Introduction: Accurate detection of sugarcane stem nodes is essential for intelligent seed cane cutting, yet existing detectors are often limited by large parameter counts, small target feature loss, and performance degradation under motion blur, making them difficult to deploy on edge devices. Methods: This study developed SAD-YOLOv11, a lightweight and accurate detector based on YOLOv11, incorporating three modifications. These include an average pooling downsampling module named ADown for reducing computational cost while preserving edge features, a self attention based AIFI module for global contextual modeling, and a SEAMHead detection head with joint channel and spatial attention for adaptive feature calibration. The model was evaluated on a custom sugarcane stem node dataset. Results: The model achieved a precision of 95.92%, a recall of 95.66%, and an mAP50 of 97.57%, maintaining detection accuracy at a level comparable to the baseline YOLOv11 while reducing parameter count and FLOPs by 18.13% and 17.55%. Under physically captured motion blur conditions, the model maintained more stable detection than the baseline, with the advantage becoming more pronounced as blur severity increased. Deployment on the Jetson Orin NX platform with TensorRT-FP16 quantization achieved a throughput of 37.1 FPS with a zero frame drop rate at a 30 FPS input frame rate, and compressed the engine size by 46.7%. Discussion: These results suggest that SAD-YOLOv11 achieves a sound balance between detection accuracy and computational efficiency suitable for intelligent seed cane cutting equipment.

Rice bacterial leaf blight (BLB), caused by the bacterium Xanthomonas oryzae pv. oryzae, severely damages leaves during rice growth, leading to reduced yield or even death. This study aimed to develop an automated identification and assessment method for rice BLB based on multispectral UAV imagery to overcome the limitations of in-field inspection methods. By obtaining multispectral image data of rice fields and extracting color features (CFs), texture features (TFs), and vegetation indices (VIs) of rice canopy using image processing techniques, three algorithms, namely, Support Vector Machine (SVM), Random Forest (RF), and Back Propagation Neural Network (BPNN), were utilized to establish a monitoring model for the severity levels of rice BLB. The classification results of several models are compared, with the overall Correct Identification Rate (CIR) of the three-feature fusion classification algorithm generally higher than the other two. Among the three algorithms, the RF algorithm performs the best, with a CIR reaching 93.4% and a Kappa coefficient of 0.91. The BPNN algorithm follows, with a CIR of 82.1% and a Kappa coefficient of 0.76, showing moderate effectiveness. Lastly, the SVM algorithm performs the poorest, with a CIR of 65.1% and a Kappa coefficient of 0.54. A rice BLB large-scale detection framework based on unmanned aerial vehicle (UAV) images was designed, and a graphical user interface (GUI) was developed using Python language to achieve automated processing from image input to final recognition results, achieving good results.

The use of UAVs to detect litchi in natural environments is imperative for rapid litchi yield estimation and automated harvesting systems. However, UAV-based lychee fruit detection bottlenecks arise from complex canopy architecture and leaf occlusion. This study proposed a collaborative optimization strategy integrating agronomic technique with deep learning. Three leaf thinning intensities (0, 6, and 12 compound leaves) were applied at the early stage of fruit to systematically evaluate their effects on fruit growth, canopy structure, and detection performance. Results indicated that moderate defoliation (six leaves) significantly enhanced canopy openness and light penetration without adversely impacting on yield and fruit quality. Subsequent UAV-based detection under moderate versus no defoliation treatment revealed that the YOLOv8-based model achieved significant performance gains: mean average precision (mAP) increased from 0.818 to 0.884, and the F1-score improved from 0.796 to 0.842. The study contributes a novel collaborative optimization strategy that effectively mitigates occlusion issues in fruit detection. This approach demonstrates that agronomic techniques can be strategically used to enhance AI perception, offering a significant step forward in the integration of agricultural machinery and agronomy for intelligent orchard systems.