$Fusarium$ head blight (FHB) is one of the most detrimental wheat diseases. The accurate identification of FHB severity is significant to the sustainable management of FHB and the guarantee of food production and security. A total of 2752 images with five infection levels were collected to establish an FHB severity grading dataset (FHBSGD), and a novel lightweight GSEYOLOX-s was proposed to automatically recognize the severity of FHB. The simple, parameter-free attention module (SimAM) was fused into the CSPDarknet feature extraction network to obtain more representative disease features while avoiding additional parameters. Meanwhile, the ghost convolution of the model head (G-head) was designed to achieve lightweight and speed improvements. Furthermore, the efficient intersection over union (EIoU) loss was employed to accelerate the convergence speed and improve positioning precision. The results indicate that the GSEYOLOX-s model with only 8.06 MB parameters achieved a mean average precision (mAP) of 99.23% and a detection speed of 47 frames per second (FPS), which is the best performance compared with other lightweight models, such as EfficientDet, Mobilenet-YOLOV4, YOLOV7, YOLOX series. The proposed GSEYOLOX-s was deployed on mobile terminals to assist farmers in the real-time identification of the severity of FHB and facilitate the precise management of crop diseases.

The behavior of pigs is intricately tied to their health status, highlighting the critical importance of accurately recognizing pig behavior, particularly abnormal behavior, for effective health monitoring and management. This study addresses the challenge of accommodating frequent non-rigid deformations in pig behavior using deformable convolutional networks (DCN) to extract more comprehensive features by incorporating offsets during training. To overcome the inherent limitations of traditional DCN offset weight calculations, the study introduces the multi-path coordinate attention (MPCA) mechanism to enhance the optimization of the DCN offset weight calculation within the designed DCN-MPCA module, further integrated into the cross-scale cross-feature (C2f) module of the backbone network. This optimized C2f-DM module significantly enhances feature extraction capabilities. Additionally, a gather-and-distribute (GD) mechanism is employed in the neck to improve non-adjacent layer feature fusion in the YOLOv8 network. Consequently, the novel DM-GD-YOLO model proposed in this study is evaluated on a self-built dataset comprising 11,999 images obtained from an online monitoring platform focusing on pigs aged between 70 and 150 days. The results show that DM-GD-YOLO can simultaneously recognize four common behaviors and three abnormal behaviors, achieving a precision of 88.2%, recall of 92.2%, and mean average precision (mAP) of 95.3% with 6.0MB Parameters and 10.0G FLOPs. Overall, the model outperforms popular models such as Faster R-CNN, EfficientDet, YOLOv7, and YOLOv8 in monitoring pens with about 30 pigs, providing technical support for the intelligent management and welfare-focused breeding of pigs while advancing the transformation and modernization of the pig industry.

Livestock behavior serves as a crucial indicator of physiological health. Leveraging deep learning techniques to automatically recognize dairy goat behaviors, particularly abnormal ones, enables early detection of potential health and environmental issues. To address the challenges of recognizing small-target behaviors in complex environments, a multi-scale and lightweight behavior recognition model for dairy goats called GSCW-YOLO was proposed. The model integrates Gaussian Context Transformation (GCT) and the Content-Aware Reassembly of Features (CARAFE) upsampling operator, enhancing the YOLOv8n framework’s attention to behavioral features, reducing interferences from complex backgrounds, and improving the ability to distinguish subtle behavior differences. Additionally, GSCW-YOLO incorporates a small-target detection layer and optimizes the Wise-IoU loss function, increasing its effectiveness in detecting distant small-target behaviors and transient abnormal behaviors in surveillance videos. Data for this study were collected via video surveillance under varying lighting conditions and evaluated on a self-constructed dataset comprising 9213 images. Experimental results demonstrated that the GSCW-YOLO model achieved a precision of 93.5%, a recall of 94.1%, and a mean Average Precision (mAP) of 97.5%, representing improvements of 3, 3.1, and 2 percentage points, respectively, compared to the YOLOv8n model. Furthermore, GSCW-YOLO is highly efficient, with a model size of just 5.9 MB and a frame per second (FPS) of 175. It outperforms popular models such as CenterNet, EfficientDet, and other YOLO-series networks, providing significant technical support for the intelligent management and welfare-focused breeding of dairy goats, thus advancing the modernization of the dairy goat industry.