Chong Yao

Introduction: Existing detection models for automatic tea-grade determination in open-field, complex habitats suffer from insufficient feature robustness, weak suppression of background interference, and difficulty in balancing lightweight design with accuracy. To address these limitations, this study proposes Tea-DETR, a model tailored for open-air tea garden scenarios based on the end-to-end RT-DETR detection paradigm. Methods: The proposed method enhances feature representation and attention allocation from two aspects: backbone optimization and feature interaction enhancement. First, a lightweight backbone module is designed to strengthen long-range dependency modeling and improve suppression of complex background interference, thereby enhancing the robustness and discriminability of multi-scale tea-leaf features under occlusion and illumination variations. Second, an efficient attention-enhancement mechanism is introduced to reduce redundant feature interactions and enable adaptive focus on critical target regions, improving the model’s ability to capture subtle semantic differences among tea grades while maintaining computational efficiency. To validate the approach, Anji white tea from Zhejiang Province was selected as the experimental subject, and a single-leaf tea dataset containing 6,542 images was constructed. The dataset was split into training, validation, and test sets at a ratio of 8:1:1, based on which comparative experiments and convergence analyses were conducted. Results: With the number of parameters reduced to 14.65M, Tea-DETR achieves an accuracy of 92.2% and improves mAP@0.5 to 82.0%, reducing parameters by 26.8% compared with the baseline model. In addition, Tea-DETR exhibits markedly improved convergence stability and substantially enhanced capability in distinguishing subtle semantic differences among tea grades, effectively alleviating ambiguous discrimination under complex backgrounds. Discussion: Overall, the proposed method enhances the stability of fine-grained feature capture for small tea-leaf targets in open-field environments while maintaining real-time inference efficiency, providing a robust solution for real-time, non-destructive automatic tea-grade determination in field scenarios.

As an important traditional Chinese medicinal herb, Paeoniae Radix Alba (white peony root, WP) not only has significant medicinal value in the field of Chinese medicine but is also widely used in food products and health supplements due to its food and medicine dual‐use properties. The quality of Paeoniae Radix Alba is crucial for its efficacy, safety, and effectiveness in food applications, making efficient inspection methods essential. The algorithm uses a self‐developed detection head (LSD‐Head) combined with a Feature Fusion Attention (FCA) mechanism for effective defect detection. Additionally, OpenCV technology is used to accurately measure the physical dimensions of the slices. Compared to the YOLOv8 model (76.4% precision, 63.7% recall, 70.1% mAP@0.5, 8.2 GFLOPs), the proposed model reduces parameter size by 13%, reaching only 65.8% of YOLOv8's size, while improving accuracy by 2.6%. For physical dimensions, the average error between the detected and actual sizes is controlled within 5%. Experimental results show that the proposed algorithm performs well in defect detection and accurately measures the area and maximum and minimum diameters of Paeoniae Radix Alba decoction pieces.

Pest infestations in rice crops greatly affect yield and quality, making early detection essential. As most rice pests affect leaves and rhizomes, visual inspection of rice for pests is becoming increasingly important. In precision agriculture, fast and accurate automatic pest identification is essential. To tackle this issue, multiple models utilizing computer vision and deep learning have been applied. Owing to its high efficiency, deep learning is now the favored approach for detecting plant pests. In this regard, the paper introduces an effective rice pest detection framework utilizing the Transformer architecture, designed to capture long-range features. The paper enhances the original model by adding the self-developed RepPConv-block to reduce the problem of information redundancy in feature extraction in the model backbone and to a certain extent reduce the model parameters. The original model’s CCFM structure is enhanced by integrating the Gold-YOLO neck, improving its ability to fuse multi-scale features. Additionally, the MPDIoU-based loss function enhances the model’s detection performance. Using the self-constructed high-quality rice pest dataset, the model achieves higher identification accuracy while reducing the number of parameters. The proposed RP18-DETR and RP34-DETR models reduce parameters by 16.5% and 25.8%, respectively, compared to the original RT18-DETR and RT34-DETR models. With a threshold of 0.5, the average accuracy calculated is 1.2% higher for RP18-DETR than for RT18-DETR.

The quantification of centipede populations is one of the key measures in achieving intelligent management of edible centipedes and promoting the upgrade of the rural centipede industry chain. However, current centipede counting techniques still face several challenges, including low detection accuracy, large model size, and difficulty in deployment on mobile devices. These challenges have limited existing network models to the experimental stage, preventing their practical application. To tackle the identified challenges, this study introduces a lightweight centipede detection model (FCM-YOLO), which enhances detection performance while ensuring fast processing and broad applicability. Based on the YOLOv5s framework, this model incorporates the C3FS module, resulting in fewer parameters and increased detection speed. Additionally, it integrates an attention module (CBAM) to suppress irrelevant information and improve target focus, thus enhancing detection accuracy. Furthermore, to enhance the precision of bounding box positioning, this study proposes a new loss function, CMPDIOU, for bounding box loss. Experimental results show that FCM-YOLO, while reducing parameter size, achieves an improved detection accuracy of 97.4% (2.7% higher than YOLOv5s) and reduces floating-point operations (FLOPs) to 11.5G (4.3G lower than YOLOv5s). In summary, this paper provides novel insights into the detection and enumeration of centipedes, contributing to the advancement of intelligent agricultural practices.

The utilization of target detection algorithms for counting edible centipedes represents a novel endeavor in the field of traditional Chinese medicine materials using deep learning. However, the accuracy of current target detection algorithms is relatively low due to the complexity of the centipede background and the density of the detection targets, making them poorly suited for practical application scenarios. To address this, this study proposes a centipede target detection algorithm based on an improved Your Only Look Once V5 (YOLOv5) model, termed FD-YOLO. This algorithm enhances the original model by incorporating the CBAM attention mechanism and the BiFormer universal visual transformer to suppress irrelevant information and intensify focus on the desired detection targets, thereby improving the precision of the algorithm. Additionally, the FD-YOLO algorithm enhances the model’s generalizability and robustness by improving the existing SPPF module. Experimental results demonstrate that compared to the original YOLOv5 prototype network, the improved YOLOv5 model has increased the AP@0.5 by 3.5%, reaching 97.2%, and raised the recall rate from 86.2% to 92.9%. Therefore, the enhanced YOLOv5 algorithm can effectively detect and count centipedes, making it more suitable for current practical application scenarios.