A tracking algorithm was proposed to extract pairwise interactions from the group. • The CNN + LSTM model was used to recognise interactive actions. • The method can locate and identify 89.23% of tail-biting interactions in the group. [ABSTRACT FROM AUTHOR]

Measuring particulate matter concentration in poultry houses remains as a difficult task, primarily because aerosol analysers are expensive, require specialist knowledge to operate and are labour intensive to maintain. However, it is well known that high concentrations of particulate matter causes health and welfare problems with livestock, farm workers and people living in the vicinity of the farm premises. In this work, a data-based mechanistic model is developed to relate broiler activity and ventilation rate with indoor particulate matter concentration. For six complete growing cycles, in a U.K. commercial poultry farm, broiler activity was monitored using a camera-based flock monitoring system (eYeNamic®) and ventilation rate was measured. Indoor particulate matter concentration was continuously monitored by measuring size-segregated mass fraction concentrations with the aerosol analyser DustTrak™. A discrete-time multi-input single-output time-invariant parameters Transfer Function model was developed to determine the particulate dynamics within each day of the growing cycle in the poultry house using broiler activity and ventilation rate as inputs. This model monitored indoor particulate matter concentration with an average accuracy of R T 2 = (51 ± 26) %. A dynamic linear regression modelling with time-variant parameters improved average accuracy with R T 2 = (97.7 ± 1.3) %. It forecasted one sample-ahead the indoor particulate matter concentration level, using a time window of 14 samples, with a mean relative prediction error, M R P E = (4.6 ± 3.2) %. Thus, dynamic modelling with time-variant parameters has the potential to be part of a control system to manage in real-time indoor particulate matter concentration in broiler houses. • Broiler activity & ventilation rate predict indoor particulate matter concentration. • Dynamic linear regression model shows a mean relative prediction error of 4.6%. • Real-time monitoring of indoor PM concentration in a commercial broiler house. [ABSTRACT FROM AUTHOR]

• Monitor bioacoustics to detect respiratory problems. • Algorithm to detect sneezing in broiler chickens. • Classification of unbalanced dataset. • The algorithm obtained a sensitivity of 66.7% and a precision of 88.4%. Respiratory diseases are a major health challenge in meat chicken production. As sneezing is a clinical sign of many respiratory diseases, sound has a great potential in monitoring these diseases. This study focussed on the development of an algorithm to monitor chicken sneezing sounds in a situation where multiple birds are active and multiple noise sources are present. An experiment was designed where the sneezing from within a group of 51 chickens was recorded. 763 sneezes were annotated out of 480 min of sound recordings. First, the number of labelled sneezes of adequate quality were investigated. Then raw sound signal was filtered using spectral subtraction and split into short intervals with elevated energy that could be sneezes. This led to a highly unbalanced dataset containing only 0.24% sneezes, from which features characterising the sneezing sounds were calculated. These were then grouped into 8 different features on which the algorithm classified the sound as sneeze or no-sneeze with a sensitivity of 66.7% and a precision of 88.4%. The algorithm enabled the monitoring of the number of sneezes in the experimental group. This work represents the first step towards the development of an automated sound-based monitoring system for poultry health. [ABSTRACT FROM AUTHOR]

• Rotated bounding box detector significantly outperforms horizontal detector in densely-housed pigs. • Encoding the angle parameter with direction vector enables the learning of pigs' orientation for subsequent computer vision tasks. • A sequential non-maximum suppression to improve the performance of video object detection. • A super lightweight model achieved satisfying performance that can be deployed in edge device. Pig detection in real production environments is a challenging task due to the variations of housing system and dynamic background. Though considerable progress has been made, for practical settings, there still existing challenges for densely housed pigs as they are often arbitrarily arranged at varying orientations in presence of lens distortion, overlap, occlusion, and motion blur. In this paper, we propose a rotated and oriented bounding box detector for fast and accurate predict the location and orientation of each animal. The key point is to parameterize pigs' geometric parameters (body centre, body length, body width, orientation) with an orientated bounding box (box centre, long edge, short edge and direction vector). To further improve the performance on video object detection, a fast sequential non-Maximum Suppression (FastSeq-NMS) method is proposed by making used of the orientation and temporal information. To quantitative evaluate the proposed method, 3123 images from 27 different pens were selected as training and validation sets, video clips from three new environments were selected as test set. Our lightweight model (1.7 M) achieves 99.21 Average Precision (AP@0.5) on validation set, and 96.54 AP@0.5 on test set, further improved to 97.41 AP@0.5 with the proposed NMS method. The experiments show the effectiveness of the proposed method. More information available online: https://gitlab.kuleuven.be/m3-biores/public/m3pig. [ABSTRACT FROM AUTHOR]

In calf rearing, bovine respiratory disease (BRD) is a major animal health challenge. Farmers incur severe economic losses due to BRD. Additional to economic costs, outbreaks of BRD impair the welfare of the animal and extra expertise and labour are needed to treat and care for the infected animals. Coughing is recognised as a clinical manifestation of BRD. Therefore, the monitoring of coughing in a calf house has the potential to detect cases of respiratory infection before they become too severe, and thus to limit the impact of BRD on both the farmer and the animal. The objective of this study was to develop an algorithm for detection of coughing sounds in a calf house. Sounds were recorded in four adjacent compartments of one calf house over two time periods (82 and 96 days). There were approximately 21 and 14 calves in each compartment over the two time-periods, respectively. The algorithm was developed using 445 min of sound data. These data contained 664 different cough references, which were labelled by a human expert. It was found that, during the first time period in all 3 of the compartments and during the second period in 2 out of 4 compartments, the algorithm worked very well (precision higher than 80%), while in the 2 other cases the algorithm worked well but the precision was less (66.6% and 53.8%). A relation between the number of calves diagnosed with BRD and the detected coughs is shown. Highlights • Algorithm for detection of calf coughs in a real-life situation. • Quality rating of reference sounds to mitigate the impact of unclear sounds. • A sensitivity of 41.4% and a precision of 94.2% was obtained. • Detected coughs correspond with the number of animals diagnosed with BRD. [ABSTRACT FROM AUTHOR]

Automatic animal monitoring through Precision Livestock Farming (PLF) tools is a method to support farmers in achieving farm sustainability. The development of PLF systems requires close interdisciplinary collaboration between sector experts, farmers, animal scientists and bio-engineers. Labelling is a key activity in the development of reliable algorithm to be included in PLF tools. It is a set of procedures that animal experts must embark to precisely define and interpret detailed variations in measured field signals. This application note will describe the fundamental aspects of sound and image labelling and how this has enabled the engineering of useful automated PLF systems. [ABSTRACT FROM AUTHOR]

• The first study to use action density in automated analysis of animal behaviours. • Precise action density estimation and suckling event counting. • High-efficient spatiotemporal feature extraction by using different temporal resolution input. Analysis of piglet suckling behaviour is important for the evaluation of piglet nutrient ingestion, health, welfare, and affinity with the sow. In this study, an action density estimation network (ADEN) was proposed for counting the events of piglet suckling followed by automated analysis of suckling behaviour. ADEN is a two-stream network primarily composed of 1) a network stream that processes video images with a higher frame rate (faster stream) and 2) a network stream that processes video images with a lower frame rate (slower stream). Each stream consists of a ResNet-50 with five convolutional stages. A multi-stage attention connection (MSAC), composed of four Spatial-Temporal-Channel (STC) multi-attention structures, is proposed to bridge Faster Stream and Slower Stream and capture discriminative features. The output attention features from each faster stream stage are laterally fused into the corresponding slower stream stage in a concatenating manner. Following this, the features from the last convolutional stages in the Slow stream and Fast stream are fused using concatenation and are then decoded by using three convolutional layers. The last convolutional layer outputs a heatmap on the action density of piglet suckling behaviour. Finally, the number of suckling events is predicted by integrating all the pixel values in the heatmap. Experimental and comparative tests were conducted to validate the effectiveness of the proposed ADEN with a training dataset and a test dataset from 14 pig pens. The 507 video clips (126,750 images for 7 h) from the 1-9th pens were selected as training datasets. The 143 video clips (35,750 images for 2 h) from the 10-13th pens were selected as short-term test datasets. One untrimmed video (162,000 images for 9 h) from the 14th pen was used to ultimately evaluate the action density estimation performance of the ADEN. ADEN was compared with seven approaches and its superiority was demonstrated with an r = 0.938, an RMSE = 1.080, and a MAE = 0.967 in short video clips and r = 0.982, MAE = 0.161, and RMSE = 0.563 in the untrimmed long video. The ADEN proved it feasible to predict the number of suckling events by using action density estimation. [ABSTRACT FROM AUTHOR]

• An ingenious approach was proposed to weigh hens and roosters in commercial farms. • A new system was proposed by synchronizing electronic weigher and vision system. • Precise body weight was obtained by using automatic electronic platform weigher. • A novel image processing method was proposed to obtain the gender. The body weight of breeding broiler chickens (broiler breeders) is an important control variable used to optimize the amount, quality and fertility of the eggs being laid. In modern breeding barns, the population of animals generally supports a female:male ratio of 10:1, wherein males and females each receive their own food supply. To control this supply the broiler breeders are weighed using automatic electronic platform weighers and the weights are then classified into cockerel and hen categories using theoretical growth curves. However, due to the non-uniform growth of the animals and replacement (called spiking) of cockerals this classification is not always correct, causing a risk of under/over feeding of the population. To overcome this challenge, in this study we have developed a system that integrates the electronic platform weigher with the low-cost 3D Kinect camera was employed to separate weigh male and female broiler breeders under commercial conditions. A novel image processing algorithm is proposed. The algorithm first constructed the Height Accumulating Image (HAI) using depth image to locate the region of interest (ROI) where a broiler breeder jumps onto the weigher, then the comb size was calculated on RGB image as the gender classifying feature, and finally, an adaptive classification threshold was determined by the kernel density estimation using the recent days comb size measurements. The results showed that enough measurements can be obtained for estimating overall weight expectation with the average acceptance rate of 77.32%. Based on these accepted measurements, the accuracy, sensitivity, precision, and specificity were 99.7%, 98.82%, 100% and 100% respectively. [ABSTRACT FROM AUTHOR]