This narrative review with structured literature screening combines comprehensive research on the rapid adoption of object detection computer vision models, particularly "You Only Look Once" (YOLO), used alone or in conjunction with other machine learning models, to advance Precision Poultry Farming (PPF), which refers to the application of data-driven and automated technologies to monitor, manage, and optimize poultry health, welfare, and production efficiency. A literature search across search engines, such as Google Scholar, was used because of its broad interdisciplinary coverage, allowing retrieval of literature spanning animal science, computer vision, and agricultural engineering, which are often indexed across different publications venues, on October 15 2024, which revealed 408 results when searching with search expression "YOLO + broilers + layers" and publications dated from 2015 to October 15, 2024. We removed 200 articles during screening, and 126 articles were excluded after eligibility evaluation, resulting in 82 eligible research papers to be included for this review. The YOLO object detection models have evolved from YOLOv1 to YOLO11 by 2024, progressively improving in model performance, speed, accuracy, and robustness through the refinement of key architectural components, including backbone networks, detection heads, and loss functions. This review highlights how YOLO models have been applied to broiler chickens and laying hens across diverse housing systems to support key tasks such as identification, behavior detection, counting, tracking, health and disease monitoring, flock distribution pattern, and calculating activity index, often in combination with other machine vision models. The analysis shows that it took 4 years to apply YOLO models for the object detection task in poultry since the release of the first version of the YOLO model in 2015. The application of YOLO models in poultry from 2019 to 2021 was very slow and sporadic while it took rapid growth in publications since 2021, led primarily by research groups in China and the USA, and mainly concentrated in journals such as Computers and Electronics in Agriculture (10), Institute of Electrical and Electronics Engineers (IEEE) Conference (10), Poultry Science (9), Animals (6), and AgriEngineering (5). Major opportunities and challenges are identified around deploying these models for reliable, real-time decision support on commercial farms, particularly for animal welfare assessment, disease and wild bird detection, and integration with complementary sensing and analytics frameworks.

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.

Poultry diseases threaten animal welfare and productivity, especially in cage-free systems where communal environments increase disease transmission risks. Traditional diagnostic methods, though accurate, are often labor-intensive, time-consuming, and not suitable for continuous monitoring. This study aimed to develop a web-based disease screening tool to make this process faster and accurate using fecal images. A publicly available dataset consisting of 6812 PCR-verified images categorized into Coccidiosis, Newcastle Disease (NCD), Salmonella, and Healthy from commercial farms in Tanzania was used in this study. Augmentation was used to address the imbalance present in the dataset, with NCD underrepresented (376 images) compared to other classes (>2000 images). Five YOLOv11 detection models were trained, with YOLO11n selected due to its high mean average precision (mAP@0.5 = 0.881). For classification, EfficientNet-B0 was chosen over the EfficientNet-B1 variant because of its high accuracy (99.12% vs. 98.54% for B1). Despite high class imbalance, B0 had higher precision than B1 for the underrepresented NCD class (0.88 for B1 vs. 1.00 for B0). The system achieved an average total inference time of 25.8 milliseconds, demonstrating real-time capabilities. Field testing, expanding datasets across different regions, and incorporating additional diseases is required to further validate and enhance the robustness of the system.

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.

Mislaid eggs are management and economic challenges in Cage-free (CF) housing systems, producing about 10-15 % floor eggs, although approximately 40 % of table egg laying hens are now in CF production systems. Ramps may ease the use of nesting boxes by minimizing physical extension to hens, thereby reducing floor eggs, and increasing the number of eggs laid in the nest box. The objective of our study was to develop a deep learning method for monitoring hens' ramp use and the potential impact of ramp access to the nest box on the number of floor eggs and the number of eggs laid in the nest boxes. A total of 600 Lohmann LSL Lite hens were raised from day 1 to 413 in three identical research rooms (7.3 m L × 6.1 m W × 3 m H) following the Lohmann LSL Lite management guide. Each study room had four nest boxes placed at the four corners of the room. Two nest boxes were provided with ramp access (R), and two nest boxes had no ramp access (NR) in each study room and were replicated among three study rooms. The ramp use was video recorded at 15 frames per second (fps). We trained two You Only Look Once (YOLO) models, YOLOv5u and YOLO11, object detection models for 200 epochs each. A total of 2,000 images were used for training (70 %), validation (20 %), and testing (10 %) for the model. All models achieved a precision, recall, and mean average precision at 0.50 intersection over union (mAP@0.50) of at least 0.94. YOLO11n(nano) achieved the highest precision (0.9940), recall (0.9934), and mAP@0.50 (0.9848). Our best model provides a baseline for automatic ramp use detection with 0.99 precision. Ramp access did not lower the floor egg production statistically (p = 0.5468). Across bird weeks, ramp access (R) and no ramp access (NR) revealed opposite patterns in floor and nest-box egg production. Ramp access generally resulted in significantly higher floor egg production in several weeks (52, 54, 58), but also produced higher nest-box egg counts in other weeks (49, 51, 52, 54, 56, 58), whereas no-ramp access showed more nest-box access in weeks when ramp access floor egg were high (48, 50, 53, 55, 57, 59). Overall, ramp access did not consistently increase or decrease egg laying in either location, but shifted the proportion of eggs between the floor and nest-boxes depending on bird age (week). Future studies are warranted to investigate the effect of ramp use on nesting behavior and floor eggs from egg laying to the end of the laying cycle. Data on floor eggs and nest box eggs with ramp access to the nest box from commercial aviary systems, as well as the CF system, also need to be compared.

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.