This study addresses the challenges of tomato maturity recognition in natural environments, such as occlusion caused by branches and leaves, and the difficulty in detecting stacked fruits. To overcome these issues, we propose a novel YOLOv8n-CA method for tomato maturity recognition, which defines four maturity stages: unripe, turning color, turning ripe, and fully ripe. The model is based on the YOLOv8n architecture, incorporating the coordinate attention (CA) mechanism into the backbone network to enhance the model’s ability to capture and express features of the tomato fruits. Additionally, the C2f-FN structure was utilized in both the backbone and neck networks to strengthen the model’s capacity to extract maturity-related features. The CARAFE up-sampling operator was integrated to expand the receptive field for improved feature fusion. Finally, the SIoU loss function was used to solve the problem of insufficient CIoU of the original loss function. Experimental results showed that the YOLOv8n-CA model had a parameter count of only 2.45 × 10⁶, computational complexity of 6.9 GFLOPs, and a weight file size of just 4.90 MB. The model achieved a mean average precision (mAP) of 97.3%. Compared to the YOLOv8n model, it reduced the model size slightly while improving accuracy by 1.3 percentage points. When compared to seven other models—Faster R-CNN, YOLOv3s, YOLOv5s, YOLOv5m, YOLOv7, YOLOv8n, YOLOv10s, and YOLOv11n—the YOLOv8n-CA model was the smallest in size and demonstrated superior detection performance.

To address the challenges of tomato maturity detection in natural environments—such as interference from complex backgrounds and the difficulty in distinguishing adjacent fruits with similar maturity levels—this study proposes a lightweight tomato maturity detection model, YOLOv8n-FDE. Four maturity stages are defined: mature, turning-mature, color-changing, and immature. The model incorporates a newly designed C3-FNet feature extraction and fusion module to enhance target feature representation, and integrates the DySample operator to improve adaptability under complex conditions. Furthermore, the detection head is optimized as the parameter-sharing lightweight detection head (PSLD), which boosts the accuracy of multi-scale tomato fruit feature prediction and precisely focuses on tomato color characteristics. A novel PIoUv2 loss function is also introduced to further improve localization performance and accelerate convergence. Experimental results demonstrate that the improved YOLOv8n-FDE model achieves a parameter count of 1.56 × 10⁶, computational complexity of 4.5 GFLOPs, and a model size of 3.20 MB. The model attains an mAP@0.5 of 97.6%, representing reductions of 46%, 21%, and 60% in parameter count, computation, and size, respectively, compared to YOLOv8n, with a 1.8 percentage point increase in mAP@0.5. This study significantly reduces model complexity and improves the accuracy of tomato maturity detection, providing a more robust data foundation for subsequent orchard yield prediction.

Improving sowing quality is crucial for ensuring wheat emergence and healthy growth. To address issues of poor wheat sowing quality, such as uneven sowing depth and inadequate soil coverage, in the Yangtze River Delta region of China, this study systematically analyzed the effects of the implement’s structural and operational parameters on sowing quality. Based on this analysis, a double-shaft rotary tillage and double-press seeder was designed. Protrusions on the grooving press roller are used to form seed furrows, rotary tiller blades cover the seeds with soil, and the rear press roller compacts the soil. DEM-MBD (discrete element method–multibody dynamics) coupled simulations, combined with single-factor and central composite design (CCD) experiments, were conducted with seeding depth as the evaluation index and four experimental factors: the protrusion height on the press grooving roller, forward speed, seed mass in the seed box, and straw mulching amount. The optimal protrusion height was 29 mm. The effects of rotary tiller blade working depth, rotational speed, and forward speed on soil-covering mass and its coefficient of variation were evaluated through discrete element method (DEM) simulations. The optimal working depth and rotational speed were found to be 55 mm and 350 r·min⁻¹, respectively, based on single-factor and Box–Behnken Design experiments. Field experiments based on optimized parameters showed results consistent with the simulations. The qualified rate of seeding depth decreased as forward speed increased. The optimal forward speed was 4.5 km·h⁻¹, at which the average seeding depth was 25.7 mm, the qualified seeding depth rate was 90%, the soil-covering mass within a 50 cm² area was 143.2 g, and the coefficient of variation was 13.21%, meeting the requirements for wheat sowing operations.

Accurate ripeness assessment of tomatoes in natural orchard settings is challenged by severe occlusion, dense clustering, and scale variation among fruits. This paper introduces YOLOv8n–TiD, a lightweight detection framework designed to overcome these obstacles. The architecture enhances the YOLOv8n backbone with a novel C2f-iRD module, which integrates re-parameterized dilated convolutions and inverted residual blocks to enlarge the receptive field while retaining fine-grained texture details. For feature fusion, we propose C2f-iRMB in the neck to ensure cross-scale consistency. To address semantic drift during upsampling, we replace standard interpolation with the DySample operator. The detection head is re-engineered as TADAH (Task-Adaptive Dynamic Alignment Head), enabling genuine task decoupling via deformable convolutions and conditionally shared features. Additionally, we introduce F–PIoUv2, a regression loss that emphasizes medium-quality predictions and curbs excessive bounding box expansion. Evaluations on a custom dataset show that YOLOv8n–TiD cuts parameters by 45%, FLOPs by 19%, and model size by 41%, while raising mAP@0.5 by 1.9 points—all in real time. On Android devices, it sustains 30 FPS inference and generalizes effectively to a distinct cherry tomato cultivar. These findings confirm the method’s robustness in discriminating occluded, small, and visually similar maturity stages, providing a practical vision system for robotic harvesting and field-based grading.