The automated recognition of individual cows is foundational for implementing intelligent farming. Traditional methods of individual cow recognition from an overhead perspective primarily rely on singular back features and perform poorly for cows with diverse orientation distributions and partial body visibility in the frame. This study proposes an open-set method for individual cow recognition based on spatial feature transformation and metric learning to address these issues. Initially, a spatial transformation deep feature extraction module, ResSTN, which incorporates preprocessing techniques, was designed to effectively address the low recognition rate caused by the diverse orientation distribution of individual cows. Subsequently, by constructing an open-set recognition framework that integrates three attention mechanisms, four loss functions, and four distance metric methods and exploring the impact of each component on recognition performance, this study achieves refined and optimized model configurations. Lastly, introducing moderate cropping and random occlusion strategies during the data-loading phase enhances the model’s ability to recognize partially visible individuals. The method proposed in this study achieves a recognition accuracy of 94.58% in open-set scenarios for individual cows in overhead images, with an average accuracy improvement of 2.98 percentage points for cows with diverse orientation distributions, and also demonstrates an improved recognition performance for partially visible and randomly occluded individual cows. This validates the effectiveness of the proposed method in open-set recognition, showing significant potential for application in precision cattle farming management.

As the unique identifier of individual breeding pigs, the loss of ear tags can result in the loss of breeding pigs’ identity information, leading to data gaps and confusion in production and genetic breeding records, which can have catastrophic consequences for breeding efforts. Detecting the loss of ear tags in breeding pigs can be challenging in production environments due to factors such as overlapping breeding pig clusters, imbalanced pig-to-tag ratios, and relatively small-sized ear tags. This study proposes an improved method for the detection of lost ear tags in breeding pigs based on Cascade Mask R-CNN. Firstly, the model utilizes ResNeXt combined with a feature pyramid network (FPN) as the feature extractor; secondly, the classification branch incorporates the online hard example mining (OHEM) technique to improve the utilization of ear tags and low-confidence samples; finally, the regression branch employs a decay factor of Soft-NMS to reduce the overlap of redundant bounding boxes. The experiment employs a sliding window detection method to evaluate the algorithm’s performance in detecting lost ear tags in breeding pigs in a production environment. The results show that the accuracy of the detection can reach 92.86%. This improvement effectively enhances the accuracy and real-time performance of lost ear tag detection, which is highly significant for the production and breeding of breeding pigs.

Research on the Intelligent Cloud Animal Husbandry Platform: Aiming at the problem that the traditional talent training mode is difficult to cultivate the intelligent animal husbandry compound talents needed by the implementation of the rural revitalization strategy, a cloud animal husbandry platform is designed to cultivate Understand Agriculture, devote to Rural Community and Be Sincere to Farmers compound talents. The platform adopts the two-wing multilevel architecture design of the concept of the cloud side, which is composed of three parts: the data center platform, resource sharing platform, and business cloud service platform. The data center platform is responsible for the collection, processing, integration, and asset management of the four-dimensional real data and provides computing, storage, and data asset services for the cloud livestock platform. The resource sharing platform provides sharing services from resources and development kits to carriers. Livestock cloud service platform is to carry out the integration of industry, education, and science and education, the design and implementation of cloud teaching, cloud scientific research, and cloud breeding business cloud services. Through its practical application in many universities and enterprises, the platform is verified to be safe, effective, and reliable in teaching, scientific research, and social services and has both operational and promotional value.

In precision feeding, non-contact and pressure-free monitoring of sheep feeding behavior is crucial for health monitoring and optimizing production management. The experimental conditions and real-world environments differ when using acoustic sensors to identify sheep feeding behaviors, leading to discrepancies and consequently posing challenges for achieving high-accuracy classification in complex production environments. This study enhances the classification performance by integrating the deep spectrogram features and acoustic characteristics associated with feeding behavior. We conducted the task of collecting sound data in actual production environments, considering noise and complex surroundings. The method included evaluating and filtering the optimal acoustic features, utilizing a customized convolutional neural network (SheepVGG-Lite) to extract Short-Time Fourier Transform (STFT) spectrograms and Constant Q Transform (CQT) spectrograms’ deep features, employing cross-spectrogram feature fusion and assessing classification performance through a support vector machine (SVM). Results indicate that the fusion of cross-spectral features significantly improved classification performance, achieving a classification accuracy of 96.47%. These findings highlight the value of integrating acoustic features with spectrogram deep features for accurately recognizing sheep feeding behavior.

Ovine pulmonary adenocarcinoma (OPA) is a contagious lung tumour caused by the Jaagsiekte Sheep Retrovirus (JSRV). Histopathological diagnosis is the gold standard for OPA diagnosis. However, interpretation of traditional pathology images is complex and operator dependent. The mask regional convolutional neural network (Mask R-CNN) has emerged as a valuable tool in pathological diagnosis. This study utilized 54 typical OPA whole slide images (WSI) to extract 7167 typical lesion images containing OPA to construct a Common Objects in Context (COCO) dataset for OPA pathological images. The dataset was categorized into training and test sets (8:2 ratio) for model training and validation. Mean average specificity (mASp) and average sensitivity (ASe) were used to evaluate model performance. Six WSI-level pathological images (three OPA and three non-OPA images), not included in the dataset, were used for anti-peeking model validation. A random selection of 500 images, not included in the dataset establishment, was used to compare the performance of the model with assessment by pathologists. Accuracy, sensitivity, specificity, and concordance rate were evaluated. The model achieved a mASp of 0.573 and an ASe of 0.745, demonstrating effective lesion detection and alignment with expert annotation. In Anti-Peeking verification, the model showed good performance in locating OPA lesions and distinguished OPA from non-OPA pathological images. In the random 500-image diagnosis, the model achieved 92.8% accuracy, 100% sensitivity, and 88% specificity. The agreement rates between junior and senior pathologists were 100% and 96.5%, respectively. In conclusion, the Mask R-CNN-based OPA diagnostic model developed for OPA facilitates rapid and accurate diagnosis in practical applications.