Accurate plant classification based on deep learning is important for precision agriculture, such as weed control, crop monitoring, and smart farming systems. The accuracies of deep learning models rely on datasets. Although many datasets have been proposed in recent decades, they have the common limitations in terms of scale, less environmental diversity, and challenges of data integration. To solve these problems, in this paper, we introduce a new dataset named OpenPlant, which is a large-scale and open dataset containing 635,176 RGB images across 1167 plant species. OpenPlant includes diverse growth stages of plants, plant structures, and environmental conditions, and its annotations were carefully verified to ensure quality. The proposed OpenPlant can be a benchmark for agricultural plant classification. In this paper, we benchmarked 10 widely used convolutional neural networks (CNNs), 6 vision transformers (ViTs), and 12 vision–language models (VLMs) to provide a comprehensive evaluation. The OpenPlant dataset offers a comprehensive benchmark for agricultural research using deep learning and the results provide insights into future directions.

Automatic reseeding in spoon-chain potato planters requires reliable classification of miss-seeding, normal, and multiple-seeding events. Oblique viewing and continuous spoon motion cause scale changes, boundary truncation, blur, and occlusion, which destabilize single-frame predictions. The proposed system treats each seed-spoon passage as one control event. It combines lightweight detection, track-level learning, and multi-frame classification with air-blow clearing and missed-seed reseeding. Based on the target-size distribution, the detector removes the P3 head from YOLOv8n and restores shallow details through space-to-depth rearrangement and gated addition. Frame quality combines boundary distance, sharpness, adjacent-box intersection over union, and box-area stability. High-quality frames form a track prototype, while low-quality frames receive stronger constraints. A quality-gated temporal network classifies each spoon as containing 0, 1, or at least 2 seed potatoes. Each model was trained with three random seeds under the same data split. Compared with YOLOv8n, the detector reduced the parameter count and computational cost by 35.8% and 48.3%, respectively. Track-level learning improved event accuracy by 3.67 percentage points over frame-level training. The seven-frame model achieved 93.41% event accuracy and 93.80% macro-F1. At 0.5 m/s, the closed-loop recognition, air-blow, and reseeding success rates were 93.7%, 96.4%, and 97.1%, respectively. These results provide a practical basis for real-time, event-level planting-quality control in spoon-chain potato planters.

Fast and accurate detection of missed and multiple seeding, followed by timely correction, is needed to maintain potato planting quality. Photoelectric, laser, capacitive, and machine vision methods have been developed for defect detection. Backup metering channels, catch-up compensation, in situ release, preparatory seed belts, and electric reseeding devices have also been used for correction. However, stable field use remains limited. Reported outcomes often cover detection accuracy, model performance, or single-action success, but end-to-end verification from defect detection through reseeding to outcome checking is not consistently available. Using a structured search of international and Chinese databases and citation screening, this review synthesized 88 publications published by 1 June 2026. The review compares the principles, reported performance, and operating conditions of the main detection methods and considers planting-quality control and reseeding in a broader agronomic context. Photoelectric and capacitive sensors generally produce clear event signals with simple processing. Machine vision provides more detailed class and position information but is more sensitive to lighting, occlusion, vibration, and computing delay. The analysis shows that high detection accuracy alone does not ensure reliable field correction. Performance also depends on sensor position, space-time matching, reseeding method, actuator response, and post-action checking. Future studies should use a wider set of metrics, conduct longer field tests under varied conditions, and improve the coordination of detection, control, actuation, and verification. These comparisons can inform sensor selection, correction-system design, and field evaluation protocols for potato seed-metering detection and reseeding systems.