Aiming at the problem of accurately locating and identifying multi-scale and differently shaped apple leaf diseases from a complex background in natural scenes, this study proposed an apple leaf disease detection method based on an improved YOLOv5s model. Firstly, the model utilized the bidirectional feature pyramid network (BiFPN) to achieve multi-scale feature fusion efficiently. Then, the transformer and convolutional block attention module (CBAM) attention mechanisms were added to reduce the interference from invalid background information, improving disease characteristics’ expression ability and increasing the accuracy and recall of the model. Experimental results showed that the proposed BTC-YOLOv5s model (with a model size of 15.8M) can effectively detect four types of apple leaf diseases in natural scenes, with 84.3% mean average precision (mAP). With an octa-core CPU, the model could process 8.7 leaf images per second on average. Compared with classic detection models of SSD, Faster R-CNN, YOLOv4-tiny, and YOLOx, the mAP of the proposed model was increased by 12.74%, 48.84%, 24.44%, and 4.2%, respectively, and offered higher detection accuracy and faster detection speed. Furthermore, the proposed model demonstrated strong robustness and mAP exceeding 80% under strong noise conditions, such as exposure to bright lights, dim lights, and fuzzy images. In conclusion, the new BTC-YOLOv5s was found to be lightweight, accurate, and efficient, making it suitable for application on mobile devices. The proposed method could provide technical support for early intervention and treatment of apple leaf diseases.

Wheat aphids are the primary pests in wheat-producing areas, posing a serious threat to stable, high wheat yields and regional food security. To detect and count wheat aphids under different complex conditions, this study designed an improved model and developed a mini program. Firstly, we constructed a dual-source dataset containing 542 images collected from indoor and field environments, including 117 indoor images and 425 field images. Secondly, we proposed Aphid Identification and Detection YOLO (AID-YOLO), an enhanced YOLO11n-based method for close-range wheat aphid detection and image-level counting. Specifically, the original downsampling structure was replaced with the ADown module to improve feature extraction efficiency while reducing redundant computation, an IEMA multi-scale attention mechanism integrating IRMB and EMA was introduced to strengthen feature learning under complex background interference, and the dynamic upsampling operator DySample was adopted to enhance cross-scale feature fusion. Finally, AID-YOLO achieved a 19.0% reduction in parameter count (2.09 M vs. 2.58 M) and a 19.0% decrease in computational cost (5.1 vs. 6.3 GFLOPs). Across three random seeds, AID-YOLO achieved an average mAP50 of 95.3 ± 0.10%, compared with 93.0 ± 0.39% for the YOLO11n baseline on the combined indoor–field evaluation set. These results suggest that AID-YOLO achieves a favorable balance between detection accuracy and model lightweighting under the tested indoor and field conditions, providing a useful technical reference for intelligent wheat aphid monitoring.

Fusarium Head Blight (FHB) is a major disease caused by Fusarium graminearum, poses a significant threat to yield and quality of wheat production. Timely and accurately monitoring of wheat FHB is essential for effective management and loss assessment. In this study, unmanned aerial vehicle (UAV) equipped with RGB digital and multispectral cameras were employed to capture remote sensing images of wheat fields, and the color space of L*a*b* and HSV from RGB images, as well as vegetation indices (VIs) and texture features (TFs) from multispectral images were integrated. First, the Lasso-MGRS method was utilized to screen and reduce the dimensionality of different types of features. Then, support vector machine (SVM) were applied to estimate the severity of wheat FHB using both single and integrated features. Finally, Bayesian optimization (BO) was used to fine-tune the parameters of the SVM, random forest (RF) and extreme gradient boosting (XGBoost) to improve the models’ accuracy. The results indicated that the combination with different types of features showed a better estimation performance with the overall accuracy (OA) and kappa coefficient were 0.7703 and 0.7123 respectively. The models with BO achieved the highest accuracy with the OA and kappa coefficient were 0.8649 and 0.8309 respectively.