Search Results (28)

Foraging behavior in hens is an important indicator of animal welfare. It involves both the search for food and exploration of the environment, which provides necessary enrichment. In addition, it has been inversely linked to damaging behaviors such as severe feather pecking. Conventional studies rely on manual observation to investigate foraging location, duration, timing, and frequency. However, this approach is labor-intensive, time-consuming, and subject to human bias. Our study developed computer vision-based methods to automatically detect foraging hens in a cage-free research environment and compared their performance. A cage-free room was divided into four pens, two larger pens measuring 2.9 m × 2.3 m with 30 hens each and two smaller pens measuring 2.3 m × 1.8 m with 18 hens each. Cameras were positioned vertically, 2.75 m above the floor, recording the videos at 15 frames per second. Out of 4886 images, 70% were used for model training, 20% for validation, and 10% for testing. We trained multiple You Only Look Once (YOLO) object detection models from YOLOv9, YOLOv10, and YOLO11 series for 100 epochs each. All the models achieved precision, recall, and mean average precision at 0.5 intersection over union (mAP@0.5) above 75%. YOLOv9c achieved the highest precision (83.9%), YOLO11x achieved the highest recall (86.7%), and YOLO11m achieved the highest mAP@0.5 (89.5%). These results demonstrate the use of computer vision to automatically detect complex poultry behavior, such as foraging, making it more efficient. Full article

Rooster behavior and activity are critical for egg fertility and hatchability in broiler and layer breeder houses. Desirable roosters are expected to have good leg health, reach sexual maturity, be productive, and show less aggression toward females during mating. However, not all roosters are desirable, and low-productive roosters should be removed and replaced. The objectives of this study were to apply an object detection model based on deep learning to identify hens and roosters based on phenotypic characteristics, such as comb size and body size, in a cage-free (CF) environment, and to compare the performance metrics among the applied models. Six roosters were mixed with 200 Lohmann LSL Lite hens during the pre-peak phase in a CF research facility and were marked with different identifications. Deep learning methods, such as You Only Look Once (YOLO) models, were innovated and trained (based on a comb size of up to 2500 images) for the identification of male and female chickens based on comb size and body features. The performance matrices of the YOLOv5u and YOLOv11 models, including precision, recall, mean average precision (mAP), and F1 score, were statistically compared for hen and rooster detection using a one-way ANOVA test at a significance level of p < 0.05. For rooster detection based on comb size, YOLOv5lu, and YOLOv11x variants performed the best among the five variants of each model, with YOLOv5lu achieving a precision of 87.7%, recall of 56.3%, and mAP@0.50 of 60.1%, while YOLOv11x achieved a precision of 86.7%, recall of 65.3%, and mAP@0.50 of 61%. For rooster detection based on body size, YOLOv5xu, and YOLOv11m outperformed other variants, with YOLOv5xu achieving a precision of 88.9%, recall of 77.7%, and mAP@0.50 of 82.3%, while YOLOv11m achieved a precision of 89.0%, recall of 78.8%, and mAP@0.50 of 82.6%. This study provides a reference for automatic rooster monitoring based on comb and body size and offers further opportunities for tracking the activities of roosters in a poultry breeder farm for performance evaluation and genetic selection in the future. Full article

In recent years, artificial intelligence (AI) has significantly impacted agricultural operations, particularly with the development of deep learning models for animal monitoring and farming automation. This study focuses on evaluating the Depth Anything Model (DAM), a cutting-edge monocular depth estimation model, for its potential in poultry farming. DAM leverages a vast dataset of over 62 million images to predict depth using only RGB images, eliminating the need for costly depth sensors. In this study, we assess DAM’s ability to monitor poultry behavior, specifically detecting drinking patterns. We also evaluate its effectiveness in managing operations, such as tracking floor eggs. Additionally, we evaluate DAM’s accuracy in detecting disparity within cage-free facilities. The accuracy of the model in estimating physical depth was assessed using root mean square error (RMSE) between predicted and actual perch frame depths, yielding an RMSE of 0.11 m, demonstrating high precision. DAM demonstrated 92.3% accuracy in detecting drinking behavior and achieved an 11% reduction in motion time during egg collection by optimizing the robot’s route using cluster-based planning. These findings highlight DAM’s potential as a valuable tool in poultry science, reducing costs while improving the precision of behavioral analysis and farm management tasks. Full article

As a consequence of the European Union introducing the prohibition of supplying antibiotic growth promoters (AGPs) in diets in 2006, antibiotic alternatives for poultry feed have become one of the most central issues. In general, probiotics and prebiotics are highly effective additives that improve host health and prevent pathogen colonization by modulating immune functions, altering the intestinal microecology, and enhancing digestion. However, the specific situations in which probiotics or prebiotics should be used still require further research. In addition, the advanced applications of probiotics and prebiotics, such as in ovo injection, also need to be investigated to improve the host performance. In the following review, we summarize various probiotic and prebiotic supplementation methods and compare the specific conditions for their use to improve poultry production management. Full article

Modern poultry and egg production is facing challenges such as dead chickens and floor eggs in cage-free housing. Precision poultry management strategies are needed to address those challenges. In this study, convolutional neural network (CNN) models and an intelligent bionic quadruped robot were used to detect floor eggs and dead chickens in cage-free housing environments. A dataset comprising 1200 images was used to develop detection models, which were split into training, testing, and validation sets in a 3:1:1 ratio. Five different CNN models were developed based on YOLOv8 and the robot’s 360° panoramic depth perception camera. The final results indicated that YOLOv8m exhibited the highest performance, achieving a precision of 90.59%. The application of the optimal model facilitated the detection of floor eggs in dimly lit areas such as below the feeder area and in corner spaces, as well as the detection of dead chickens within the flock. This research underscores the utility of bionic robotics and convolutional neural networks for poultry management and precision livestock farming. Full article

The welfare of hens in cage-free systems is closely linked to their behaviors, such as feeding, drinking, pecking, perching, bathing, preening, and foraging. To monitor these behaviors, we developed and evaluated deep learning models based on YOLO (You Only Look Once), an advanced object detection technology known for its high accuracy, speed, and compact size. Three YOLO-based models—YOLOv5s_BH, YOLOv5x_BH, and YOLOv7_BH—were created to track and classify the behaviors of laying hens in cage-free environments. A dataset comprising 1500 training images, 500 validation images, and 50 test images was used to train and validate the models. The models successfully detected poultry behaviors in test images with bounding boxes and objectness scores ranging from 0 to 1. Among the models, YOLOv5s_BH demonstrated superior performance, achieving a precision of 78.1%, surpassing YOLOv5x_BH and YOLOv7_BH by 1.9% and 2.2%, respectively. It also achieved a recall of 71.7%, outperforming YOLOv5x_BH and YOLOv7_BH by 1.9% and 2.8%, respectively. Additionally, YOLOv5s_BH recorded a mean average precision (mAP) of 74.6%, exceeding YOLOv5x_BH by 2.6% and YOLOv7_BH by 9%. While all models demonstrated high detection precision, their performance was influenced by factors such as stocking density, varying light conditions, and obstructions from equipment like drinking lines, perches, and feeders. This study highlights the potential for the automated monitoring of poultry behaviors in cage-free systems, offering valuable insights for producers. Full article

The epidemic of avian influenza outbreaks, especially high-pathogenicity avian influenza (HPAI), which causes respiratory disease and death, is a disaster in poultry. The outbreak of HPAI in 2014–2015 caused the loss of 60 million chickens and turkeys. The most recent HPAI outbreak, ongoing since 2021, has led to the loss of over 50 million chickens so far in the US and Canada. Farm biosecurity management practices have been used to prevent the spread of the virus. However, existing practices related to controlling the transmission of the virus through wild birds, especially waterfowl, are limited. For instance, ducks were considered hosts of avian influenza viruses in many past outbreaks. The objectives of this study were to develop a machine vision framework for tracking wild birds and test the performance of deep learning models in the detection of wild birds on poultry farms. A deep learning framework based on computer vision was designed and applied to the monitoring of wild birds. A night vision camera was used to collect data on wild bird near poultry farms. In the data, there were two main wild birds: the gadwall and brown thrasher. More than 6000 pictures were extracted through random video selection and applied in the training and testing processes. An overall precision of 0.95 (mAP@0.5) was reached by the model. The model is capable of automatic and real-time detection of wild birds. Missed detection mainly came from occlusion because the wild birds tended to hide in grass. Future research could be focused on applying the model to alert to the risk of wild birds and combining it with unmanned aerial vehicles to drive out detected wild birds. Full article

High particulate matter levels in cage-free (CF) houses have led to concerns from producers, as that can pose significant risks to the health and well-being of hens and their caretakers. This study aimed to assess the effectiveness of an electrostatic particle ionization (EPI) + bedding management (BM) treatment in reducing particulate matter (PM) concentrations. Four identical CF rooms each housed 175 hens for six weeks, with two rooms assigned to the EPI + BM treatment (EPI + 20% wood chip topping over 81-week-old litter) and the other two as controls. Measurements of PM were conducted twice a week for 10 min using TSI DustTrak. Additionally, small and large particle concentrations were monitored continuously using a Dylos monitor, with a sampling period of one minute. Footpad scoring was recorded for logistic analysis. Statistical analysis was performed using ANOVA with the Tukey HSD method (p < 0.05). Results demonstrated that the EPI + BM treatment significantly reduced particle counts (37.83% decrease in small particles, 55.90% decrease in large particles) compared to the control group (p < 0.01). PM concentrations were also substantially lowered across different size fractions, ranging from 58.41% to 64.17%. These findings underscore the effectiveness of the EPI + BM treatment in reducing PM in CF houses. The integration of EPI and bedding management innovated in this study holds promise for improving air quality and contributing to the well-being of hens and caretakers in CF housing systems. Full article

The poultry industry is shifting towards more sustainable and ethical practices, including adopting cage-free (CF) housing to enhance hen behavior and welfare. However, ensuring optimal indoor air quality, particularly concerning particulate matter (PM), remains challenging in CF environments. This study explores the effectiveness of electrostatic particle ionization (EPI) technology in mitigating PM in CF hen houses while considering the height at which the technology is placed and the duration of the electric supply. The primary objectives are to analyze the impact of EPI in reducing PM and investigate its power consumption correlation with electric supply duration. The study was conducted in a laying hen facility with four identical rooms housing 720 laying hens. The study utilized a Latin Square Design method in two experiments to assess the impact of EPI height and electric supply durations on PM levels and electricity consumption. Experiment 1 tested four EPI heights: H1 (1.5 m or 5 ft), H2 (1.8 m or 6 ft), H3 (2.1 m or 7 ft), and H4 (2.4 m or 8 ft). Experiment 2 examined four electric supply durations: D1 (control), D2 (8 h), D3 (16 h), and D4 (24 h), through 32 feet corona pipes. Particulate matter levels were measured at three different locations within the rooms for a month, and statistical analysis was conducted using ANOVA with a significance level of ≤0.05. The study found no significant differences in PM concentrations among different EPI heights (p > 0.05). However, the duration of EPI system operation had significant effects on PM₁, PM_2.5, and PM₄ concentrations (p < 0.05). Longer EPI durations resulted in more substantial reductions: D2—17.8% for PM₁, 11.0% for PM_2.5, 23.1% for PM4, 23.7% for PM₁₀, and 22.7% for TSP; D3—37.6% for PM₁, 30.4% for PM_2.5, 39.7% for PM₄, 40.2% for PM₁₀, and 41.1% for TSP; D4—36.6% for PM₁, 24.9% for PM_2.5, 38.6% for PM₄, 36.3% for PM₁₀, and 37.9% for TSP compared to the D1. These findings highlight the importance of prolonged EPI system operation for enhancing PM reduction in CF hen houses. However, utilizing 16 h EPI systems during daylight may offer a more energy-efficient approach while maintaining effective PM reduction. Further research is needed to optimize PM reduction strategies, considering factors like animal activities, to improve air quality and environmental protection in CF hen houses. Full article

Poultry locomotion is an important indicator of animal health, welfare, and productivity. Traditional methodologies such as manual observation or the use of wearable devices encounter significant challenges, including potential stress induction and behavioral alteration in animals. This research introduced an innovative approach that employs an enhanced track anything model (TAM) to track chickens in various experimental settings for locomotion analysis. Utilizing a dataset comprising both dyed and undyed broilers and layers, the TAM model was adapted and rigorously evaluated for its capability in non-intrusively tracking and analyzing poultry movement by intersection over union (mIoU) and the root mean square error (RMSE). The findings underscore TAM’s superior segmentation and tracking capabilities, particularly its exemplary performance against other state-of-the-art models, such as YOLO (you only look once) models of YOLOv5 and YOLOv8, and its high mIoU values (93.12%) across diverse chicken categories. Moreover, the model demonstrated notable accuracy in speed detection, as evidenced by an RMSE value of 0.02 m/s, offering a technologically advanced, consistent, and non-intrusive method for tracking and estimating the locomotion speed of chickens. This research not only substantiates TAM as a potent tool for detailed poultry behavior analysis and monitoring but also illuminates its potential applicability in broader livestock monitoring scenarios, thereby contributing to the enhancement of animal welfare and management in poultry farming through automated, non-intrusive monitoring and analysis. Full article

Social dynamics and lighting conditions influence floor egg-laying behavior (FELB) in hens. Hens prefer to lay eggs in darker areas, leading to mislaid eggs in cage-free systems. Consistent lighting is crucial to prevent mislaid eggs, but equipment obstructions can result in a dark floor area. These dark areas entice hens to lay their eggs outside the designated nesting area, which can lead to potential losses, damage, or contamination, creating hygiene problems and increasing the risk of bacterial growth, resulting in foodborne illnesses. Therefore, additional lighting in dark areas can be a potential solution. The objectives of this study were to evaluate the effectiveness of providing additional light in darker areas in reducing the number of mislaid eggs and FELB. Approximately 720 Hy-Line W-36 hens were housed in four cage-free experimental rooms (180 hens per room), and 6 focal hens from each room were randomly selected and provided with numbered harnesses (1–6) to identify which hens were performing FELB and identify the effect of illuminating solutions. Eggs laid on the floor and in nests were collected and recorded daily for two weeks before and after the light treatment. Statistical analysis was performed using paired t-tests for mislaid eggs and logistic regression for FELB in R Studio (p < 0.05). This study found that additional lighting in darker areas reduced the number of mislaid eggs by 23.8%. Similarly, the number of focal hens performing FELB decreased by 33.3%. This research also unveiled a noteworthy disparity in FELB, with approximately one-third of hens preferring designated nesting areas, while others opted for the floor, which was influenced by social dynamics. Additionally, egg-laying times varied significantly, ranging from 21.3 to 108.03 min, indicating that environmental factors and disturbances played a substantial role in this behavior. These findings suggest that introducing additional lighting in darker areas changes FELB in hens, reducing mislaid eggs and improving egg quality in cage-free systems. Full article

Cage-free (CF) layer houses tend to have high particulate matter (PM) levels because of bedding/litter floor and the birds’ activities, such as perching, dustbathing, and foraging on it. It has been reported that optimizing bedding management can potentially suppress PM levels in CF houses. The objectives of this study were to (1) test the effect of the top application of new bedding materials (BMs) on PM levels and (2) compare different BM PM reduction efficiencies. Small flake shavings (SFS), large flake shavings (LFS), and aspen wood chips (AWC) were top-dressed on the surface of the original litter (33-week-old litter) evenly in each of the BM treatment rooms at 20% volume of the original litter floor. The initial litter depths in the control, SFS, LFS, and AWC rooms were 4.6 ± 0.6, 4.8 ± 0.8 cm, 4.8 ± 0.8 cm, and 4.6 ± 0.9 cm, respectively. One room was used as a control without adding new BM. The results indicate that the top application of new bedding suppressed PM levels in all treatment rooms (p < 0.01). The PM_2.5 reductions in the SFS, AWC, and LFS treatment rooms were 36.5%, 34.6%, and 28.9% greater than in the control room, respectively. The mitigation efficiencies were different between PM sizes. For instance, PM_2.5, PM₁₀, and TSP in the SFS room were lower than in the control room by 36.5%, 39.4%, and 38.7%, respectively. For litter quality, the moisture content was 18.0 ± 2.8, 20.0 ± 3.1, 20.6 ± 2.4, and 19.7 ± 4.2% in the control, SFS, LFS, and AWC rooms, respectively. Treatment rooms with 20% new BM had 10% higher litter moisture than the control room. The findings of this study reveal that the top application of new bedding on old litter is a potential strategy for reducing PM generation in CF houses. Further studies are warranted, such as regarding the effect of different ratios of new bedding on PM reduction, cost analysis, and verification tests in commercial CF houses. Full article

Defective eggs diminish the value of laying hen production, particularly in cage-free systems with a higher incidence of floor eggs. To enhance quality, machine vision and image processing have facilitated the development of automated grading and defect detection systems. Additionally, egg measurement systems utilize weight-sorting for optimal market value. However, few studies have integrated deep learning and machine vision techniques for combined egg classification and weighting. To address this gap, a two-stage model was developed based on real-time multitask detection (RTMDet) and random forest networks to predict egg category and weight. The model uses convolutional neural network (CNN) and regression techniques were used to perform joint egg classification and weighing. RTMDet was used to sort and extract egg features for classification, and a Random Forest algorithm was used to predict egg weight based on the extracted features (major axis and minor axis). The results of the study showed that the best achieved accuracy was 94.8% and best R2 was 96.0%. In addition, the model can be used to automatically exclude non-standard-size eggs and eggs with exterior issues (e.g., calcium deposit, stains, and cracks). This detector is among the first models that perform the joint function of egg-sorting and weighing eggs, and is capable of classifying them into five categories (intact, crack, bloody, floor, and non-standard) and measuring them up to jumbo size. By implementing the findings of this study, the poultry industry can reduce costs and increase productivity, ultimately leading to better-quality products for consumers. Full article

Poultry farming plays a significant role in ensuring food security and economic growth in many countries. However, various factors such as feeding management practices, environmental conditions, and diseases lead to poultry mortality (dead birds). Therefore, regular monitoring of flocks and timely veterinary assistance is crucial for maintaining poultry health, well-being, and the success of poultry farming operations. However, the current monitoring method relies on manual inspection by farm workers, which is time-consuming. Therefore, developing an automatic early mortality detection (MD) model with higher accuracy is necessary to prevent the spread of infectious diseases in poultry. This study aimed to develop, evaluate, and test the performance of YOLOv5-MD and YOLOv6-MD models in detecting poultry mortality under various cage-free (CF) housing settings, including camera height, litter condition, and feather coverage. The results demonstrated that the YOLOv5s-MD model performed exceptionally well, achieving a high mAP@0.50 score of 99.5%, a high FPS of 55.6, low GPU usage of 1.04 GB, and a fast-processing time of 0.4 h. Furthermore, this study also evaluated the models’ performances under different CF housing settings, including different levels of feather coverage, litter coverage, and camera height. The YOLOv5s-MD model with 0% feathered covering achieved the best overall performance in object detection, with the highest mAP@0.50 score of 99.4% and a high precision rate of 98.4%. However, 80% litter covering resulted in higher MD. Additionally, the model achieved 100% precision and recall in detecting hens’ mortality at the camera height of 0.5 m but faced challenges at greater heights such as 2 m. These findings suggest that YOLOv5s-MD can detect poultry mortality more accurately than other models, and its performance can be optimized by adjusting various CF housing settings. Therefore, the developed model can assist farmers in promptly responding to mortality events by isolating affected birds, implementing disease prevention measures, and seeking veterinary assistance, thereby helping to reduce the impact of poultry mortality on the industry, ensuring the well-being of poultry and the overall success of poultry farming operations. Full article

The welfare of laying hens in conventional caged houses has become an increased public concern, leading primary food chains, restaurants, and grocers in the United States to pledge to source only cage-free (CF) eggs by 2025 or 2030. Cage-free housing systems have been considered as a more humane alternative; however, they still come with certain challenges. One of the primary challenges with CF housing is the poor indoor air quality due to the high levels of ammonia (NH₃) and particulate matter (PM). Despite the importance of air quality in animal welfare, most studies have focused on the egg-laying stage, thereby leaving a significant knowledge gap in the pullet phase. Addressing this gap is essential to ensure the well-being of laying hens in CF housing and to help producers and researchers identify effective strategies to mitigate the impact of poor indoor air quality on the bird’s health and welfare. Therefore, the objective of this study was to (a) examine the effect of the pullets’ age on NH₃ and PM levels, and (b) find the effect of housing, litter moisture content (LMC), and relative humidity (RH) on air pollutant concentrations. The results show that the PM levels of PM_2.5, PM₁₀, and total suspended particles (TSP) increased significantly with the growth of birds from 1 to 16 weeks of age (WOA) (p < 0.01). For instance, PM_2.5, PM₁₀, and TSP levels were measured at 0.023 ± 0.003, 0.031 ± 0.004, and 0.058 ± 0.013 mg m⁻³ in the first week, and these levels increased to 1.44 ± 0.58, 2.723 ± 1.094, and 6.39 ± 2.96 mg m⁻³, respectively, by 16 WOA. In addition, PM levels measured near the perch were found to be three times higher than other locations inside the rooms (e.g., between the feeder and drinker or near the exhaust fan) (p < 0.01), as perching is one of the primary reasons for dust generation. Furthermore, a significant interaction between the age of the pullets and PM levels was found (p < 0.01), as the litter quality and the behaviors of birds were changing over time. For NH₃ levels, average daily concentrations were lower than 1 ppm at 16 WOA for all rooms due to dry litter conditions (i.e., 9–10% LMC). Additionally, RH has been shown to have a significant effect on air pollutant concentration. Overall, the results indicate that the bird’s age significantly affects PM generation and PM variation within the rooms. The variation of PM was directly affected by RH inside the house. Therefore, this research will provide valuable information for both researchers and producers to control air pollutant emissions from the pullet stage in CF housing to ultimately improve the health and welfare of hens. Full article