Digestive diseases are one of the common broiler diseases that significantly affect production and animal welfare in broiler breeding. Droppings examination and observation are the most precise techniques to detect the occurrence of digestive disease infections in birds. This study proposes an automated broiler digestive disease detector based on a deep Convolutional Neural Network model to classify fine-grained abnormal broiler droppings images as normal and abnormal (shape, color, water content, and shape&water). Droppings images were collected from 10,000 25-35-day-old Ross broiler birds reared in multilayer cages with automatic droppings conveyor belts. For comparative purposes, Faster R-CNN and YOLO-V3 deep Convolutional Neural Networks were developed. The performance of YOLO-V3 was improved by optimizing the anchor box. Faster R-CNN achieved 99.1% recall and 93.3% mean average precision, while YOLO-V3 achieved 88.7% recall and 84.3% mean average precision on the testing data set. The proposed detector can provide technical support for the detection of digestive diseases in broiler production by automatically and nonintrusively recognizing and classifying chicken droppings.

Broilers produce abnormal sounds such as cough and snore when they suffer from respiratory diseases. The aim of this research work was to develop a method for broiler abnormal sound detection. The sounds were recorded in a broiler house for one week (24/7). There were 20 thousand white feather broilers reared on the floor in a building. Results showed that the developed recognition algorithm, using wavelet transform Mel frequency cepstrum coefficients (WMFCCs), correlation distance Fisher criterion (CDF), and hidden Markov model (HMM), provided an average accuracy, precision, recall, and F1 of 93.8%, 94.4%, 94.1%, and 94.2%, respectively, for broiler sound samples. The results indicate that sound analysis can be used in broiler respiratory assessment in a commercial broiler farm.

Surface temperature variation in a broiler’s head can be used as an indicator of its health status. Surface temperatures in the existing thermograph based animal health assessment studies were mostly obtained manually. 2185 thermal images, each of which had an individual broiler, were captured from 20 broilers. Where 15 broilers served as the experimental group, they were injected with 0.1mL of pasteurella inoculum. The rest, 5 broilers, served as the control group. An algorithm was developed to extract head surface temperature automatically from the top-view broiler thermal image. Adaptive K-means clustering and ellipse fitting were applied to locate the broiler’s head region. The maximum temperature inside the head region was extracted as the head surface temperature. The developed algorithm was tested in Matlab^® (R2016a) and the testing results indicated that the head region in 92.77% of the broiler thermal images could be located correctly. The maximum error of the extracted head surface temperatures was not greater than 0.1 °C. Different trend features were observed in the smoothed head surface temperature time series of the broilers in experimental and control groups. Head surface temperature extracted by the presented algorithm lays a foundation for the development of an automatic system for febrile broiler identification.

Estrus detection is an essential operation in the breeding of sows, and accurate estrus detection is immensely important to maintain the productivity and reproductive performance of sow. However, traditional sow estrus detection relies on the manually back-pressure test, which is time-consuming and labor-intensive. This study aimed to develop an automatic method to detect estrus. In this study, a model based on the optimized yolov5s algorithm was constructed to detect the four sow postures of standing, sitting, sternum, lateral, and calculated the frequency of posture change in sows. Based on this, we studied the behavior of sows before and after estrus. The method embedded a convolutional block attention module into the backbone network to improve the feature extraction capability of the model. In addition, the object box judgment module was used to avoid interference from other sows in the detection region. Accelerate the optimized model on the TensorRT platform, ensuring that the embedded graphics card can run the model with lower latency. The result shows that the precision of estrus detection is 97.1%, and the accuracy of estrus detection is 94.1%. The processing time of a single image on the embedded graphics card is 74.4 ms, and this method could better meet the estrus detection demand in sow production.

Sow farrowing is an important part of pig breeding. The accurate and effective early warning of sow behaviors in farrowing helps breeders determine whether it is necessary to intervene with the farrowing process in a timely manner and is thus essential for increasing the survival rate of piglets and the profits of pig farms. For large pig farms, human resources and costs are important considerations in farrowing supervision. The existing method, which uses cloud computing-based deep learning to supervise sow farrowing, has a high equipment cost and requires uploading all data to a cloud data center, requiring a large network bandwidth. Thus, this paper proposes an approach for the early warning and supervision of farrowing behaviors based on the embedded artificial-intelligence computing platform (NVIDIA Jetson Nano). This lightweight deep learning method allows the rapid processing of sow farrowing video data at edge nodes, reducing the bandwidth requirement and ensuring data security in the network transmission. Experiments indicated that after the model was migrated to the Jetson Nano, its precision of sow postures and newborn piglets detection was 93.5%, with a recall rate of 92.2%, and the detection speed was increased by a factor larger than 8. The early warning of 18 approaching farrowing (5 h) sows were tested. The mean error of warning was 1.02 h.

The production management of lactating sows is a crucial aspect of pig farm operations, as their health directly impacts the farm’s production efficiency. The feeding behavior of lactating sows can reflect their health and welfare status, and monitoring this behavior is essential for precise feeding and management. To address the issues of time-consuming and labor-intensive manual inspection of lactating sows’ feeding behavior and the reliance on breeders’ experience, we propose a method based on the improved YOLO (You Only Look Once) v5s algorithm and image segmentation for detecting the feeding behavior of lactating sows. Based on the YOLOv5s algorithm, the SE (Squeeze-and-Excitation) attention module was added to enhance the algorithm’s performance and reduce the probability of incorrect detection. Additionally, the loss function was replaced by WIoU (Weighted Intersection over Union) to accelerate the model’s convergence speed and improve detection accuracy. The improved YOLOv5s-C3SE-WIoU model is designed to recognize pre-feeding postures and feed trough conditions by detecting images of lactating sows. Compared to the original YOLOv5s, the improved model achieves an 8.9% increase in mAP@0.5 and a 4.7% increase in mAP@0.5 to 0.95. This improvement satisfies the requirements for excellent detection performance, making it suitable for deployment in large-scale pig farms. From the model detection results, the trough remnant image within the detection rectangle was extracted. This image was further processed using image processing techniques to achieve trough remnant image segmentation and infer the remnant amount. Based on the detection model and residue inference method, video data of lactating sows’ feeding behavior were processed to derive the relationship between feeding behavior, standing time, and residue amount. Using a standing duration of 2 s and a leftover-feed proportion threshold of 2% achieves the highest accuracy, enabling the identification of abnormal feeding behavior. We analyzed the pre-feeding postures and residual feed amounts of abnormal and normal groups of lactating sows. Our findings indicated that standing time was significantly lower and residual feed amount was higher in the abnormal groups compared to the normal groups. By combining standing time and residual feed amount information, accurate detection of the feeding status of lactating sows can be realized. This approach facilitates the accurate detection of abnormal feeding behaviors of lactating sows in large-scale pig farm environments.