An automated positioning system for monitoring chickens’ location: Effects of wearing a backpack on behaviour, leg health and production

Effect of Lighting Methods on the Production, Behavior and Meat Quality Parameters of Broiler Chickens

Many farms have been replacing traditional lighting sources with light-emitting diode (LED) bulbs because of technological modernization. We aimed to investigate the effects of incandescent lighting (IL) and LED lighting on Cobb 500 broiler chickens for six weeks. Production parameters (body weight, feed consumption, feed conversion ratio), calculated slaughter values (yield%, relative breast%, thigh%) and breast meat quality parameters (pH at 45 min and 24 h postmortem, color, drip loss, kitchen equipment losses, shear force, meat composition) were recorded. Non-stop recordings were used to analyze the behavior of the birds during several periods of rearing. The LED group was significantly better in the body weight parameter between week 1 and 5 and the feed conversion ratio between week 2 and 3. The most significant difference in behavior was observed in the middle of the rearing period. The chickens in the LED group spent more time eating, drinking and interacting, and rested less. There was no difference in the meat quality parameters; only shear force was significantly lower in the LED group (1781.9 g/s vs. 2098.8 g/s). According to our results, LED lighting can bring about positive changes in animal production efficiency, behavior and other important characteristics for meat consumers.

MCP: Multi-Chicken Pose Estimation Based on Transfer Learning

Poultry managers can better understand the state of poultry through poultry behavior analysis. As one of the key steps in behavior analysis, the accurate estimation of poultry posture is the focus of this research. This study mainly analyzes a top-down pose estimation method of multiple chickens. Therefore, we propose the "multi-chicken pose" (MCP), a pose estimation system for multiple chickens through deep learning. Firstly, we find the position of each chicken from the image via the chicken detector; then, an estimate of the pose of each chicken is made using a pose estimation network, which is based on transfer learning. On this basis, the pixel error (PE), root mean square error (RMSE), and image quantity distribution of key points are analyzed according to the improved chicken keypoint similarity (CKS). The experimental results show that the algorithm scores in different evaluation metrics are a mean average precision (mAP) of 0.652, a mean average recall (mAR) of 0.742, a percentage of correct keypoints (PCKs) of 0.789, and an RMSE of 17.30 pixels. To the best of our knowledge, this is the first time that transfer learning has been used for the pose estimation of multiple chickens as objects. The method can provide a new path for future poultry behavior analysis.

Pose Estimation and Behavior Classification of Jinling White Duck Based on Improved HRNet

In breeding ducks, obtaining the pose information is vital for perceiving their physiological health, ensuring welfare in breeding, and monitoring environmental comfort. This paper proposes a pose estimation method by combining HRNet and CBAM to achieve automatic and accurate detection of duck's multi-poses. Through comparison, HRNet-32 is identified as the optimal option for duck pose estimation. Based on this, multiple CBAM modules are densely embedded into the HRNet-32 network to obtain the pose estimation model based on HRNet-32-CBAM, realizing accurate detection and correlation of eight keypoints across six different behaviors. Furthermore, the model's generalization ability is tested under different illumination conditions, and the model's comprehensive detection abilities are evaluated on Cherry Valley ducklings of 12 and 24 days of age. Moreover, this model is compared with mainstream pose estimation methods to reveal its advantages and disadvantages, and its real-time performance is tested using images of 256 × 256, 512 × 512, and 728 × 728 pixel sizes. The experimental results indicate that for the duck pose estimation dataset, the proposed method achieves an average precision (AP) of 0.943, which has a strong generalization ability and can achieve real-time estimation of the duck's multi-poses under different ages, breeds, and farming modes. This study can provide a technical reference and a basis for the intelligent farming of poultry animals.

Farmers' Perspectives of the Benefits and Risks in Precision Livestock Farming in the EU Pig and Poultry Sectors

More efficient livestock production systems are necessary, considering that only 41% of global meat demand will be met by 2050. Moreover, the COVID-19 pandemic crisis has clearly illustrated the necessity of building sustainable and stable agri-food systems. Precision Livestock Farming (PLF) offers the continuous capacity of agriculture to contribute to overall human and animal welfare by providing sufficient goods and services through the application of technical innovations like digitalization. However, adopting new technologies is a challenging issue for farmers, extension services, agri-business and policymakers. We present a review of operational concepts and technological solutions in the pig and poultry sectors, as reflected in 41 and 16 European projects from the last decade, respectively. The European trend of increasing broiler-meat production, which is soon to outpace pork, stresses the need for more outstanding research efforts in the poultry industry. We further present a review of farmers' attitudes and obstacles to the acceptance of technological solutions in the pig and poultry sectors using examples and lessons learned from recent European projects. Despite the low resonance at the research level, the investigation of farmers' attitudes and concerns regarding the acceptance of technological solutions in the livestock sector should be incorporated into any technological development.

Setting the stage to tag "n" track: a guideline for implementing, validating and reporting a radio frequency identification system for monitoring resource visit behavior in poultry

Passive radio frequency identification (RFID) can advance poultry behavior research by enabling automated, individualized, longitudinal, in situ, and noninvasive monitoring; these features can usefully extend traditional approaches to animal behavior monitoring. Furthermore, since the technology can provide insight into the visiting patterns of tagged animals at functional resources (e.g., feeders), it can be used to investigate individuals' welfare, social position, and decision-making. However, the lack of guidelines that would facilitate implementing an RFID system for such investigations, describing it, and establishing its validity undermines this technology's potential for advancing poultry science. This paper aims to fill this gap by 1) providing a nontechnical overview of how RFID functions; 2) providing an overview of the practical applications of RFID technology in poultry sciences; 3) suggesting a roadmap for implementing an RFID system in poultry behavior research; 4) reviewing how validation studies of RFID systems have been done in farm animal behavior research, with a focus on terminologies and procedures for quantifying reliability and validity; and 5) suggesting a way to report on an RFID system deployed for animal behavior monitoring. This guideline is aimed mainly at animal scientists, RFID component manufacturers, and system integrators who wish to deploy RFID system as an automated tool for monitoring poultry behavior for research purposes. For such a particular application, it can complement indications in classic general standards (e.g., ISO/IEC 18000-63) and provide ideas for setting up, testing, and validating an RFID system and a standard for reporting on its adequacy and technical aspects.

Individual Monitoring of Activity and Lameness in Conventional and Slower-Growing Breeds of Broiler Chickens Using Accelerometers

Accelerometers are increasingly being investigated to detect animal behavior as a method for monitoring individual welfare that overcomes manual challenges associated with time, resource, and discrete sampling. We investigated the effects of broiler chicken hybrid (hereafter breed) and weight on accelerometer activity (activityA; calculated as percentage of time spent active (%)) and its association with lameness as a major broiler welfare concern. Accelerometers were attached to birds of different breeds on between 2 and 4 occasions from 26 to 30 days old (conventional breed CNV) and 26 to 49 days old (two slower-growing breeds SGH; SGN). At 2.2 kg, lameness was scored using a 6-point gait scoring system (0: unaffected to 5: severely lame). Linear mixed effects models and breed-stratified generalized linear models together with a random-effect meta-analysis were used for data analyses. ActivityA was lower in faster-growing, heavier birds compared to slower-growing, lighter birds, showing overall consistency with previous behavioral research, but did not vary linearly with gait score. Accelerometers offer the potential for simple broad-scale continuous monitoring of broiler chicken activity behavior that requires limited data processing. Exploration of the ability of accelerometers to capture more subtle and specific changes in behavioral patterning, such as non-linear acceleration with gait score that could indicate early development of lameness, warrants further investigation.

Impact of Body-worn Sensors on Broiler Chicken Behavior and Agonistic Interactions

Technology, like body-worn sensors, enables data collection from similar-looking individuals in large groups but may alter behavior. We aimed to evaluate the impact of body-worn sensors on broiler behavior. Broilers were housed in 8 pens (10 birds/m2). At 21 days-old, 10 birds/pen were fitted with a harness contained a sensor (HAR), while the remaining 10-birds were unharnessed (NON). Behaviors were recorded on days 22-26 using scan sampling (126 scans/day for 5 days). Percent of birds performing behaviors were calculated daily for each group (HAR-or-NON), and agonistic interactions were identified based on birds involved (two NON-birds (N-N), NON-aggressor to HAR-recipient (N-H), HAR-aggressor to NON-recipient (H-N), or two HAR-birds (H-H)). HAR-birds performed locomotory behavior and explored less often than NON-birds (p<0.05). Consummatory behavior was unaffected by treatment on any day (p>0.05). Agonistic interactions occurred more often between NON-aggressor and HAR-recipient birds than other categories on days 22 and 23 (p<0.05). HAR-broilers showed no behavioral differences when compared to NON-broilers after 2 days; thus, a similar acclimation period is required before using body-worn sensors to evaluate broiler welfare without altering behavior.

A Deep Learning Model for Detecting Cage-Free Hens on the Litter Floor

Real-time and automatic detection of chickens (e.g., laying hens and broilers) is the cornerstone of precision poultry farming based on image recognition. However, such identification becomes more challenging under cage-free conditions comparing to caged hens. In this study, we developed a deep learning model (YOLOv5x-hens) based on YOLOv5, an advanced convolutional neural network (CNN), to monitor hens’ behaviors in cage-free facilities. More than 1000 images were used to train the model and an additional 200 images were adopted to test it. One-way ANOVA and Tukey HSD analyses were conducted using JMP software (JMP Pro 16 for Mac, SAS Institute, Cary, North Caronia) to determine whether there are significant differences between the predicted number of hens and the actual number of hens under various situations (i.e., age, light intensity, and observational angles). The difference was considered significant at p < 0.05. Our results show that the evaluation metrics (Precision, Recall, F1 and mAP@0.5) of the YOLOv5x-hens model were 0.96, 0.96, 0.96 and 0.95, respectively, in detecting hens on the litter floor. The newly developed YOLOv5x-hens was tested with stable performances in detecting birds under different lighting intensities, angles, and ages over 8 weeks (i.e., birds were 8−16 weeks old). For instance, the model was tested with 95% accuracy after the birds were 8 weeks old. However, younger chicks such as one-week old birds were harder to be tracked (e.g., only 25% accuracy) due to interferences of equipment such as feeders, drink lines, and perches. According to further data analysis, the model performed efficiently in real-time detection with an overall accuracy more than 95%, which is the key step for the tracking of individual birds for evaluation of production and welfare. However, there are some limitations of the current version of the model. Error detections came from highly overlapped stock, uneven light intensity, and images occluded by equipment (i.e., drinking line and feeder). Future research is needed to address those issues for a higher detection. The current study established a novel CNN deep learning model in research cage-free facilities for the detection of hens, which provides a technical basis for developing a machine vision system for tracking individual birds for evaluation of the animals’ behaviors and welfare status in commercial cage-free houses.

Keypoint Detection for Injury Identification during Turkey Husbandry Using Neural Networks

Injurious pecking against conspecifics is a serious problem in turkey husbandry. Bloody injuries act as a trigger mechanism to induce further pecking, and timely detection and intervention can prevent massive animal welfare impairments and costly losses. Thus, the overarching aim is to develop a camera-based system to monitor the flock and detect injuries using neural networks. In a preliminary study, images of turkeys were annotated by labelling potential injuries. These were used to train a network for injury detection. Here, we applied a keypoint detection model to provide more information on animal position and indicate injury location. Therefore, seven turkey keypoints were defined, and 244 images (showing 7660 birds) were manually annotated. Two state-of-the-art approaches for pose estimation were adjusted, and their results were compared. Subsequently, a better keypoint detection model (HRNet-W48) was combined with the segmentation model for injury detection. For example, individual injuries were classified using “near tail” or “near head” labels. Summarizing, the keypoint detection showed good results and could clearly differentiate between individual animals even in crowded situations.

Twelve Threats of Precision Livestock Farming (PLF) for Animal Welfare

Research and development of Precision Livestock Farming (PLF) is booming, partly due to hopes and claims regarding the benefits of PLF for animal welfare. These claims remain largely unproven, however, as only few PLF technologies focusing on animal welfare have been commercialized and adopted in practice. The prevailing enthusiasm and optimism about PLF innovations may be clouding the perception of possible threats that PLF may pose to farm animal welfare. Without claiming to be exhaustive, this paper lists 12 potential threats grouped into four categories: direct harm, indirect harm via the end-user, via changes to housing and management, and via ethical stagnation or degradation. PLF can directly harm the animals because of (1) technical failures, (2) harmful effects of exposure, adaptation or wearing of hardware components, (3) inaccurate predictions and decisions due to poor external validation, and (4) lack of uptake of the most meaningful indicators for animal welfare. PLF may create indirect effects on animal welfare if the farmer or stockperson (5) becomes under- or over-reliant on PLF technology, (6) spends less (quality) time with the animals, and (7) loses animal-oriented husbandry skills. PLF may also compromise the interests of the animals by creating transformations in animal farming so that the housing and management are (8) adapted to optimize PLF performance or (9) become more industrialized. Finally, PLF may affect the moral status of farm animals in society by leading to (10) increased speciesism, (11) further animal instrumentalization, and (12) increased animal consumption and harm. For the direct threats, possibilities for prevention and remedies are suggested. As the direction and magnitude of the more indirect threats are harder to predict or prevent, they are more difficult to address. In order to maximize the potential of PLF for improving animal welfare, the potential threats as well as the opportunities should be acknowledged, monitored and addressed.

The Relationships between Damaging Behaviours and Health in Laying Hens

Simple Summary

The design of housing systems and genetic selection of laying hens have in the past focused mainly on productivity, excluding issues around the animals’ behavioural needs and welfare. Because of inadequate housing conditions and especially a barren environment, behavioural disorders such as feather and body pecking, as well as cannibalism, occur in the modern layer industry. Since conventional cages for egg production were banned in the European Union in January 2012, alternative systems such as floor, aviary, free-range, and organic systems have become increasingly common and now concern over 50% of hens housed in Europe. Despite the many advantages that come with non-cage systems, the shift to a housing system where laying hens are kept in larger groups and more complex environments has given rise to new challenges related to management, health, and welfare. We have carried out a review showing the close relationships between damaging behaviours and health in modern husbandry systems for laying hens.

Abstract

Since the ban in January 2012 of conventional cages for egg production in the European Union (Council Directive 1999/74/EC), alternative systems such as floor, aviary, free-range, and organic systems have become increasingly common, reaching 50% of housing for hens in 2019. Despite the many advantages associated with non-cage systems, the shift to a housing system where laying hens are kept in larger groups and more complex environments has given rise to new challenges related to management, health, and welfare. This review examines the close relationships between damaging behaviours and health in modern husbandry systems for laying hens. These new housing conditions increase social interactions between animals. In cases of suboptimal rearing and/or housing and management conditions, damaging behaviour or infectious diseases are likely to spread to the whole flock. Additionally, health issues, and therefore stimulation of the immune system, may lead to the development of damaging behaviours, which in turn may result in impaired body conditions, leading to health and welfare issues. This raises the need to monitor both behaviour and health of laying hens in order to intervene as quickly as possible to preserve both the welfare and health of the animals.

Implementation of Inertia Sensor and Machine Learning Technologies for Analyzing the Behavior of Individual Laying Hens

Simple Summary

Poultry-welfare regulations have caused a shift from cage housing towards more welfare-friendly systems with more possibilities for the birds to meet their natural behavioural needs. The welfare-friendly systems with litter allow and encourage the hens to perform natural behavior including activities that lead to increases in the amount of airborne dust particles emission from such poultry houses. For successful management of these systems, the behavior of the hens needs to be considered, which is more challenging and time-consuming for the farmer. The main objective of this study was to show a proof of principle to identify, classify and analyze the behaviors of laying hens in three levels of activity by using an inertia sensor and machine learning techniques. The model was able to predict the laying hen behaviors with an accuracy of 90%. The results of such monitoring could be used by farmers in the management of poultry houses.

Abstract

Welfare-oriented regulations cause farmers worldwide to shift towards more welfare-friendly, e.g., loose housing systems such as aviaries with litter. In contrast to the traditional cage housing systems, good technical results can only be obtained if the behavior of hens is considered. With increasing flock sizes, the automation of behavioural assessment can be beneficial. This research aims to show a proof of principle of tools for analyzing laying-hen behaviors by using wearable inertia sensor technology and a machine learning model (ML). For this aim, the behaviors of hens were classified into three classes: static, semi-dynamic, and highly dynamic behavior. The activities of hens were continuously recorded on video and synchronized with the sensor signals. Two hens were equipped with sensors, one marked green and one blue, for five days to collect the data. The training data set indicated that the ML model can accurately classify the highly dynamic behaviors with a one-second time window; a four-second time window is accurate for static and semi-dynamic behaviors. The Bagged Trees model, with an overall accuracy of 89% was the best ML model with the F1-scores of 89%, 91%, and 87% for static, semi-dynamic, and highly dynamic behaviors. The Bagged Trees model also performed well in classifying the behaviors of the hen in the validation data set with an overall F1-score of 0.92 (uniform either % or decimals). This research illustrates that the combination of wearable inertia sensors and machine learning is a viable technique for analyzing the laying-hen behaviors and supporting farmers in the management of hens in loose housing systems.

Classification of broiler behaviours using triaxial accelerometer and machine learning

Understanding broiler behaviours provides important implications for animal well-being and farm management. The objectives of this study were to classify specific broiler behaviours by analysing data from wearable accelerometers using two machine learning models, K-Nearest Neighbour (KNN) and Support Vector Machine (SVM). Lightweight triaxial accelerometers were used to record accelerations of nine 7-week-old broilers at a sampling frequency of 40 Hz. A total of 261.6-min data were labelled for four behaviours - walking, resting, feeding and drinking. Instantaneous motion features including magnitude area, vector magnitude, movement variation, energy, and entropy were extracted and stored in a dataset which was then segmented by one of the six window lengths (1, 3, 5, 7, 10 and 20 s) with 50% overlap between consecutive windows. The mean, variation, SD, minimum and maximum of each instantaneous motion feature and two-way correlations of acceleration data were calculated within each window, yielding a total of 43 statistic features for training and testing of machine learning models. Performance of the models was evaluated using pure behaviour datasets (single behaviour type per dataset) and continuous behaviour datasets (continuous recording that involved multiple behaviour types per dataset). For pure behaviour datasets, both KNN and SVM models showed high sensitivities in classifying broiler resting (87% and 85%, respectively) and walking (99% and 99%, respectively). The accuracies of SVM were higher than KNN in differentiating feeding (88% and 75%, respectively) and drinking (83% and 62%, respectively) behaviours. Sliding window with 1-s length yielded the best performance for classifying continuous behaviour datasets. The performance of classification model generally improved as more birds were included for training. In conclusion, classification of specific broiler behaviours can be achieved by recording bird triaxial accelerations and analysing acceleration data through machine learning. Performances of different machine learning models differ in classifying specific broiler behaviours.

How Are Information Technologies Addressing Broiler Welfare? A Systematic Review Based on the Welfare Quality® Assessment

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.

Validation of an Ultra-Wideband Tracking System for Recording Individual Levels of Activity in Broilers

Individual data on activity of broilers is valuable, as activity may serve as a proxy for multiple health, welfare and performance indicators. However, broilers are often kept in large groups, which makes it difficult to identify and monitor them individually. Sensor technologies might offer solutions. Here, an ultra-wideband (UWB) tracking system was implemented with the goal of validating this system for individual tracking of activity of group-housed broilers. The implemented approaches were (1) a comparison of distances moved as recorded by the UWB system and on video and (2) a study recording individual levels of activity of broilers and assessing group-level trends in activity over time; that could be compared to activity trends from literature. There was a moderately strong positive correlation between the UWB system and video tracking. Using the UWB system, we detected reductions in activity over time and we found that lightweight birds were on average more active than heavier birds. Both findings match with reports in literature. Overall, the UWB system appears well-suited for activity monitoring in broilers, when the settings are kept the same for all individuals. The longitudinal information on differences in activity can potentially be used as proxy for health, welfare and performance; but further research into individual patterns in activity is required.

Validity of Micro-Data Loggers to Determine Walking Activity of Turkeys and Effects on Turkey Gait

Accelerometers have the potential to provide objective, non-invasive methods for detecting changes in animal behavior and health. Our objectives were to: (1) determine the effects of micro-acceleration data loggers (accelerometers) and habituation to accelerometers on turkey gait and health status, (2) determine age-related changes in gait and health status, and (3) assess the validity and reliability of the accelerometers. Thirty-six male commercial turkeys were randomly assigned to one of five groups: accelerometer and habituation period (AH), accelerometer and no habituation period (AN), VetRap bandage (no accelerometer) and habituation period (VH), bandage (no accelerometer) and no habituation period (VN), and nothing on either leg (C). Health status and body condition were assessed prior to video-recording birds as they walked across a Tekscan® pressure pad at 8, 12, and 16 weeks to determine effects of treatment on number of steps, cadence, gait time, gait distance, gait velocity, impulse, gait cycle time, maximum force, peak vertical pressure, single support time, contact time, step length, step time, step velocity, stride length, total double support time, and duty factor. Accelerometer validity and reliability were determined by comparing the number of steps detected by the accelerometer to the number of steps determined from video recordings. Several age-related changes in turkey gait were found regardless of habituation including a slower cadence at 16 weeks, shorter gait distance at 8 weeks, and slower gait velocity at 16 weeks. When comparing bandaged vs. unbandaged limbs, both treatment and age-treatment interactions were found depending on the gait parameter. Accelerometer validity and reliability were affected by both age and treatment. False discovery rate increased, while accuracy and specificity decreased with age. Validity and reliability were lowest for non-habituated birds (AN and VN). Results demonstrated that micro-data loggers do not adversely affect turkey health status, but habituation to wearing accelerometers greatly affects accelerometer reliability and validity. Accelerometer validity and turkey gait are also greatly affected by the age of the turkeys.